Datasets:

librarian-bots

/

dataset_cards_with_metadata

like 11

Follow

Librarian Bots 74

codeparrot/github-code

codeparrot

--- annotations_creators: [] language_creators: - crowdsourced - expert-generated language: - code license: - other multilinguality: - multilingual pretty_name: github-code size_categories: - unknown source_datasets: [] task_categories: - text-generation task_ids: - language-modeling --- # GitHub Code Dataset ## Dataset Description The GitHub Code dataset consists of 115M code files from GitHub in 32 programming languages with 60 extensions totaling in 1TB of data. The dataset was created from the public GitHub dataset on Google BiqQuery. ### How to use it The GitHub Code dataset is a very large dataset so for most use cases it is recommended to make use of the streaming API of `datasets`. You can load and iterate through the dataset with the following two lines of code: ```python from datasets import load_dataset ds = load_dataset("codeparrot/github-code", streaming=True, split="train") print(next(iter(ds))) #OUTPUT: { 'code': "import mod189 from './mod189';\nvar value=mod189+1;\nexport default value;\n", 'repo_name': 'MirekSz/webpack-es6-ts', 'path': 'app/mods/mod190.js', 'language': 'JavaScript', 'license': 'isc', 'size': 73 } ``` You can see that besides the code, repo name, and path also the programming language, license, and the size of the file are part of the dataset. You can also filter the dataset for any subset of the 30 included languages (see the full list below) in the dataset. Just pass the list of languages as a list. E.g. if your dream is to build a Codex model for Dockerfiles use the following configuration: ```python ds = load_dataset("codeparrot/github-code", streaming=True, split="train", languages=["Dockerfile"]) print(next(iter(ds))["code"]) #OUTPUT: """\ FROM rockyluke/ubuntu:precise ENV DEBIAN_FRONTEND="noninteractive" \ TZ="Europe/Amsterdam" ... """ ``` We also have access to the license of the origin repo of a file so we can filter for licenses in the same way we filtered for languages: ```python ds = load_dataset("codeparrot/github-code", streaming=True, split="train", licenses=["mit", "isc"]) licenses = [] for element in iter(ds).take(10_000): licenses.append(element["license"]) print(Counter(licenses)) #OUTPUT: Counter({'mit': 9896, 'isc': 104}) ``` Naturally, you can also download the full dataset. Note that this will download ~300GB compressed text data and the uncompressed dataset will take up ~1TB of storage: ```python ds = load_dataset("codeparrot/github-code", split="train") ``` ## Data Structure ### Data Instances ```python { 'code': "import mod189 from './mod189';\nvar value=mod189+1;\nexport default value;\n", 'repo_name': 'MirekSz/webpack-es6-ts', 'path': 'app/mods/mod190.js', 'language': 'JavaScript', 'license': 'isc', 'size': 73 } ``` ### Data Fields |Field|Type|Description| |---|---|---| |code|string|content of source file| |repo_name|string|name of the GitHub repository| |path|string|path of file in GitHub repository| |language|string|programming language as inferred by extension| |license|string|license of GitHub repository| |size|int|size of source file in bytes| ### Data Splits The dataset only contains a train split. ## Languages The dataset contains 30 programming languages with over 60 extensions: ```python { "Assembly": [".asm"], "Batchfile": [".bat", ".cmd"], "C": [".c", ".h"], "C#": [".cs"], "C++": [".cpp", ".hpp", ".c++", ".h++", ".cc", ".hh", ".C", ".H"], "CMake": [".cmake"], "CSS": [".css"], "Dockerfile": [".dockerfile", "Dockerfile"], "FORTRAN": ['.f90', '.f', '.f03', '.f08', '.f77', '.f95', '.for', '.fpp'], "GO": [".go"], "Haskell": [".hs"], "HTML":[".html"], "Java": [".java"], "JavaScript": [".js"], "Julia": [".jl"], "Lua": [".lua"], "Makefile": ["Makefile"], "Markdown": [".md", ".markdown"], "PHP": [".php", ".php3", ".php4", ".php5", ".phps", ".phpt"], "Perl": [".pl", ".pm", ".pod", ".perl"], "PowerShell": ['.ps1', '.psd1', '.psm1'], "Python": [".py"], "Ruby": [".rb"], "Rust": [".rs"], "SQL": [".sql"], "Scala": [".scala"], "Shell": [".sh", ".bash", ".command", ".zsh"], "TypeScript": [".ts", ".tsx"], "TeX": [".tex"], "Visual Basic": [".vb"] } ``` ## Licenses Each example is also annotated with the license of the associated repository. There are in total 15 licenses: ```python [ 'mit', 'apache-2.0', 'gpl-3.0', 'gpl-2.0', 'bsd-3-clause', 'agpl-3.0', 'lgpl-3.0', 'lgpl-2.1', 'bsd-2-clause', 'cc0-1.0', 'epl-1.0', 'mpl-2.0', 'unlicense', 'isc', 'artistic-2.0' ] ``` ## Dataset Statistics The dataset contains 115M files and the sum of all the source code file sizes is 873 GB (note that the size of the dataset is larger due to the extra fields). A breakdown per language is given in the plot and table below:  | | Language |File Count| Size (GB)| |---:|:-------------|---------:|-------:| | 0 | Java | 19548190 | 107.70 | | 1 | C | 14143113 | 183.83 | | 2 | JavaScript | 11839883 | 87.82 | | 3 | HTML | 11178557 | 118.12 | | 4 | PHP | 11177610 | 61.41 | | 5 | Markdown | 8464626 | 23.09 | | 6 | C++ | 7380520 | 87.73 | | 7 | Python | 7226626 | 52.03 | | 8 | C# | 6811652 | 36.83 | | 9 | Ruby | 4473331 | 10.95 | | 10 | GO | 2265436 | 19.28 | | 11 | TypeScript | 1940406 | 24.59 | | 12 | CSS | 1734406 | 22.67 | | 13 | Shell | 1385648 | 3.01 | | 14 | Scala | 835755 | 3.87 | | 15 | Makefile | 679430 | 2.92 | | 16 | SQL | 656671 | 5.67 | | 17 | Lua | 578554 | 2.81 | | 18 | Perl | 497949 | 4.70 | | 19 | Dockerfile | 366505 | 0.71 | | 20 | Haskell | 340623 | 1.85 | | 21 | Rust | 322431 | 2.68 | | 22 | TeX | 251015 | 2.15 | | 23 | Batchfile | 236945 | 0.70 | | 24 | CMake | 175282 | 0.54 | | 25 | Visual Basic | 155652 | 1.91 | | 26 | FORTRAN | 142038 | 1.62 | | 27 | PowerShell | 136846 | 0.69 | | 28 | Assembly | 82905 | 0.78 | | 29 | Julia | 58317 | 0.29 | ## Dataset Creation The dataset was created in two steps: 1. Files of with the extensions given in the list above were retrieved from the GitHub dataset on BigQuery (full query [here](https://huggingface.co./datasets/codeparrot/github-code/blob/main/query.sql)). The query was executed on _Mar 16, 2022, 6:23:39 PM UTC+1_. 2. Files with lines longer than 1000 characters and duplicates (exact duplicates ignoring whitespaces) were dropped (full preprocessing script [here](https://huggingface.co./datasets/codeparrot/github-code/blob/main/github_preprocessing.py)). ## Considerations for Using the Data The dataset consists of source code from a wide range of repositories. As such they can potentially include harmful or biased code as well as sensitive information like passwords or usernames. ## Releases You can load any older version of the dataset with the `revision` argument: ```Python ds = load_dataset("codeparrot/github-code", revision="v1.0") ``` ### v1.0 - Initial release of dataset - The query was executed on _Feb 14, 2022, 12:03:16 PM UTC+1_ ### v1.1 - Fix missing Scala/TypeScript - Fix deduplication issue with inconsistent Python `hash` - The query was executed on _Mar 16, 2022, 6:23:39 PM UTC+1_

Sterzhang/PVIT-3M

Sterzhang

--- configs: - config_name: PVIT-3M data_files: - split: all_data path: PVIT-3M.json language: - en task_categories: - visual-question-answering - image-text-to-text tags: - multi-modal - personalized license: apache-2.0 pretty_name: personalized visual instruction tuning size_categories: - 1M<n<10M --- # PVIT-3M The paper titled "[**Personalized Visual Instruction Tuning**](https://arxiv.org/abs/2410.07113)" introduces a novel dataset called PVIT-3M. This dataset is specifically designed for tuning MLLMs in the context of personalized visual instruction tasks. The dataset consists of 3 million image-text pairs that aim to improve MLLMs' abilities to generate responses based on personalized visual inputs, making them more tailored and adaptable to individual user needs and preferences. Here’s the PVIT-3M statistics: <img width="900" alt="image" src="https://cdn-uploads.huggingface.co/production/uploads/65d8b0f0661492b25c6623de/BLF2Uo72nqpvjPv_yplbt.png"> ## Directory The images in the PVIT-3M dataset have been organized into 40 separate folders, each named pvit-3m_0 to pvit-3m_39. After downloading, you can combine all the subfolders for a unified dataset structure. ``` Sterzhang/PVIT-3M └─ image └─ pvit-3m_0 └─ aug-face └─ coco └─ concat-person └─ crop-face └─ flickr30k └─ object365 └─ vg └─ pvit-3m_1 └─ ... └─ ... └─ PVIT-3M.json └─ README.md ``` ## Json Structure The PVIT-3M.json file contains structured data for each conversation instance in the PVIT-3M dataset. Below is an outline of the key fields: - `image`: A list of image file paths related to the conversation. - `conversations`: A list of dictionaries, each representing a turn in the conversation. - `from`: `human` or `gpt`. - `value`: The content of the conversation. - `type`: A string indicating the type. ## Example Here is an example from the PVIT-3M: ```json { "image": [ "crop-face/object365/objects365_v2_01169026/2.jpg", "object365/objects365_v2_01169026.jpg" ], "conversations": [ { "from": "human", "value": "<image>\nThis is a photo of Erin.\n<image>\nHow does Erin look in this photo?" }, { "from": "gpt", "value": "Erin is a woman with short, brown hair. She is wearing a dark blue dress with short sleeves and a ruffled design. She has a pearl necklace and a watch on her left wrist. She is also wearing a ring on her left hand." } ], "type": "crop description" } ``` "crop-face/object365/objects365_v2_01169026/2.jpg": <img width="100" alt="image" src="https://cdn-uploads.huggingface.co/production/uploads/65d8b0f0661492b25c6623de/lJi0aDYE44wyGP2QMZ13W.png"> "object365/objects365_v2_01169026.jpg": <img width="400" alt="image" src="https://cdn-uploads.huggingface.co/production/uploads/65d8b0f0661492b25c6623de/RY_80A5rSOO1vv6A6CuJy.png"> ## Script The script processes conversation data in the **PVIT-3M** dataset by adding personalized wrapper tokens (`<person_s>` and `<person_e>`) around specific segments. This helps the model correctly associate personalized text and images with each individual, reducing ambiguity in multimodal training. ```python import json def process_image_description(text): segments = text.split('<image>\n') processed_segments = [] for i, segment in enumerate(segments): if i == 0: processed_segments.append(segment) elif i == len(segments) - 1: continue else: last_newline_index = segment.rfind('\n') if last_newline_index != -1: segment = segment[:last_newline_index] + '<person_e>' + segment[last_newline_index:] else: segment += '<person_e>' processed_segments.append(f'<person_s><image>\n{segment}') processed_segments.append(f"<image>\n{segments[-1]}") return ''.join(processed_segments) def process_conversation_data(input_path, output_path): with open(input_path, 'r', encoding='utf-8') as f: data = json.load(f) for item in data: conversation_value = item["conversations"][0]["value"] item["conversations"][0]["value"] = process_image_description(conversation_value) with open(output_path, 'w', encoding='utf-8') as f: json.dump(data, f, ensure_ascii=False, indent=4) input_file = "" output_file = "" process_conversation_data(input_file, output_file) ``` # Code Our code will be released in [PVIT](https://github.com/sterzhang/PVIT), containing scripts for generating PVIT dataset as well as our code for training. # Case Study <img width="1000" alt="image" src="https://github.com/user-attachments/assets/d50fa03f-fdb6-41ff-ab25-806578d29f3e"> # Citation Our paper is now available at: [https://arxiv.org/abs/2410.07113](https://arxiv.org/abs/2410.07113) ```bibtex @misc{pi2024personalizedvisualinstructiontuning, title={Personalized Visual Instruction Tuning}, author={Renjie Pi and Jianshu Zhang and Tianyang Han and Jipeng Zhang and Rui Pan and Tong Zhang}, year={2024}, eprint={2410.07113}, archivePrefix={arXiv}, primaryClass={cs.CV}, url={https://arxiv.org/abs/2410.07113}, }

common-canvas/commoncatalog-cc-by-nc-sa

common-canvas

--- license: cc-by-nc-sa-4.0 dataset_info: features: - name: jpg dtype: image - name: blip2_caption dtype: string - name: caption dtype: string - name: licensename dtype: string - name: licenseurl dtype: string - name: width dtype: int32 - name: height dtype: int32 - name: original_width dtype: int32 - name: original_height dtype: int32 - name: photoid dtype: int64 - name: uid dtype: string - name: unickname dtype: string - name: datetaken dtype: timestamp[us] - name: dateuploaded dtype: int64 - name: capturedevice dtype: string - name: title dtype: string - name: usertags dtype: string - name: machinetags dtype: string - name: longitude dtype: float64 - name: latitude dtype: float64 - name: accuracy dtype: int64 - name: pageurl dtype: string - name: downloadurl dtype: string - name: serverid dtype: int64 - name: farmid dtype: int64 - name: secret dtype: string - name: secretoriginal dtype: string - name: ext dtype: string - name: url dtype: string - name: key dtype: string - name: status dtype: string - name: error_message dtype: string - name: exif dtype: string - name: sha256 dtype: string - name: description dtype: string task_categories: - text-to-image language: - en --- # Dataset Card for CommonCatalog CC-BY-NC-SA This dataset is a large collection of high-resolution Creative Common images (composed of different licenses, see paper Table 1 in the Appendix) collected in 2014 from users of Yahoo Flickr. The dataset contains images of up to 4k resolution, making this one of the highest resolution captioned image datasets. ## Dataset Details ### Dataset Description We provide captions synthetic captions to approximately 100 million high resolution images collected from Yahoo Flickr Creative Commons (YFCC). - **Curated by:** Aaron Gokaslan - **Language(s) (NLP):** en - **License:** See relevant yaml tag / dataset name. ### Dataset Sources <!-- Provide the basic links for the dataset. --> - **Repository:** https://github.com/mosaicml/diffusion - **Paper:** https://arxiv.org/abs/2310.16825 - **Demo:** See CommonCanvas Gradios ## Uses We use CommonCatalog to train a family latent diffusion models called CommonCanvas. The goal is to produce a model that is competitive with Stable Diffusion 2, but to do so using an easily accessible dataset of known provenance. Doing so makes replicating the model significantly easier, and provides a clearer mechanism for applying training-data attribution techniques. ### Direct Use Training text-to-image models Training image-to-text models ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the dataset will not work well for. --> * Commercial use * Crafting content that is offensive or injurious towards individuals, including negative portrayals of their living conditions, cultural backgrounds, religious beliefs, etc. * Deliberately creating or spreading content that is discriminatory or reinforces harmful stereotypes. * Falsely representing individuals without their permission. * Generating sexual content that may be seen by individuals without their consent. * Producing or disseminating false or misleading information. * Creating content that depicts extreme violence or bloodshed. * Distributing content that modifies copyrighted or licensed material in a way that breaches its usage terms. ## Dataset Structure The dataset is divided into 10 subsets each containing parquets about 4GB each. Each subfolder within contains a resolution range of the images and their respective aspect ratios. The dataset is also divided along images licensed for commercial use (C) and those that are not (NC). ## Dataset Creation ### Curation Rationale Creating a standardized, accessible dataset with synthetic caption and releasing it so other people can train on a common dataset for open source image generation. ### Source Data Yahoo Flickr Creative Commons 100M Dataset and Synthetically Generated Caption Data. #### Data Collection and Processing All synthetic captions were generated with BLIP2. See paper for more details. #### Who are the source data producers? <!-- This section describes the people or systems who originally created the data. It should also include self-reported demographic or identity information for the source data creators if this information is available. --> Users of Flickr ## Bias, Risks, and Limitations See Yahoo Flickr Creative Commons 100M dataset for more information. The information was collected circa 2014 and known to have a bias towards internet connected Western countries. Some areas such as the global south lack representation. ## Citation **BibTeX:** ``` @article{gokaslan2023commoncanvas, title={CommonCanvas: An Open Diffusion Model Trained with Creative-Commons Images}, author={Gokaslan, Aaron and Cooper, A Feder and Collins, Jasmine and Seguin, Landan and Jacobson, Austin and Patel, Mihir and Frankle, Jonathan and Stephenson, Cory and Kuleshov, Volodymyr}, journal={arXiv preprint arXiv:2310.16825}, year={2023} } ``` ## Dataset Card Authors [Aaron Gokaslan](https://huggingface.co./Skylion007) ## Dataset Card Contact [Aaron Gokaslan](https://huggingface.co./Skylion007)

CohereForAI/aya_collection

CohereForAI

--- language: - ace - afr - amh - ara - aze - ban - bbc - bel - bem - ben - bjn - bul - cat - ceb - ces - cym - dan - deu - ell - eng - epo - est - eus - fil - fin - fon - fra - gla - gle - glg - guj - hat - hau - heb - hin - hrv - hun - hye - ibo - ind - isl - ita - jav - jpn - kan - kas - kat - kau - kaz - khm - kin - kir - kor - kur - lao - lav - lij - lit - ltz - mad - mal - man - mar - min - mkd - mlg - mlt - mon - mri - msa - mya - nep - nij - nld - nor - nso - nya - pan - pes - pol - por - pus - ron - rus - sin - slk - slv - smo - sna - snd - som - sot - spa - sqi - srp - sun - swa - swe - tam - taq - tel - tgk - tha - tur - twi - ukr - urd - uzb - vie - wol - xho - yid - yor - zho - zul license: apache-2.0 size_categories: - 100M<n<1B task_categories: - text-classification - summarization - translation pretty_name: Aya Collection dataset_info: - config_name: aya_dataset features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: train num_bytes: 245523658 num_examples: 202364 download_size: 134230030 dataset_size: 245523658 - config_name: templated_afriqa features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: test num_bytes: 1053208.8833372337 num_examples: 6834 - name: train num_bytes: 785976.7786098759 num_examples: 5100 - name: validation num_bytes: 794915.3380528903 num_examples: 5158 download_size: 945238 dataset_size: 2634101.0 - config_name: templated_afrisenti features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: test num_bytes: 13970874.910620399 num_examples: 42576 - name: train num_bytes: 32313882.88468279 num_examples: 98476 - name: validation num_bytes: 6141462.204696811 num_examples: 18716 download_size: 13309887 dataset_size: 52426220.0 - config_name: templated_amharic_qa features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: test num_bytes: 1563941.8685517767 num_examples: 523 - name: train num_bytes: 5475291.704241497 num_examples: 1831 - name: validation num_bytes: 786456.4272067252 num_examples: 263 download_size: 3648433 dataset_size: 7825689.999999999 - config_name: templated_armenian_instruct features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: test num_bytes: 1864796.3648305084 num_examples: 3063 - name: train num_bytes: 2445604.6351694916 num_examples: 4017 download_size: 1825641 dataset_size: 4310401.0 - config_name: templated_bengali_news features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: train num_bytes: 14242457 num_examples: 19096 download_size: 4609132 dataset_size: 14242457 - config_name: templated_dutch_imdb features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: test num_bytes: 39967063.5 num_examples: 24992 - name: train num_bytes: 39967063.5 num_examples: 24992 download_size: 44533807 dataset_size: 79934127.0 - config_name: templated_hindi_headline features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: test num_bytes: 228788501.12729776 num_examples: 23452 - name: train num_bytes: 919144047.8727022 num_examples: 94217 download_size: 243324488 dataset_size: 1147932549.0 - config_name: templated_hindi_news features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: test num_bytes: 109524809.11948325 num_examples: 10655 - name: train num_bytes: 437112433.88051677 num_examples: 42524 download_size: 112865381 dataset_size: 546637243.0 - config_name: templated_indic_paraphrase features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: train num_bytes: 5340504 num_examples: 7523 download_size: 1724626 dataset_size: 5340504 - config_name: templated_indic_sentiment features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: train num_bytes: 7496187 num_examples: 11559 download_size: 3003109 dataset_size: 7496187 - config_name: templated_indo_stories features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: train num_bytes: 2042351 num_examples: 2599 download_size: 813713 dataset_size: 2042351 - config_name: templated_japanese_instruct features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: train num_bytes: 1345341895 num_examples: 2463624 download_size: 580330810 dataset_size: 1345341895 - config_name: templated_joke_explaination features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: train num_bytes: 591008 num_examples: 754 download_size: 157851 dataset_size: 591008 - config_name: templated_ligurian_news features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: validation num_bytes: 105221.25 num_examples: 54 - name: test num_bytes: 140295.0 num_examples: 72 - name: train num_bytes: 596253.75 num_examples: 306 download_size: 546344 dataset_size: 841770.0 - config_name: templated_masakhanews features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: test num_bytes: 31426840.99009901 num_examples: 9240 - name: train num_bytes: 109538186.24752475 num_examples: 32206 - name: validation num_bytes: 15679408.762376238 num_examples: 4610 download_size: 86433056 dataset_size: 156644436.0 - config_name: templated_mintaka features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: test num_bytes: 41153051.4 num_examples: 156000 - name: train num_bytes: 144035679.9 num_examples: 546000 - name: validation num_bytes: 20576525.7 num_examples: 78000 download_size: 43108344 dataset_size: 205765257.0 - config_name: templated_ntx_llm features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: train num_bytes: 10019994 num_examples: 5983 download_size: 1037270 dataset_size: 10019994 - config_name: templated_nusax_senti features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: test num_bytes: 2684840.4 num_examples: 8000 - name: train num_bytes: 3356050.5 num_examples: 10000 - name: validation num_bytes: 671210.1 num_examples: 2000 download_size: 2336444 dataset_size: 6712101.0 - config_name: templated_persian_farstail features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: test num_bytes: 731412.1801486664 num_examples: 1029 - name: train num_bytes: 3424629.62483603 num_examples: 4818 - name: validation num_bytes: 720750.1950153039 num_examples: 1014 download_size: 1417008 dataset_size: 4876792.0 - config_name: templated_persian_instruct features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: test num_bytes: 38518994.420354694 num_examples: 11186 - name: train num_bytes: 564885564.1599021 num_examples: 164044 - name: validation num_bytes: 38512107.41974315 num_examples: 11184 download_size: 280563392 dataset_size: 641916666.0 - config_name: templated_scirepeval features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: validation num_bytes: 53956804 num_examples: 32973 download_size: 27742964 dataset_size: 53956804 - config_name: templated_seed_instruct features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: validation num_bytes: 186542.23316647828 num_examples: 380 - name: test num_bytes: 197342.04666559017 num_examples: 402 - name: train num_bytes: 5696410.720167931 num_examples: 11604 download_size: 2674875 dataset_size: 6080295.0 - config_name: templated_soda features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: test num_bytes: 487742788.92976975 num_examples: 595872 - name: train num_bytes: 2519225981.566041 num_examples: 3077721 - name: validation num_bytes: 479157981.5041894 num_examples: 585384 download_size: 1668121549 dataset_size: 3486126752.0 - config_name: templated_tamil_stories features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: train num_bytes: 14555943 num_examples: 1202 download_size: 4912529 dataset_size: 14555943 - config_name: templated_tamil_thirukkural features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: train num_bytes: 7722387 num_examples: 3990 download_size: 1441119 dataset_size: 7722387 - config_name: templated_telugu_food features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: train num_bytes: 1108509 num_examples: 441 download_size: 312391 dataset_size: 1108509 - config_name: templated_telugu_jokes features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: train num_bytes: 966698 num_examples: 929 download_size: 298210 dataset_size: 966698 - config_name: templated_telugu_news features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: train num_bytes: 1150840295 num_examples: 467090 download_size: 423260269 dataset_size: 1150840295 - config_name: templated_telugu_poems features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: train num_bytes: 8244805 num_examples: 5115 download_size: 2713433 dataset_size: 8244805 - config_name: templated_telugu_riddles features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: train num_bytes: 339040 num_examples: 844 download_size: 79031 dataset_size: 339040 - config_name: templated_thai_pos features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: test num_bytes: 319580.309461865 num_examples: 1000 - name: train num_bytes: 41690529.69053814 num_examples: 130454 download_size: 7405764 dataset_size: 42010110.0 - config_name: templated_thai_scb features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: test num_bytes: 131923007.25034823 num_examples: 177862 - name: train num_bytes: 1188824615.223528 num_examples: 1602804 - name: validation num_bytes: 131917073.5261238 num_examples: 177854 download_size: 441007386 dataset_size: 1452664696.0 - config_name: templated_thai_usembassy features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: train num_bytes: 10002322 num_examples: 1230 download_size: 3958145 dataset_size: 10002322 - config_name: templated_thai_wikitionary features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: train num_bytes: 12238652 num_examples: 19729 download_size: 2641369 dataset_size: 12238652 - config_name: templated_turku_paraphrase features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: test num_bytes: 9449925.655740838 num_examples: 31413 - name: train num_bytes: 75488399.52960008 num_examples: 250935 - name: validation num_bytes: 9502269.814659085 num_examples: 31587 download_size: 28908781 dataset_size: 94440595.00000001 - config_name: templated_ukranian_gec features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: train num_bytes: 21369624 num_examples: 29958 download_size: 9511988 dataset_size: 21369624 - config_name: templated_uner_llm features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: train num_bytes: 59421032.72376601 num_examples: 54957 - name: test num_bytes: 16164354.663105734 num_examples: 14950 - name: validation num_bytes: 8420601.613128258 num_examples: 7788 download_size: 12453483 dataset_size: 84005989.0 - config_name: templated_urdu_news_category features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: test num_bytes: 29923228.33936761 num_examples: 11187 - name: train num_bytes: 269284981.6606324 num_examples: 100674 download_size: 118185925 dataset_size: 299208210.0 - config_name: templated_urdu_news_gen features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: test num_bytes: 29497844.81704079 num_examples: 11187 - name: train num_bytes: 265456872.1829592 num_examples: 100674 download_size: 123276747 dataset_size: 294954717.0 - config_name: templated_urdu_news_headline features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: test num_bytes: 29258423.35545901 num_examples: 11187 - name: train num_bytes: 263302271.644541 num_examples: 100674 download_size: 123095949 dataset_size: 292560695.0 - config_name: templated_wiki_split features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: test num_bytes: 4608986.773259303 num_examples: 10000 - name: train num_bytes: 912527760.4534814 num_examples: 1979888 - name: validation num_bytes: 4608986.773259303 num_examples: 10000 download_size: 395631256 dataset_size: 921745734.0 - config_name: templated_xcsqa features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: validation num_bytes: 6315047.0 num_examples: 17000 download_size: 2125506 dataset_size: 6315047.0 - config_name: templated_xlel_wd features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: test num_bytes: 493033268.5027245 num_examples: 621319 - name: train num_bytes: 3671177872.612755 num_examples: 4626407 - name: validation num_bytes: 420416838.88452065 num_examples: 529808 download_size: 2363004380 dataset_size: 4584627980.0 - config_name: templated_xwikis features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: test num_bytes: 219985468.96557257 num_examples: 34987 - name: train num_bytes: 8995693557.81201 num_examples: 1430696 - name: validation num_bytes: 251360765.22241676 num_examples: 39977 download_size: 5713306872 dataset_size: 9467039791.999998 - config_name: translated_adversarial_qa features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: script dtype: string - name: split dtype: string splits: - name: test num_bytes: 167379954.08333334 num_examples: 119000 - name: train num_bytes: 1673799540.8333333 num_examples: 1190000 - name: validation num_bytes: 167379954.08333334 num_examples: 119000 download_size: 595462085 dataset_size: 2008559448.9999998 - config_name: translated_cnn_dailymail features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: script dtype: string - name: split dtype: string splits: - name: test num_bytes: 4825107898.98773 num_examples: 1378800 - name: train num_bytes: 41993976492.495476 num_examples: 12000000 - name: validation num_bytes: 5613754777.516795 num_examples: 1604160 download_size: 25383694727 dataset_size: 52432839169.0 - config_name: translated_dolly features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: split dtype: string - name: script dtype: string splits: - name: train num_bytes: 2188278931 num_examples: 1762152 download_size: 1089137630 dataset_size: 2188278931 - config_name: translated_flan_coqa features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: script dtype: string - name: split dtype: string splits: - name: train num_bytes: 2884413536 num_examples: 762671 download_size: 1416350365 dataset_size: 2884413536 - config_name: translated_flan_cot features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: script dtype: string - name: split dtype: string splits: - name: train num_bytes: 7470682150.0 num_examples: 11029200 download_size: 3086804878 dataset_size: 7470682150.0 - config_name: translated_flan_gem_wiki features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: script dtype: string - name: split dtype: string splits: - name: train num_bytes: 11446176046 num_examples: 3230493 download_size: 5342129672 dataset_size: 11446176046 - config_name: translated_flan_lambada features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: script dtype: string - name: split dtype: string splits: - name: train num_bytes: 223527122 num_examples: 509201 download_size: 99315916 dataset_size: 223527122 - config_name: translated_flan_qa features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: script dtype: string - name: split dtype: string splits: - name: train num_bytes: 34188800 num_examples: 64260 download_size: 14245088 dataset_size: 34188800 - config_name: translated_hotpotqa features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: script dtype: string - name: split dtype: string splits: - name: train num_bytes: 13234982265.87797 num_examples: 42301644 - name: validation num_bytes: 833990488.1220294 num_examples: 2665600 download_size: 4862020346 dataset_size: 14068972754.0 - config_name: translated_joke_explaination features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: script dtype: string - name: split dtype: string splits: - name: train num_bytes: 96548938 num_examples: 89726 download_size: 40366737 dataset_size: 96548938 - config_name: translated_mintaka features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: script dtype: string - name: split dtype: string splits: - name: test num_bytes: 131276187.4 num_examples: 476000 - name: train num_bytes: 459466655.9 num_examples: 1666000 - name: validation num_bytes: 65638093.7 num_examples: 238000 download_size: 130340546 dataset_size: 656380937.0 - config_name: translated_mlqa features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: script dtype: string - name: split dtype: string splits: - name: test num_bytes: 3730486242.0756793 num_examples: 2746830 - name: validation num_bytes: 369508041.92432094 num_examples: 272076 download_size: 1662296336 dataset_size: 4099994284.0 - config_name: translated_nqopen features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: script dtype: string - name: split dtype: string splits: - name: train num_bytes: 4456165405.095046 num_examples: 20926150 - name: validation num_bytes: 182959989.9049544 num_examples: 859180 download_size: 1482593128 dataset_size: 4639125395.0 - config_name: translated_paws features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: script dtype: string - name: split dtype: string splits: - name: test num_bytes: 536748719.07157385 num_examples: 952000 - name: train num_bytes: 3314490433.8568525 num_examples: 5878719 - name: validation num_bytes: 536748719.07157385 num_examples: 952000 download_size: 686023556 dataset_size: 4387987872.0 - config_name: translated_piqa features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: script dtype: string - name: split dtype: string splits: - name: train num_bytes: 1324751595.2891204 num_examples: 1917447 - name: validation num_bytes: 151113599.71087962 num_examples: 218722 download_size: 504206733 dataset_size: 1475865195.0 - config_name: translated_soda features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: script dtype: string - name: split dtype: string splits: - name: test num_bytes: 9332736341.158312 num_examples: 17876160 - name: validation num_bytes: 9168469957.193184 num_examples: 17561520 - name: train num_bytes: 74651741547.6485 num_examples: 142989840 download_size: 32022718450 dataset_size: 93152947846.0 - config_name: translated_wiki_split features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: script dtype: string - name: split dtype: string splits: - name: train num_bytes: 72471632064.9965 num_examples: 117803336 - name: validation num_bytes: 366039049.0017441 num_examples: 595000 - name: test num_bytes: 366039049.0017441 num_examples: 595000 download_size: 27980267627 dataset_size: 73203710163.0 - config_name: translated_wikiqa features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: script dtype: string - name: split dtype: string splits: - name: test num_bytes: 15512870.67820774 num_examples: 34867 - name: train num_bytes: 55062749.16496945 num_examples: 123760 - name: validation num_bytes: 7412293.156822811 num_examples: 16660 download_size: 32773189 dataset_size: 77987913.00000001 - config_name: translated_xlel_wd features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: dataset_name dtype: string - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: template_id dtype: int64 - name: language dtype: string - name: script dtype: string - name: split dtype: string splits: - name: test num_bytes: 8449087876.213723 num_examples: 8755108 - name: validation num_bytes: 7326325551.677284 num_examples: 7591680 - name: train num_bytes: 60579299633.10899 num_examples: 62773440 download_size: 35927637128 dataset_size: 76354713061.0 configs: - config_name: aya_dataset data_files: - split: train path: aya_dataset/train-* - config_name: templated_afriqa data_files: - split: test path: templated_afriqa/test-* - split: train path: templated_afriqa/train-* - split: validation path: templated_afriqa/validation-* - config_name: templated_afrisenti data_files: - split: test path: templated_afrisenti/test-* - split: train path: templated_afrisenti/train-* - split: validation path: templated_afrisenti/validation-* - config_name: templated_amharic_qa data_files: - split: test path: templated_amharic_qa/test-* - split: train path: templated_amharic_qa/train-* - split: validation path: templated_amharic_qa/validation-* - config_name: templated_armenian_instruct data_files: - split: test path: templated_armenian_instruct/test-* - split: train path: templated_armenian_instruct/train-* - config_name: templated_bengali_news data_files: - split: train path: templated_bengali_news/train-* - config_name: templated_dutch_imdb data_files: - split: test path: templated_dutch_imdb/test-* - split: train path: templated_dutch_imdb/train-* - config_name: templated_hindi_headline data_files: - split: test path: templated_hindi_headline/test-* - split: train path: templated_hindi_headline/train-* - config_name: templated_hindi_news data_files: - split: test path: templated_hindi_news/test-* - split: train path: templated_hindi_news/train-* - config_name: templated_indic_paraphrase data_files: - split: train path: templated_indic_paraphrase/train-* - config_name: templated_indic_sentiment data_files: - split: train path: templated_indic_sentiment/train-* - config_name: templated_indo_stories data_files: - split: train path: templated_indo_stories/train-* - config_name: templated_japanese_instruct data_files: - split: train path: templated_japanese_instruct/train-* - config_name: templated_joke_explaination data_files: - split: train path: templated_joke_explaination/train-* - config_name: templated_ligurian_news data_files: - split: validation path: templated_ligurian_news/validation-* - split: test path: templated_ligurian_news/test-* - split: train path: templated_ligurian_news/train-* - config_name: templated_masakhanews data_files: - split: test path: templated_masakhanews/test-* - split: train path: templated_masakhanews/train-* - split: validation path: templated_masakhanews/validation-* - config_name: templated_mintaka data_files: - split: test path: templated_mintaka/test-* - split: train path: templated_mintaka/train-* - split: validation path: templated_mintaka/validation-* - config_name: templated_ntx_llm data_files: - split: train path: templated_ntx_llm/train-* - config_name: templated_nusax_senti data_files: - split: test path: templated_nusax_senti/test-* - split: train path: templated_nusax_senti/train-* - split: validation path: templated_nusax_senti/validation-* - config_name: templated_persian_farstail data_files: - split: test path: templated_persian_farstail/test-* - split: train path: templated_persian_farstail/train-* - split: validation path: templated_persian_farstail/validation-* - config_name: templated_persian_instruct data_files: - split: test path: templated_persian_instruct/test-* - split: train path: templated_persian_instruct/train-* - split: validation path: templated_persian_instruct/validation-* - config_name: templated_scirepeval data_files: - split: validation path: templated_scirepeval/validation-* - config_name: templated_seed_instruct data_files: - split: validation path: templated_seed_instruct/validation-* - split: test path: templated_seed_instruct/test-* - split: train path: templated_seed_instruct/train-* - config_name: templated_soda data_files: - split: test path: templated_soda/test-* - split: train path: templated_soda/train-* - split: validation path: templated_soda/validation-* - config_name: templated_tamil_stories data_files: - split: train path: templated_tamil_stories/train-* - config_name: templated_tamil_thirukkural data_files: - split: train path: templated_tamil_thirukkural/train-* - config_name: templated_telugu_food data_files: - split: train path: templated_telugu_food/train-* - config_name: templated_telugu_jokes data_files: - split: train path: templated_telugu_jokes/train-* - config_name: templated_telugu_news data_files: - split: train path: templated_telugu_news/train-* - config_name: templated_telugu_poems data_files: - split: train path: templated_telugu_poems/train-* - config_name: templated_telugu_riddles data_files: - split: train path: templated_telugu_riddles/train-* - config_name: templated_thai_pos data_files: - split: test path: templated_thai_pos/test-* - split: train path: templated_thai_pos/train-* - config_name: templated_thai_scb data_files: - split: test path: templated_thai_scb/test-* - split: train path: templated_thai_scb/train-* - split: validation path: templated_thai_scb/validation-* - config_name: templated_thai_usembassy data_files: - split: train path: templated_thai_usembassy/train-* - config_name: templated_thai_wikitionary data_files: - split: train path: templated_thai_wikitionary/train-* - config_name: templated_turku_paraphrase data_files: - split: test path: templated_turku_paraphrase/test-* - split: train path: templated_turku_paraphrase/train-* - split: validation path: templated_turku_paraphrase/validation-* - config_name: templated_ukranian_gec data_files: - split: train path: templated_ukranian_gec/train-* - config_name: templated_uner_llm data_files: - split: train path: templated_uner_llm/train-* - split: test path: templated_uner_llm/test-* - split: validation path: templated_uner_llm/validation-* - config_name: templated_urdu_news_category data_files: - split: test path: templated_urdu_news_category/test-* - split: train path: templated_urdu_news_category/train-* - config_name: templated_urdu_news_gen data_files: - split: test path: templated_urdu_news_gen/test-* - split: train path: templated_urdu_news_gen/train-* - config_name: templated_urdu_news_headline data_files: - split: test path: templated_urdu_news_headline/test-* - split: train path: templated_urdu_news_headline/train-* - config_name: templated_wiki_split data_files: - split: test path: templated_wiki_split/test-* - split: train path: templated_wiki_split/train-* - split: validation path: templated_wiki_split/validation-* - config_name: templated_xcsqa data_files: - split: validation path: templated_xcsqa/validation-* - config_name: templated_xlel_wd data_files: - split: test path: templated_xlel_wd/test-* - split: train path: templated_xlel_wd/train-* - split: validation path: templated_xlel_wd/validation-* - config_name: templated_xwikis data_files: - split: test path: templated_xwikis/test-* - split: train path: templated_xwikis/train-* - split: validation path: templated_xwikis/validation-* - config_name: translated_adversarial_qa data_files: - split: test path: translated_adversarial_qa/test-* - split: train path: translated_adversarial_qa/train-* - split: validation path: translated_adversarial_qa/validation-* - config_name: translated_cnn_dailymail data_files: - split: test path: translated_cnn_dailymail/test-* - split: train path: translated_cnn_dailymail/train-* - split: validation path: translated_cnn_dailymail/validation-* - config_name: translated_dolly data_files: - split: train path: translated_dolly/train-* - config_name: translated_flan_coqa data_files: - split: train path: translated_flan_coqa/train-* - config_name: translated_flan_cot data_files: - split: train path: translated_flan_cot/train-* - config_name: translated_flan_gem_wiki data_files: - split: train path: translated_flan_gem_wiki/train-* - config_name: translated_flan_lambada data_files: - split: train path: translated_flan_lambada/train-* - config_name: translated_flan_qa data_files: - split: train path: translated_flan_qa/train-* - config_name: translated_hotpotqa data_files: - split: train path: translated_hotpotqa/train-* - split: validation path: translated_hotpotqa/validation-* - config_name: translated_joke_explaination data_files: - split: train path: translated_joke_explaination/train-* - config_name: translated_mintaka data_files: - split: test path: translated_mintaka/test-* - split: train path: translated_mintaka/train-* - split: validation path: translated_mintaka/validation-* - config_name: translated_mlqa data_files: - split: test path: translated_mlqa/test-* - split: validation path: translated_mlqa/validation-* - config_name: translated_nqopen data_files: - split: train path: translated_nqopen/train-* - split: validation path: translated_nqopen/validation-* - config_name: translated_paws data_files: - split: test path: translated_paws/test-* - split: train path: translated_paws/train-* - split: validation path: translated_paws/validation-* - config_name: translated_piqa data_files: - split: train path: translated_piqa/train-* - split: validation path: translated_piqa/validation-* - config_name: translated_soda data_files: - split: test path: translated_soda/test-* - split: validation path: translated_soda/validation-* - split: train path: translated_soda/train-* - config_name: translated_wiki_split data_files: - split: test path: translated_wiki_split/test-* - split: train path: translated_wiki_split/train-* - split: validation path: translated_wiki_split/validation-* - config_name: translated_wikiqa data_files: - split: test path: translated_wikiqa/test-* - split: train path: translated_wikiqa/train-* - split: validation path: translated_wikiqa/validation-* - config_name: translated_xlel_wd data_files: - split: test path: translated_xlel_wd/test-* - split: validation path: translated_xlel_wd/validation-* - split: train path: translated_xlel_wd/train-* ---  ****This dataset is uploaded in two places: here and additionally [here](https://huggingface.co./datasets/CohereForAI/aya_collection_language_split) as 'Aya Collection Language Split.' These datasets are identical in content but differ in structure of upload. This dataset is structured by folders split according to dataset name. The version [here](https://huggingface.co./datasets/CohereForAI/aya_collection_language_split) instead divides the Aya collection into folders split by language. We recommend you use the language split version if you are only interested in downloading data for a single or smaller set of languages, and this version if you want to download dataset according to data source or the entire collection.**** # Dataset Summary The Aya Collection is a massive multilingual collection consisting of 513 million instances of prompts and completions covering a wide range of tasks. This collection incorporates instruction-style templates from fluent speakers and applies them to a curated list of datasets, as well as translations of instruction-style datasets into 101 languages. Aya Dataset, a human-curated multilingual instruction and response dataset, is also part of this collection. See our paper for more details regarding the collection. - **Curated by:** Contributors of [Aya Open Science Intiative](https://cohere.com/research/aya) - **Language(s):** 115 languages - **License:** [Apache 2.0](https://opensource.org/license/apache-2-0) - **Aya Datasets Family:** | Name | Explanation | |------|--------------| | [aya_dataset](https://huggingface.co./datasets/CohereForAI/aya_dataset) | Human-annotated multilingual instruction finetuning dataset, comprising over 204K instances across 65 languages. | | [aya_collection](https://huggingface.co./datasets/CohereForAI/aya_collection) | Created by applying instruction-style templates from fluent speakers to 44 datasets, including translations of 19 instruction-style datasets into 101 languages. This collection structured based on dataset level subsets. An alternative version of the collection structured by language subsets is also available.| | [aya_collection_language_split](https://huggingface.co./datasets/CohereForAI/aya_collection_language_split) | Aya Collection structured based on language level subsets. | | [aya_evaluation_suite](https://huggingface.co./datasets/CohereForAI/aya_evaluation_suite) | A diverse evaluation set for multilingual open-ended generation, featuring 250 culturally grounded prompts in 7 languages, 200 translated prompts in 24 languages, and human-edited versions selected for cross-cultural relevance from English Dolly in 6 languages.| | [aya_redteaming](https://huggingface.co./datasets/CohereForAI/aya_redteaming)| A red-teaming dataset consisting of harmful prompts in 8 languages across 9 different categories of harm with explicit labels for "global" and "local" harm.| # Dataset The `Aya Collection` is a comprehensive, large corpus of datasets that can be used by researchers around the world to train multilingual models. Our goal is only to include datasets with permissive licensing for manipulation and redistribution. The `Aya Collection` consists of three different sources of data: 1. Templated data: We collaborated with fluent speakers to create templates that allowed for the automatic expansion of existing datasets into various languages. 2. Translated data: We translated a hand-selected subset of 19 datasets into 101 languages (114 dialects) using the NLLB 3.3B parameter machine translation model. 3. Aya Dataset: We release the [Aya Dataset](https://huggingface.co./datasets/CohereForAI/aya_dataset) as a subset of the overall collection. This is the only dataset in the collection that is human-annotated in its entirety. ## Load with Datasets To load this dataset with Datasets, you'll need to install Datasets as `pip install datasets --upgrade` and then use the following code: ```python from datasets import load_dataset dataset = load_dataset("CohereForAI/aya_collection", "templated_mintaka") ``` In the above code snippet, "templated_mintaka" refers to a subset of the aya_collection. You can load other subsets by specifying its name at the time of loading the dataset. ## Data Instances An example of a `train` instance looks as follows: ```json {'id': 246001, 'inputs': 'The following query in English is taken from the geography category. What could be the answer to the question?\nWhat is the seventh tallest mountain in North America?', 'targets': 'The answer is Mount Lucania.', 'dataset_name': 'Mintaka-inst', 'sub_dataset_name': '-', 'task_type': 'question-answering', 'template_id': 3, 'language': 'eng', 'split': 'train', 'script': 'Latn' } ``` ## Data Fields The data fields are the same among all splits: - `id:` Unique id of the data point - `inputs:` Prompt or input to the language model. - `targets:` Completion or output of the language model. - `dataset_name:` The name of the source dataset that the data point was taken from - `sub_dataset_name:` If the source is a collection, this field indicates which part of that collection the data point was taken from. If it is not a collection, this field is left blank. - `task_type:` The task type that this conversation belongs to. - `template_id`: The id of the template applied to this data point. - `language:` The ISO code of the dialect of the conversation. - `script:` The script of the language. - `split:` Indicates whether the data point is part of the `train` or the `test` split. ### Statistics The total number of data points, including the Aya Dataset` is 513,758,189. To view the breakdown of dialect codes and the respective templated and translated data point counts in the Aya Collection , refer to the toggled table below. <details> <summary> <b> Breakdown of Aya Collection data point counts grouped by dialects </b> </summary> |dialect code|language|translated data point count|templated data point count|total count | |------------|--------|---------------------------|--------------------------|---------------| |ace |Achinese|8240684 |2000 |8242684 | |acm |Arabic |4120342 |0 |4120342 | |acq |Arabic |4120342 |0 |4120342 | |aeb |Arabic |4120342 |0 |4120342 | |afr |Afrikaans|4120342 |6108 |4126450 | |ajp |Arabic |4120342 |0 |4120342 | |als |Albanian|4120342 |0 |4120342 | |amh |Amharic |4120342 |25327 |4145669 | |apc |Arabic |4120342 |0 |4120342 | |arb |Arabic |6424999 |216430 |6641429 | |ars |Arabic |4120342 |0 |4120342 | |ary |Arabic |4120342 |18076 |4138418 | |arz |Arabic |4120342 |0 |4120342 | |azb |Azerbaijani|4120342 |0 |4120342 | |azj |Azerbaijani|4120342 |0 |4120342 | |bel |Belarusian|4120342 |21273 |4141615 | |ben |Bengali |4120342 |30661 |4151003 | |bjn |Banjar |8240684 |2000 |8242684 | |bul |Bulgarian|4120342 |37722 |4158064 | |cat |Catalan |4120342 |66900 |4187242 | |ceb |Cebuano |4120342 |0 |4120342 | |ces |Czech |4120342 |179604 |4299946 | |ckb |Kurdish |4120342 |0 |4120342 | |cym |Welsh |4120342 |0 |4120342 | |dan |Danish |4120342 |36310 |4156652 | |deu |German |4120342 |1326722 |5447064 | |ell |Greek |4120342 |40291 |4160633 | |eng |English |9771427 |8066678 |17838105 | |epo |Esperanto|4120342 |0 |4120342 | |est |Estonian|4120342 |0 |4120342 | |eus |Basque |4120342 |0 |4120342 | |fin |Finnish |4120342 |457895 |4578237 | |fra |French |4120342 |835520 |4955862 | |gla |Scottish Gaelic|4120342 |0 |4120342 | |gle |Irish |4120342 |0 |4120342 | |glg |Galician|4120342 |0 |4120342 | |guj |Gujarati|4120342 |2157 |4122499 | |hat |Haitian Creole|4120342 |0 |4120342 | |hau |Hausa |4120342 |51396 |4171738 | |heb |Hebrew |4120342 |103466 |4223808 | |hin |Hindi |4120342 |260387 |4380729 | |hun |Hungarian|4120342 |82039 |4202381 | |hye |Armenian|4120342 |7080 |4127422 | |ibo |Igbo |4120342 |36312 |4156654 | |ind |Indonesian|4120342 |45709 |4166051 | |isl |Icelandic|4120342 |0 |4120342 | |ita |Italian |4120342 |405682 |4526024 | |jav |Javanese|4120342 |829 |4121171 | |jpn |Japanese|4120342 |2693177 |6813519 | |kan |Kannada |4120342 |1156 |4121498 | |kas |Kashmiri|4120342 |0 |4120342 | |kat |Georgian|4120342 |0 |4120342 | |kaz |Kazakh |4120342 |0 |4120342 | |khk |Mongolian|4120342 |0 |4120342 | |khm |Khmer |4120342 |0 |4120342 | |kir |Kyrgyz |4120342 |0 |4120342 | |kmr |Kurdish |4120342 |0 |4120342 | |knc |Kanuri |8240684 |0 |8240684 | |kor |Korean |4120342 |41011 |4161353 | |lao |Lao |4120342 |0 |4120342 | |lit |Lithuanian|4120342 |0 |4120342 | |ltz |Luxembourgish|4120342 |0 |4120342 | |lvs |Latvian |4120342 |0 |4120342 | |mal |Malayalam|4120342 |4347 |4124689 | |mar |Marathi |4120342 |3678 |4124020 | |min |Minangkabau|6753788 |2000 |6755788 | |mkd |Macedonian|4120342 |0 |4120342 | |mlt |Maltese |4120342 |0 |4120342 | |mni |Manipuri|4120342 |0 |4120342 | |mri |Maori |4120342 |0 |4120342 | |mya |Burmese |4120342 |0 |4120342 | |nld |Dutch |4120342 |220181 |4340523 | |nno |Norwegian|4120342 |0 |4120342 | |nob |Norwegian|4120342 |0 |4120342 | |npi |Nepali |4120342 |0 |4120342 | |nso |Northern Sotho|4120342 |0 |4120342 | |pbt |Pashto |4120342 |0 |4120342 | |pes |Persian |4120342 |245520 |4365862 | |plt |Malagasy|4120342 |0 |4120342 | |pol |Polish |4120342 |332503 |4452845 | |por |Portuguese|4120342 |287432 |4407774 | |ron |Romanian|4120342 |36359 |4156701 | |rus |Russian |4120342 |545920 |4666262 | |sin |Sinhala |4120342 |195 |4120537 | |slk |Slovak |4120342 |27845 |4148187 | |slv |Slovenian|4120342 |25731 |4146073 | |smo |Samoan |4120342 |0 |4120342 | |sna |Shona |4120342 |3684 |4124026 | |snd |Sindhi |4120342 |0 |4120342 | |som |Somali |4120342 |2926 |4123268 | |sot |Southern Sotho|4120342 |0 |4120342 | |spa |Spanish |4120342 |379194 |4499536 | |srp |Serbian |4120342 |77124 |4197466 | |sun |Sundanese|4120342 |2208 |4122550 | |swe |Swedish |4120342 |76486 |4196828 | |swh |Swahili |4120342 |12726 |4133068 | |tam |Tamil |4120342 |11462 |4131804 | |taq |Tamasheq|4120342 |0 |4120342 | |tel |Telugu |4120342 |477821 |4598163 | |tgk |Tajik |4120342 |0 |4120342 | |tha |Thai |4120342 |2125180 |6245522 | |tur |Turkish |4120342 |59932 |4180274 | |ukr |Ukrainian|4120342 |189384 |4309726 | |urd |Urdu |4120342 |337739 |4458081 | |uzn |Uzbek |4120342 |0 |4120342 | |vie |Vietnamese|4120342 |42232 |4162574 | |xho |Xhosa |4120342 |2952 |4123294 | |ydd |Yiddish |4120342 |0 |4120342 | |yor |Yoruba |4120342 |4907 |4125249 | |yue |Chinese |4120342 |0 |4120342 | |zho-Hans |Chinese |4120342 |54528 |4174870 | |zho-Hant |Chinese |4120342 |0 |4120342 | |zsm |Malay |4120342 |13950 |4134292 | |zul |Zulu |4120342 |786 |4121128 | |arq |Arabic |0 |6046 |6046 | |ban |Balinese|0 |2000 |2000 | |bbc |Toba Batak|0 |2000 |2000 | |bem |Bemba |0 |776 |776 | |fil |Filipino|0 |220 |220 | |fon |Fon |0 |845 |845 | |hrv |Croatian|0 |9007 |9007 | |kin |Kinyarwanda|0 |11165 |11165 | |lij |Ligurian|0 |6409 |6409 | |mad |Madurese|0 |2000 |2000 | |nij |Ngaju |0 |2000 |2000 | |nor |Norwegian|0 |72352 |72352 | |pan |Punjabi |0 |2156 |2156 | |twi |Twi |0 |10840 |10840 | |wol |Wolof |0 |785 |785 | |zho |Chinese |0 |74972 |74972 | PS: Templated data also includes Mozambican Portuguese, which doesn't have its own ISO language code. </details> <br> # Motivations & Intentions - **Curation Rationale:** Automatic augmentation of existing datasets serves to enhance the available linguistic resources for multiple languages. The list of languages was initially established from mT5 and aligned with the annotators’ language list and NLLB translation model. The datasets were translated directly from English for all languages. # Additional Information ## Provenance - **Methods Used:** A combination of crowd-sourced templating and automatic translation was employed to source this dataset. - **Methodology Details:** - *Source:* Existing NLP datasets - *Dates of Collection:* May 2023 - Dec 2023 ## Dataset Version and Maintenance - **Maintenance Status:** Actively Maintained - **Version Details:** - *Current version:* 1.0 - *Last Update:* 02/2024 - *First Release:* 02/2024 ## Authorship - **Publishing Organization:** [Cohere For AI](https://cohere.com/research) - **Industry Type:** Not-for-profit - Tech - **Contact Details:** https://cohere.com/research/aya ## Licensing Information This dataset can be used for any purpose, whether academic or commercial, under the terms of the [Apache 2.0](https://opensource.org/license/apache-2-0) License. ## Citation Information ```bibtex @misc{singh2024aya, title={Aya Dataset: An Open-Access Collection for Multilingual Instruction Tuning}, author={Shivalika Singh and Freddie Vargus and Daniel Dsouza and Börje F. Karlsson and Abinaya Mahendiran and Wei-Yin Ko and Herumb Shandilya and Jay Patel and Deividas Mataciunas and Laura OMahony and Mike Zhang and Ramith Hettiarachchi and Joseph Wilson and Marina Machado and Luisa Souza Moura and Dominik Krzemiński and Hakimeh Fadaei and Irem Ergün and Ifeoma Okoh and Aisha Alaagib and Oshan Mudannayake and Zaid Alyafeai and Vu Minh Chien and Sebastian Ruder and Surya Guthikonda and Emad A. Alghamdi and Sebastian Gehrmann and Niklas Muennighoff and Max Bartolo and Julia Kreutzer and Ahmet Üstün and Marzieh Fadaee and Sara Hooker}, year={2024}, eprint={2402.06619}, archivePrefix={arXiv}, primaryClass={cs.CL} } ```

HuggingFaceGECLM/REDDIT_comments

HuggingFaceGECLM

--- dataset_info: features: - name: archived dtype: string - name: author dtype: string - name: author_fullname dtype: string - name: body dtype: string - name: comment_type dtype: string - name: controversiality dtype: string - name: created_utc dtype: string - name: edited dtype: string - name: gilded dtype: string - name: id dtype: string - name: link_id dtype: string - name: locked dtype: string - name: name dtype: string - name: parent_id dtype: string - name: permalink dtype: string - name: retrieved_on dtype: string - name: score dtype: string - name: subreddit_id dtype: string - name: subreddit_name_prefixed dtype: string - name: subreddit_type dtype: string - name: total_awards_received dtype: string splits: - name: programming num_bytes: 3466623746 num_examples: 7503347 - name: tifu num_bytes: 4761338653 num_examples: 12738669 - name: explainlikeimfive num_bytes: 8451732573 num_examples: 16392814 - name: WritingPrompts num_bytes: 4651591771 num_examples: 4436210 - name: changemyview num_bytes: 8603031915 num_examples: 11600073 - name: LifeProTips num_bytes: 5272994396 num_examples: 12829459 - name: todayilearned num_bytes: 22655655241 num_examples: 60199778 - name: science num_bytes: 7069809765 num_examples: 18112884 - name: askscience num_bytes: 3144754665 num_examples: 6286702 - name: ifyoulikeblank num_bytes: 547200329 num_examples: 1332211 - name: Foodforthought num_bytes: 308377128 num_examples: 567900 - name: IWantToLearn num_bytes: 408331672 num_examples: 745543 - name: bestof num_bytes: 2003718831 num_examples: 4347522 - name: IAmA num_bytes: 9380094090 num_examples: 25778822 - name: socialskills num_bytes: 1000014402 num_examples: 1842733 - name: relationship_advice num_bytes: 22298879735 num_examples: 38937398 - name: philosophy num_bytes: 1494947876 num_examples: 2391695 - name: YouShouldKnow num_bytes: 1165617658 num_examples: 2639265 - name: history num_bytes: 1457852402 num_examples: 2962043 - name: books num_bytes: 4562689426 num_examples: 10187495 - name: Showerthoughts num_bytes: 13259109532 num_examples: 34123213 - name: personalfinance num_bytes: 9484869588 num_examples: 18361314 - name: buildapc num_bytes: 9801044390 num_examples: 21761801 - name: EatCheapAndHealthy num_bytes: 853462012 num_examples: 1821897 - name: boardgames num_bytes: 3131627378 num_examples: 6328926 - name: malefashionadvice num_bytes: 2928017882 num_examples: 7712258 - name: femalefashionadvice num_bytes: 1619784736 num_examples: 3262969 - name: scifi num_bytes: 888152056 num_examples: 2193741 - name: Fantasy num_bytes: 2285934538 num_examples: 4566639 - name: Games num_bytes: 10396813188 num_examples: 23373965 - name: bodyweightfitness num_bytes: 794549854 num_examples: 1613634 - name: SkincareAddiction num_bytes: 3421122597 num_examples: 5660550 - name: podcasts num_bytes: 464773126 num_examples: 943266 - name: suggestmeabook num_bytes: 1842944304 num_examples: 3492937 - name: AskHistorians num_bytes: 2244587909 num_examples: 2714353 - name: gaming num_bytes: 28374513722 num_examples: 85729253 - name: DIY num_bytes: 2113533684 num_examples: 4489265 - name: sports num_bytes: 2230129132 num_examples: 6470079 - name: space num_bytes: 3081499208 num_examples: 7896182 - name: gadgets num_bytes: 1683252868 num_examples: 4104833 - name: Documentaries num_bytes: 1852644771 num_examples: 4051474 - name: GetMotivated num_bytes: 1211761267 num_examples: 3221980 - name: UpliftingNews num_bytes: 2003149025 num_examples: 4741948 - name: technology num_bytes: 10826871436 num_examples: 25404699 - name: Fitness num_bytes: 6191132755 num_examples: 14319856 - name: travel num_bytes: 1740556350 num_examples: 3806755 - name: lifehacks num_bytes: 626791812 num_examples: 1799437 - name: Damnthatsinteresting num_bytes: 6376694618 num_examples: 15643554 - name: gardening num_bytes: 1825313940 num_examples: 4568468 - name: mildlyinteresting num_bytes: 9079894206 num_examples: 26436769 download_size: 109177016105 dataset_size: 255339788158 annotations_creators: - no-annotation language: - en language_creators: - found license: [] multilinguality: - monolingual pretty_name: Reddit comments size_categories: - 10B<n<100B source_datasets: [] tags: - reddit - social-media task_categories: - text-generation task_ids: - dialogue-modeling - language-modeling --- # Dataset Card for "REDDIT_comments" ## Dataset Description - **Homepage:** - **Paper: https://arxiv.org/abs/2001.08435** ### Dataset Summary Comments of 50 high-quality subreddits, extracted from the REDDIT PushShift data dumps (from 2006 to Jan 2023). ### Supported Tasks These comments can be used for text generation and language modeling, as well as dialogue modeling. ## Dataset Structure ### Data Splits Each split corresponds to a specific subreddit in the following list: "tifu", "explainlikeimfive", "WritingPrompts", "changemyview", "LifeProTips", "todayilearned", "science", "askscience", "ifyoulikeblank", "Foodforthought", "IWantToLearn", "bestof", "IAmA", "socialskills", "relationship_advice", "philosophy", "YouShouldKnow", "history", "books", "Showerthoughts", "personalfinance", "buildapc", "EatCheapAndHealthy", "boardgames", "malefashionadvice", "femalefashionadvice", "scifi", "Fantasy", "Games", "bodyweightfitness", "SkincareAddiction", "podcasts", "suggestmeabook", "AskHistorians", "gaming", "DIY", "mildlyinteresting", "sports", "space", "gadgets", "Documentaries", "GetMotivated", "UpliftingNews", "technology", "Fitness", "travel", "lifehacks", "Damnthatsinteresting", "gardening", "programming" ## Dataset Creation ### Curation Rationale All the information fields have been cast to string, as their format change through time from one dump to the following. A reduced number of keys have been kept: "archived", "author", "author_fullname", "body", "comment_type", "controversiality", "created_utc", "edited", "gilded", "id", "link_id", "locked", "name", "parent_id", "permalink", "retrieved_on", "score", "subreddit", "subreddit_id", "subreddit_name_prefixed", "subreddit_type", "total_awards_received". ### Source Data The [Reddit PushShift data dumps](https://files.pushshift.io/reddit/) are part of a data collection effort which crawls Reddit at regular intervals, to extract and keep all its data. #### Initial Data Collection and Normalization See the paper. #### Who are the source language producers? Redditors are mostly young (65% below 30), male (70%), and American (50% of the site). ### Personal and Sensitive Information The data contains Redditor's usernames associated to their content. ## Considerations for Using the Data This dataset should be anonymized before any processing. Though the subreddits selected are considered as being of higher quality, they can still reflect what you can find on the internet in terms of expressions of biases and toxicity. ### Contributions Thanks to [@clefourrier](https://github.com/clefourrier) for adding this dataset.

CropNet/CropNet

CropNet

--- license: cc-by-4.0 language: - en tags: - agriculture - climate size_categories: - n>1T --- # An Open and Large-Scale Dataset for Multi-Modal Climate Change-aware Crop Yield Predictions  The CropNet dataset is an open, large-scale, and deep learning-ready dataset, specifically targeting climate change-aware crop yield predictions for the contiguous United States (U.S.) continent at the county level. It is composed of three modalities of data, i.e., Sentinel-2 Imagery, WRF-HRRR Computed Dataset, and USDA Crop Dataset, aligned in both the spatial and temporal domains, for over 2200 U.S. counties spanning 6 years (2017-2022). It is expected to facilitate researchers in developing deep learning models for timely and precisely predicting crop yields at the county level, by accounting for the effects of both short-term growing season weather variations and long-term climate change on crop yields. Although our initial goal of crafting the CropNet dataset is for precise crop yield prediction, we believe its future applicability is broad and can benefit the deep learning, agriculture, and meteorology communities, for exploring more interesting, critical, and climate change-related applications, by using one or more modalities of data. ## Citation If you use our dataset, please cite [our paper](https://dl.acm.org/doi/10.1145/3637528.3671536): ``` @inproceedings{fudong:kdd24:crop_net, author = {Fudong Lin and Kaleb Guillot and Summer Crawford and Yihe Zhang and Xu Yuan and Nian{-}Feng Tzeng}, title = {An Open and Large-Scale Dataset for Multi-Modal Climate Change-aware Crop Yield Predictions}, booktitle = {Proceedings of the 30th {ACM} {SIGKDD} Conference on Knowledge Discovery and Data Mining (KDD)}, pages = {5375--5386}, year = {2024} } ``` [Our MMST-ViT model](https://openaccess.thecvf.com/content/ICCV2023/papers/Lin_MMST-ViT_Climate_Change-aware_Crop_Yield_Prediction_via_Multi-Modal_Spatial-Temporal_Vision_ICCV_2023_paper.pdf) demonstrates how to develop deep-learning models for climate change-aware crop yield predictions. If you use MMST-ViT in your research, please cite our paper: ``` @inproceedings{fudong:iccv23:mmst_vit, title={MMST-ViT: Climate Change-aware Crop Yield Prediction via Multi-Modal Spatial-Temporal Vision Transformer}, author={Lin, Fudong and Crawford, Summer and Guillot, Kaleb and Zhang, Yihe and Chen, Yan and Yuan, Xu and others}, booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision}, pages={5774--5784}, year={2023} } ``` ## Contributions #### The `CropNet` dataset - The first *terabyte-sized*, publicly available, and multi-modal dataset for climate change-aware crop yield predictions #### The `CropNet` package - A *deep learning-ready* Python package for facilitating researchers in downloading the CropNet data on the fly over the time and region of interest, and developing deep neural networks (DNNs) for climate change-aware crop yield predictions - The `CropNet` package is available at [Python Package Index (PyPI)](https://pypi.org/project/cropnet/) ## Tutorials The tutorials for the CropNet dataset are available at Google Colab, with their links listed below - [Sentinel-2 Imagery Tutorial](https://colab.research.google.com/drive/1Tj69JdhO7aX8ks-4UWYvHrFm9GB1PNCd?usp=sharing) - [WRF-HRRR Computed Dataset Tutorial](https://colab.research.google.com/drive/14l-JSNHtelawNu3kVG_ukTd2WUJpaZEc?usp=sharing) - [USDA Crop Dataset Tutorial](https://colab.research.google.com/drive/1U-vFoRyLSb2l2Q67LeGbkUKTeRaHDkkK?usp=sharing) ## The CropNet Dataset 0ur CropNet dataset is composed of three modalities of data, i.e., Sentinel-2 Imagery, WRF-HRRR Computed Dataset, and USDA Crop Dataset, spanning from 2017 to 2022 (i.e., 6 years) across 2291 U.S. counties, with its geographic distribution illustrated below. We also include the number of counties corresponding to each crop type in the USDA Crop Dataset (see the rightmost bar chart in the figure) since crop planting is highly geography-dependent.  ### Sentinel-2 Imagery The Sentinel-2 Imagery, obtained from the Sentinel-2 mission, provides high-resolution satellite images for monitoring crop growth on the ground. It contains two types of 224x224 RGB satellite images, agriculture imagery (AG) and normalized difference vegetation index (NDVI), both with a spatial resolution of 9x9 km, and a revisit frequency of 14 days. Examples of AG and NDVI images are depicted as follows. - **Agriculture Imagery (AG)**  - **Normalized Difference Vegetation Index (NDVI)**  ### WRF-HRRR Computed Dataset The WRF-HRRR Computed Dataset, sourced from the WRF-HRRR model, contains daily and monthly meteorological parameters, with the former and the latter designed for capturing direct effects of short-term growing season weather variations on crop growth, and for learning indirect impacts of long-term climate change on crop yields, respectively. It contains 9 meteorological parameters gridded at 9 km in a one-day (and one-month) interval. The figures show the temperature in the spring, the summer, the fall, and the winter, respectively.  ### USDA Crop Dataset The USDA Crop Dataset, collected from the USDA Quick Statistic website, offers valuable information, such as production, yield, etc., for crops grown at each available county. It offers crop information for four types of crops, i.e., corn, cotton, soybeans, and winter wheat, at a county-level basis, with a temporal resolution of one year. The figure illustrates the 2022 Corn Yield across the United States.  ### The CropNet Package Beyond the contribution of our CropNet dataset, we also release the CropNet package in the Python Package Index (PyPI) for facilitating researchers in downloading the CropNet data based on the time and region of interest, and flexibly building their deep learning models for accurate crop yield predictions. In particular, the CropNet package includes three types of APIs, listed as follows: - **DataDownloader**: This API allows users to download the CropNet data over the time/region of interest on the fly. - **DataRetriever**: With this API, users can conveniently obtain the CropNet data stored in the local machine (e.g., if you have downloaded our curated CropNet from Google Drive) over the time/region of interest. - **DataLoader**: This API is designed to facilitate researchers in developing their DNNs for accurate crop yield predictions. Specifically, the code in this API ( 1) combines all three modalities of data to create $(\mathbf{x}, \mathbf{y_{s}}, \mathbf{y_{l}}, \mathbf{z})$ tuples, with $\mathbf{x}, \mathbf{y_{s}}, \mathbf{y_{l}}, \text{and}~ \mathbf{z}$, respectively representing satellite images, short-term daily whether parameters, long-term monthly meteorological parameters, and ground-truth crop yield (or production) information, and then (2) exposes those tuples via a `Dataset` object after appropriate data pre-processing techniques. ### Installation Researchers and practitioners can install the latest version of CropNet with the following commands: ```python # Create and activate a conda environment conda create -n cropnet_api python=3.10 conda activate cropnet_api # Install the latest version of CropNet pip install cropnet # Slove the ecCodes library dependency issue pip install ecmwflibs ``` ### CropNet API Examples - **Example 1: A DataDownloader Example for Downloading the Up-to-date CropNet Data** Given the time and region (i.e., the FIPS codes for two U.S. counties) of interest, the following code presents how to utilize the **DataDownloader** to download the up-to-date CropNet data: ```python from cropnet.data_downloader import DataDownloader # Use the "target_dir" to specify where the data should be downloaded to downloader = DataDownloader(target_dir="./data") # Download 2022 USDA Soybean data # Note that most of the 2023 USDA data are not yet available downloader.download_USDA("Soybean", fips_codes=["10003", "22007"], years=["2022"]) # Download the 2023 (the 1st and 2nd quarters) Sentinel-2 Imagery downloader.download_Sentinel2(fips_codes=["10003", "22007"], years=["2023"], image_type="AG") downloader.download_Sentinel2(fips_codes=["10003", "22007"], years=["2023"], image_type="NDVI") # Download the 2023 (January to July) WRF-HRRR data downloader.download_HRRR(fips_codes=["10003", "22007"], years=["2023"]) ``` - **Example 2: A DataRetriever Example for Obtaining Our Curated CropNet Data** Given the time and region of interest, the following code shows how to use the **DataRetriever** to obtain the CropNet data stored in the local machine in a user-friendly format: ```python # Use the "base_fir" to specify where the CropNet data is stored retriever = DataRetriever(base_dir="/mnt/data/CropNet") # Retrieve the 2022 USDA Soybean data usda_data = retriever.retrieve_USDA(crop_type="Soybean", fips_codes=["10003", "22007"], years=["2022"]) # Retrieve the 2022 Sentinel-2 Imagery data sentinel2_data = retriever.retrieve_Sentinel2(fips_codes=["10003", "22007"], years=["2022"], image_type="AG") sentinel2_data = retriever.retrieve_Sentinel2(fips_codes=["10003", "22007"], years=["2022"], image_type="NDVI") # Retrieve the 2022 WRF-HRRR data hrrr_data = retriever.retrieve_HRRR(fips_codes=["10003","22007"], years=["2022"]) ``` - **Example 3: A PyTorch Example for Using the DataLoader API for Training DNNs** The following code presents a PyTorch example of training a deep learning model (i.e., MMST-ViT) for climate change-aware crop yield predictions, by utilizing the DataLoader APIs: ```python import torch from torch.utils.data import DataLoader from models_mmst_vit import MMST_ViT from cropnet.dataset.hrrr_computed_dataset import HRRRComputedDataset from cropnet.dataset.sentinel2_imagery import Sentinel2Imagery from cropnet.dataset.usda_crop_dataset import USDACropDataset # The base directory for the CropNet dataset base_dir = "/mnt/data/CropNet" # The JSON configuration file config_file = "data/soybeans_train.json" # The dataloaders for each modality of data sentinel2_loader = DataLoader(Sentinel2Imagery(base_dir, config_file), batch_size=1) hrrr_loader = DataLoader(HRRRComputedDataset(base_dir, config_file), batch_size=1) usda_loader = DataLoader(USDACropDataset(base_dir, config_file), batch_size=1) # The model, the optimizer, and the loss function model = MMST_ViT() optimizer = torch.optim.AdamW(model.parameters(), lr=1e-3, betas=(0.9, 0.999)) criterion = torch.nn.MSELoss() # Traning the model for one epoch for s, h, u in zip(sentinel2_loader, hrrr_loader, usda_loader): # x: satellite images # ys (or yl): short-term daily (or long-term monthly) weather parameters # z: ground-truth crop yield (or production) information x, ys, yl, z, = s[0], h[0], h[1], u[0] optimizer.zero_grad() z_hat = model(x, ys, yl) loss = criterion(z, z_hat) loss.backward() optimizer.step() ``` ## License CropNet has a [Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0)](https://creativecommons.org/licenses/by-nc/4.0/) license. ## Dataset Terms of Use This dataset is available for research purposes only. By downloading, you agree to these terms. We are aware that unauthorized copies of our dataset have been republished on HuggingFace. Please note that any republication or distribution of this dataset without permission is prohibited and constitutes copyright infringement.

asahi417/seamless-align-enA-jaA.speaker-embedding.xlsr-2b

asahi417

--- dataset_info: - config_name: subset_1 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 16310450373 num_examples: 2073 download_size: 16362791193 dataset_size: 16310450373 - config_name: subset_10 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14507997777 num_examples: 1961 download_size: 14554505952 dataset_size: 14507997777 - config_name: subset_100 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14129720831 num_examples: 1757 download_size: 14173975107 dataset_size: 14129720831 - config_name: subset_101 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14993273606 num_examples: 1873 download_size: 15040705190 dataset_size: 14993273606 - config_name: subset_102 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15427157956 num_examples: 1868 download_size: 15475633129 dataset_size: 15427157956 - config_name: subset_103 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15482076366 num_examples: 1879 download_size: 15530574846 dataset_size: 15482076366 - config_name: subset_104 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15390676969 num_examples: 1901 download_size: 15439431804 dataset_size: 15390676969 - config_name: subset_105 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15184436320 num_examples: 1875 download_size: 15231369480 dataset_size: 15184436320 - config_name: subset_106 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15272910298 num_examples: 1880 download_size: 15320755279 dataset_size: 15272910298 - config_name: subset_107 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14914011605 num_examples: 1854 download_size: 14961302329 dataset_size: 14914011605 - config_name: subset_108 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15180068428 num_examples: 1834 download_size: 15228372695 dataset_size: 15180068428 - config_name: subset_109 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14466035226 num_examples: 1770 download_size: 14511537163 dataset_size: 14466035226 - config_name: subset_11 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13101664907 num_examples: 1779 download_size: 13144308567 dataset_size: 13101664907 - config_name: subset_110 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15611661731 num_examples: 1908 download_size: 15659409356 dataset_size: 15611661731 - config_name: subset_111 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15278480945 num_examples: 1877 download_size: 15327096988 dataset_size: 15278480945 - config_name: subset_112 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15724141438 num_examples: 1924 download_size: 15772924053 dataset_size: 15724141438 - config_name: subset_113 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15575717731 num_examples: 1930 download_size: 15625880579 dataset_size: 15575717731 - config_name: subset_114 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15882425444 num_examples: 1940 download_size: 15931108324 dataset_size: 15882425444 - config_name: subset_115 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15508119355 num_examples: 1902 download_size: 15558088350 dataset_size: 15508119355 - config_name: subset_116 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15790391750 num_examples: 1910 download_size: 15839269103 dataset_size: 15790391750 - config_name: subset_117 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15442029172 num_examples: 1901 download_size: 15490765116 dataset_size: 15442029172 - config_name: subset_118 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15796646573 num_examples: 1911 download_size: 15846588578 dataset_size: 15796646573 - config_name: subset_119 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15363910769 num_examples: 1867 download_size: 15412415056 dataset_size: 15363910769 - config_name: subset_12 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14593616895 num_examples: 1916 download_size: 14640738281 dataset_size: 14593616895 - config_name: subset_120 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14564344621 num_examples: 1774 download_size: 14609587966 dataset_size: 14564344621 - config_name: subset_121 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15707595472 num_examples: 1895 download_size: 15757411615 dataset_size: 15707595472 - config_name: subset_122 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15173277199 num_examples: 1851 download_size: 15220532819 dataset_size: 15173277199 - config_name: subset_123 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15999251579 num_examples: 1923 download_size: 16048976124 dataset_size: 15999251579 - config_name: subset_124 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15601517059 num_examples: 1886 download_size: 15649292085 dataset_size: 15601517059 - config_name: subset_125 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15779512647 num_examples: 1928 download_size: 15829615675 dataset_size: 15779512647 - config_name: subset_126 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15356045351 num_examples: 1903 download_size: 15404217390 dataset_size: 15356045351 - config_name: subset_127 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15746607635 num_examples: 1902 download_size: 15796480801 dataset_size: 15746607635 - config_name: subset_128 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15375262005 num_examples: 1890 download_size: 15423317041 dataset_size: 15375262005 - config_name: subset_129 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14491367899 num_examples: 1752 download_size: 14536131741 dataset_size: 14491367899 - config_name: subset_13 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13188431829 num_examples: 1769 download_size: 13231483897 dataset_size: 13188431829 - config_name: subset_130 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15116628991 num_examples: 1830 download_size: 15164906379 dataset_size: 15116628991 - config_name: subset_131 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15597505674 num_examples: 1882 download_size: 15646436161 dataset_size: 15597505674 - config_name: subset_132 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15682009564 num_examples: 1918 download_size: 15731148123 dataset_size: 15682009564 - config_name: subset_133 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15253685409 num_examples: 1886 download_size: 15302350698 dataset_size: 15253685409 - config_name: subset_134 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15689301205 num_examples: 1912 download_size: 15739304449 dataset_size: 15689301205 - config_name: subset_135 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15581938369 num_examples: 1888 download_size: 15631772490 dataset_size: 15581938369 - config_name: subset_136 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15412182385 num_examples: 1875 download_size: 15460732037 dataset_size: 15412182385 - config_name: subset_137 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15360445304 num_examples: 1866 download_size: 15408941456 dataset_size: 15360445304 - config_name: subset_138 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15290751173 num_examples: 1863 download_size: 15339201722 dataset_size: 15290751173 - config_name: subset_139 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15256641544 num_examples: 1859 download_size: 15305102287 dataset_size: 15256641544 - config_name: subset_14 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12993946901 num_examples: 1734 download_size: 13035965994 dataset_size: 12993946901 - config_name: subset_140 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14712168776 num_examples: 1766 download_size: 14758529545 dataset_size: 14712168776 - config_name: subset_141 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15597842345 num_examples: 1865 download_size: 15647499851 dataset_size: 15597842345 - config_name: subset_142 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15493296202 num_examples: 1893 download_size: 15541947212 dataset_size: 15493296202 - config_name: subset_143 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15528880887 num_examples: 1894 download_size: 15578798622 dataset_size: 15528880887 - config_name: subset_144 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 11610659779 num_examples: 1381 download_size: 11647759826 dataset_size: 11610659779 - config_name: subset_15 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14365778430 num_examples: 1914 download_size: 14412046441 dataset_size: 14365778430 - config_name: subset_16 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13652391626 num_examples: 1862 download_size: 13697579329 dataset_size: 13652391626 - config_name: subset_17 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14220432427 num_examples: 1875 download_size: 14266917233 dataset_size: 14220432427 - config_name: subset_18 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14758117694 num_examples: 1937 download_size: 14806166262 dataset_size: 14758117694 - config_name: subset_19 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14263981046 num_examples: 1917 download_size: 14310683240 dataset_size: 14263981046 - config_name: subset_2 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14854535769 num_examples: 1929 download_size: 14902477949 dataset_size: 14854535769 - config_name: subset_20 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14108138618 num_examples: 1877 download_size: 14154663716 dataset_size: 14108138618 - config_name: subset_21 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13644053955 num_examples: 1761 download_size: 13688549900 dataset_size: 13644053955 - config_name: subset_22 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13872299017 num_examples: 1850 download_size: 13916933531 dataset_size: 13872299017 - config_name: subset_23 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13582453701 num_examples: 1790 download_size: 13627175034 dataset_size: 13582453701 - config_name: subset_24 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13368705263 num_examples: 1758 download_size: 13412036987 dataset_size: 13368705263 - config_name: subset_25 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14867350268 num_examples: 1898 download_size: 14914077907 dataset_size: 14867350268 - config_name: subset_26 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14564112565 num_examples: 1943 download_size: 14612260797 dataset_size: 14564112565 - config_name: subset_27 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14403352351 num_examples: 1903 download_size: 14449996819 dataset_size: 14403352351 - config_name: subset_28 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14603029543 num_examples: 1912 download_size: 14650911489 dataset_size: 14603029543 - config_name: subset_29 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14673048791 num_examples: 1945 download_size: 14719897418 dataset_size: 14673048791 - config_name: subset_3 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14307378756 num_examples: 1899 download_size: 14353984563 dataset_size: 14307378756 - config_name: subset_30 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14710205080 num_examples: 1902 download_size: 14757936886 dataset_size: 14710205080 - config_name: subset_31 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14025445242 num_examples: 1805 download_size: 14071428675 dataset_size: 14025445242 - config_name: subset_32 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13945538622 num_examples: 1797 download_size: 13989843317 dataset_size: 13945538622 - config_name: subset_33 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13615084926 num_examples: 1757 download_size: 13659554271 dataset_size: 13615084926 - config_name: subset_34 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14564415851 num_examples: 1893 download_size: 14609576153 dataset_size: 14564415851 - config_name: subset_35 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14755481346 num_examples: 1928 download_size: 14803386359 dataset_size: 14755481346 - config_name: subset_36 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14405715735 num_examples: 1863 download_size: 14452030865 dataset_size: 14405715735 - config_name: subset_37 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14459656749 num_examples: 1855 download_size: 14505278929 dataset_size: 14459656749 - config_name: subset_38 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14747294818 num_examples: 1890 download_size: 14794943834 dataset_size: 14747294818 - config_name: subset_39 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14583795374 num_examples: 1899 download_size: 14631576455 dataset_size: 14583795374 - config_name: subset_4 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13461749342 num_examples: 1835 download_size: 13505049439 dataset_size: 13461749342 - config_name: subset_40 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14996728508 num_examples: 1931 download_size: 15043987691 dataset_size: 14996728508 - config_name: subset_41 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13998657085 num_examples: 1784 download_size: 14043192313 dataset_size: 13998657085 - config_name: subset_42 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13997152060 num_examples: 1797 download_size: 14041809773 dataset_size: 13997152060 - config_name: subset_43 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13745374844 num_examples: 1757 download_size: 13787997899 dataset_size: 13745374844 - config_name: subset_44 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14470227992 num_examples: 1831 download_size: 14516259581 dataset_size: 14470227992 - config_name: subset_45 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14540526118 num_examples: 1891 download_size: 14588272101 dataset_size: 14540526118 - config_name: subset_46 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14936006712 num_examples: 1897 download_size: 14983643800 dataset_size: 14936006712 - config_name: subset_47 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15007636946 num_examples: 1897 download_size: 15056520164 dataset_size: 15007636946 - config_name: subset_48 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15007698844 num_examples: 1902 download_size: 15056591062 dataset_size: 15007698844 - config_name: subset_49 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14872319895 num_examples: 1875 download_size: 14917259741 dataset_size: 14872319895 - config_name: subset_5 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14727185951 num_examples: 1987 download_size: 14775476702 dataset_size: 14727185951 - config_name: subset_50 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15197781964 num_examples: 1951 download_size: 15247032911 dataset_size: 15197781964 - config_name: subset_51 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14076247457 num_examples: 1752 download_size: 14121778451 dataset_size: 14076247457 - config_name: subset_52 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14166667429 num_examples: 1780 download_size: 14212377834 dataset_size: 14166667429 - config_name: subset_53 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14663043837 num_examples: 1846 download_size: 14710380722 dataset_size: 14663043837 - config_name: subset_54 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13650359450 num_examples: 1723 download_size: 13694095020 dataset_size: 13650359450 - config_name: subset_55 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14667394581 num_examples: 1866 download_size: 14714877043 dataset_size: 14667394581 - config_name: subset_56 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15126039375 num_examples: 1893 download_size: 15174838075 dataset_size: 15126039375 - config_name: subset_57 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15160658347 num_examples: 1924 download_size: 15208466401 dataset_size: 15160658347 - config_name: subset_58 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14776270381 num_examples: 1881 download_size: 14823232990 dataset_size: 14776270381 - config_name: subset_59 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14820738246 num_examples: 1887 download_size: 14868333441 dataset_size: 14820738246 - config_name: subset_6 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13509749274 num_examples: 1810 download_size: 13554686583 dataset_size: 13509749274 - config_name: subset_60 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15012692080 num_examples: 1885 download_size: 15061442178 dataset_size: 15012692080 - config_name: subset_61 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13825585736 num_examples: 1728 download_size: 13869424308 dataset_size: 13825585736 - config_name: subset_62 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14059852714 num_examples: 1787 download_size: 14104565757 dataset_size: 14059852714 - config_name: subset_63 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14347818528 num_examples: 1790 download_size: 14393558940 dataset_size: 14347818528 - config_name: subset_64 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14454950614 num_examples: 1812 download_size: 14500831889 dataset_size: 14454950614 - config_name: subset_65 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15012253440 num_examples: 1877 download_size: 15060938596 dataset_size: 15012253440 - config_name: subset_66 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15063107203 num_examples: 1890 download_size: 15111909056 dataset_size: 15063107203 - config_name: subset_67 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14991421779 num_examples: 1873 download_size: 15038857831 dataset_size: 14991421779 - config_name: subset_68 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15139716092 num_examples: 1883 download_size: 15188419081 dataset_size: 15139716092 - config_name: subset_69 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15398369854 num_examples: 1916 download_size: 15447262341 dataset_size: 15398369854 - config_name: subset_7 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13642415322 num_examples: 1832 download_size: 13685996881 dataset_size: 13642415322 - config_name: subset_70 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15176201337 num_examples: 1903 download_size: 15224791080 dataset_size: 15176201337 - config_name: subset_71 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13922358727 num_examples: 1736 download_size: 13966560038 dataset_size: 13922358727 - config_name: subset_72 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15371189233 num_examples: 1887 download_size: 15419825117 dataset_size: 15371189233 - config_name: subset_73 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13830427317 num_examples: 1736 download_size: 13874422671 dataset_size: 13830427317 - config_name: subset_74 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14723538586 num_examples: 1829 download_size: 14770698909 dataset_size: 14723538586 - config_name: subset_75 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15010254373 num_examples: 1862 download_size: 15058831818 dataset_size: 15010254373 - config_name: subset_76 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15247986194 num_examples: 1914 download_size: 15296025961 dataset_size: 15247986194 - config_name: subset_77 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15110877308 num_examples: 1874 download_size: 15159532855 dataset_size: 15110877308 - config_name: subset_78 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15037318101 num_examples: 1871 download_size: 15085976191 dataset_size: 15037318101 - config_name: subset_79 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15137911072 num_examples: 1891 download_size: 15186694496 dataset_size: 15137911072 - config_name: subset_8 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14896343344 num_examples: 2009 download_size: 14944904571 dataset_size: 14896343344 - config_name: subset_80 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14886044351 num_examples: 1885 download_size: 14933598111 dataset_size: 14886044351 - config_name: subset_81 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15488479968 num_examples: 1913 download_size: 15537299076 dataset_size: 15488479968 - config_name: subset_82 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15484176671 num_examples: 1910 download_size: 15532974397 dataset_size: 15484176671 - config_name: subset_83 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15204999706 num_examples: 1887 download_size: 15253724799 dataset_size: 15204999706 - config_name: subset_84 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15046661582 num_examples: 1867 download_size: 15095251446 dataset_size: 15046661582 - config_name: subset_85 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15018316453 num_examples: 1881 download_size: 15067060203 dataset_size: 15018316453 - config_name: subset_86 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15000057699 num_examples: 1862 download_size: 15047257993 dataset_size: 15000057699 - config_name: subset_87 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15201873116 num_examples: 1897 download_size: 15250090060 dataset_size: 15201873116 - config_name: subset_88 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15311639315 num_examples: 1900 download_size: 15360401050 dataset_size: 15311639315 - config_name: subset_89 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15309755677 num_examples: 1886 download_size: 15358419262 dataset_size: 15309755677 - config_name: subset_9 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14569778419 num_examples: 1977 download_size: 14618200962 dataset_size: 14569778419 - config_name: subset_90 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15290839824 num_examples: 1913 download_size: 15339744563 dataset_size: 15290839824 - config_name: subset_91 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15397885579 num_examples: 1913 download_size: 15446720083 dataset_size: 15397885579 - config_name: subset_92 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15031825290 num_examples: 1886 download_size: 15080581026 dataset_size: 15031825290 - config_name: subset_93 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15285895893 num_examples: 1875 download_size: 15334493674 dataset_size: 15285895893 - config_name: subset_94 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15343527930 num_examples: 1900 download_size: 15392308839 dataset_size: 15343527930 - config_name: subset_95 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15015741095 num_examples: 1867 download_size: 15064356988 dataset_size: 15015741095 - config_name: subset_96 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15460278621 num_examples: 1900 download_size: 15509015959 dataset_size: 15460278621 - config_name: subset_97 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15474609177 num_examples: 1899 download_size: 15523317437 dataset_size: 15474609177 - config_name: subset_98 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15471182493 num_examples: 1904 download_size: 15519934699 dataset_size: 15471182493 - config_name: subset_99 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: jaA.id dtype: string - name: jaA.laser_score dtype: float64 - name: jaA.audio.speaker_embedding sequence: float32 - name: jaA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15562076261 num_examples: 1901 download_size: 15612040624 dataset_size: 15562076261 configs: - config_name: subset_1 data_files: - split: train path: subset_1/train-* - config_name: subset_10 data_files: - split: train path: subset_10/train-* - config_name: subset_100 data_files: - split: train path: subset_100/train-* - config_name: subset_101 data_files: - split: train path: subset_101/train-* - config_name: subset_102 data_files: - split: train path: subset_102/train-* - config_name: subset_103 data_files: - split: train path: subset_103/train-* - config_name: subset_104 data_files: - split: train path: subset_104/train-* - config_name: subset_105 data_files: - split: train path: subset_105/train-* - config_name: subset_106 data_files: - split: train path: subset_106/train-* - config_name: subset_107 data_files: - split: train path: subset_107/train-* - config_name: subset_108 data_files: - split: train path: subset_108/train-* - config_name: subset_109 data_files: - split: train path: subset_109/train-* - config_name: subset_11 data_files: - split: train path: subset_11/train-* - config_name: subset_110 data_files: - split: train path: subset_110/train-* - config_name: subset_111 data_files: - split: train path: subset_111/train-* - config_name: subset_112 data_files: - split: train path: subset_112/train-* - config_name: subset_113 data_files: - split: train path: subset_113/train-* - config_name: subset_114 data_files: - split: train path: subset_114/train-* - config_name: subset_115 data_files: - split: train path: subset_115/train-* - config_name: subset_116 data_files: - split: train path: subset_116/train-* - config_name: subset_117 data_files: - split: train path: subset_117/train-* - config_name: subset_118 data_files: - split: train path: subset_118/train-* - config_name: subset_119 data_files: - split: train path: subset_119/train-* - config_name: subset_12 data_files: - split: train path: subset_12/train-* - config_name: subset_120 data_files: - split: train path: subset_120/train-* - config_name: subset_121 data_files: - split: train path: subset_121/train-* - config_name: subset_122 data_files: - split: train path: subset_122/train-* - config_name: subset_123 data_files: - split: train path: subset_123/train-* - config_name: subset_124 data_files: - split: train path: subset_124/train-* - config_name: subset_125 data_files: - split: train path: subset_125/train-* - config_name: subset_126 data_files: - split: train path: subset_126/train-* - config_name: subset_127 data_files: - split: train path: subset_127/train-* - config_name: subset_128 data_files: - split: train path: subset_128/train-* - config_name: subset_129 data_files: - split: train path: subset_129/train-* - config_name: subset_13 data_files: - split: train path: subset_13/train-* - config_name: subset_130 data_files: - split: train path: subset_130/train-* - config_name: subset_131 data_files: - split: train path: subset_131/train-* - config_name: subset_132 data_files: - split: train path: subset_132/train-* - config_name: subset_133 data_files: - split: train path: subset_133/train-* - config_name: subset_134 data_files: - split: train path: subset_134/train-* - config_name: subset_135 data_files: - split: train path: subset_135/train-* - config_name: subset_136 data_files: - split: train path: subset_136/train-* - config_name: subset_137 data_files: - split: train path: subset_137/train-* - config_name: subset_138 data_files: - split: train path: subset_138/train-* - config_name: subset_139 data_files: - split: train path: subset_139/train-* - config_name: subset_14 data_files: - split: train path: subset_14/train-* - config_name: subset_140 data_files: - split: train path: subset_140/train-* - config_name: subset_141 data_files: - split: train path: subset_141/train-* - config_name: subset_142 data_files: - split: train path: subset_142/train-* - config_name: subset_143 data_files: - split: train path: subset_143/train-* - config_name: subset_144 data_files: - split: train path: subset_144/train-* - config_name: subset_15 data_files: - split: train path: subset_15/train-* - config_name: subset_16 data_files: - split: train path: subset_16/train-* - config_name: subset_17 data_files: - split: train path: subset_17/train-* - config_name: subset_18 data_files: - split: train path: subset_18/train-* - config_name: subset_19 data_files: - split: train path: subset_19/train-* - config_name: subset_2 data_files: - split: train path: subset_2/train-* - config_name: subset_20 data_files: - split: train path: subset_20/train-* - config_name: subset_21 data_files: - split: train path: subset_21/train-* - config_name: subset_22 data_files: - split: train path: subset_22/train-* - config_name: subset_23 data_files: - split: train path: subset_23/train-* - config_name: subset_24 data_files: - split: train path: subset_24/train-* - config_name: subset_25 data_files: - split: train path: subset_25/train-* - config_name: subset_26 data_files: - split: train path: subset_26/train-* - config_name: subset_27 data_files: - split: train path: subset_27/train-* - config_name: subset_28 data_files: - split: train path: subset_28/train-* - config_name: subset_29 data_files: - split: train path: subset_29/train-* - config_name: subset_3 data_files: - split: train path: subset_3/train-* - config_name: subset_30 data_files: - split: train path: subset_30/train-* - config_name: subset_31 data_files: - split: train path: subset_31/train-* - config_name: subset_32 data_files: - split: train path: subset_32/train-* - config_name: subset_33 data_files: - split: train path: subset_33/train-* - config_name: subset_34 data_files: - split: train path: subset_34/train-* - config_name: subset_35 data_files: - split: train path: subset_35/train-* - config_name: subset_36 data_files: - split: train path: subset_36/train-* - config_name: subset_37 data_files: - split: train path: subset_37/train-* - config_name: subset_38 data_files: - split: train path: subset_38/train-* - config_name: subset_39 data_files: - split: train path: subset_39/train-* - config_name: subset_4 data_files: - split: train path: subset_4/train-* - config_name: subset_40 data_files: - split: train path: subset_40/train-* - config_name: subset_41 data_files: - split: train path: subset_41/train-* - config_name: subset_42 data_files: - split: train path: subset_42/train-* - config_name: subset_43 data_files: - split: train path: subset_43/train-* - config_name: subset_44 data_files: - split: train path: subset_44/train-* - config_name: subset_45 data_files: - split: train path: subset_45/train-* - config_name: subset_46 data_files: - split: train path: subset_46/train-* - config_name: subset_47 data_files: - split: train path: subset_47/train-* - config_name: subset_48 data_files: - split: train path: subset_48/train-* - config_name: subset_49 data_files: - split: train path: subset_49/train-* - config_name: subset_5 data_files: - split: train path: subset_5/train-* - config_name: subset_50 data_files: - split: train path: subset_50/train-* - config_name: subset_51 data_files: - split: train path: subset_51/train-* - config_name: subset_52 data_files: - split: train path: subset_52/train-* - config_name: subset_53 data_files: - split: train path: subset_53/train-* - config_name: subset_54 data_files: - split: train path: subset_54/train-* - config_name: subset_55 data_files: - split: train path: subset_55/train-* - config_name: subset_56 data_files: - split: train path: subset_56/train-* - config_name: subset_57 data_files: - split: train path: subset_57/train-* - config_name: subset_58 data_files: - split: train path: subset_58/train-* - config_name: subset_59 data_files: - split: train path: subset_59/train-* - config_name: subset_6 data_files: - split: train path: subset_6/train-* - config_name: subset_60 data_files: - split: train path: subset_60/train-* - config_name: subset_61 data_files: - split: train path: subset_61/train-* - config_name: subset_62 data_files: - split: train path: subset_62/train-* - config_name: subset_63 data_files: - split: train path: subset_63/train-* - config_name: subset_64 data_files: - split: train path: subset_64/train-* - config_name: subset_65 data_files: - split: train path: subset_65/train-* - config_name: subset_66 data_files: - split: train path: subset_66/train-* - config_name: subset_67 data_files: - split: train path: subset_67/train-* - config_name: subset_68 data_files: - split: train path: subset_68/train-* - config_name: subset_69 data_files: - split: train path: subset_69/train-* - config_name: subset_7 data_files: - split: train path: subset_7/train-* - config_name: subset_70 data_files: - split: train path: subset_70/train-* - config_name: subset_71 data_files: - split: train path: subset_71/train-* - config_name: subset_72 data_files: - split: train path: subset_72/train-* - config_name: subset_73 data_files: - split: train path: subset_73/train-* - config_name: subset_74 data_files: - split: train path: subset_74/train-* - config_name: subset_75 data_files: - split: train path: subset_75/train-* - config_name: subset_76 data_files: - split: train path: subset_76/train-* - config_name: subset_77 data_files: - split: train path: subset_77/train-* - config_name: subset_78 data_files: - split: train path: subset_78/train-* - config_name: subset_79 data_files: - split: train path: subset_79/train-* - config_name: subset_8 data_files: - split: train path: subset_8/train-* - config_name: subset_80 data_files: - split: train path: subset_80/train-* - config_name: subset_81 data_files: - split: train path: subset_81/train-* - config_name: subset_82 data_files: - split: train path: subset_82/train-* - config_name: subset_83 data_files: - split: train path: subset_83/train-* - config_name: subset_84 data_files: - split: train path: subset_84/train-* - config_name: subset_85 data_files: - split: train path: subset_85/train-* - config_name: subset_86 data_files: - split: train path: subset_86/train-* - config_name: subset_87 data_files: - split: train path: subset_87/train-* - config_name: subset_88 data_files: - split: train path: subset_88/train-* - config_name: subset_89 data_files: - split: train path: subset_89/train-* - config_name: subset_9 data_files: - split: train path: subset_9/train-* - config_name: subset_90 data_files: - split: train path: subset_90/train-* - config_name: subset_91 data_files: - split: train path: subset_91/train-* - config_name: subset_92 data_files: - split: train path: subset_92/train-* - config_name: subset_93 data_files: - split: train path: subset_93/train-* - config_name: subset_94 data_files: - split: train path: subset_94/train-* - config_name: subset_95 data_files: - split: train path: subset_95/train-* - config_name: subset_96 data_files: - split: train path: subset_96/train-* - config_name: subset_97 data_files: - split: train path: subset_97/train-* - config_name: subset_98 data_files: - split: train path: subset_98/train-* - config_name: subset_99 data_files: - split: train path: subset_99/train-* ---

ncoop57/mmmlu

ncoop57

--- license: mit ---

mlfoundations/MINT-1T-PDF-CC-2023-50

mlfoundations

--- license: cc-by-4.0 task_categories: - image-to-text - text-generation language: - en tags: - multimodal pretty_name: MINT-1T size_categories: - 100B<n<1T --- <h1 align="center"> 🍃 MINT-1T:<br>Scaling Open-Source Multimodal Data by 10x:<br> A Multimodal Dataset with One Trillion Tokens </h1> 🍃 MINT-1T is an open-source **M**ultimodal **INT**erleaved dataset with 1 trillion text tokens and 3.4 billion images, a 10x scale-up from existing open-source datasets. Additionally, we include previously untapped sources such as PDFs and ArXiv papers. 🍃 MINT-1T is designed to facilitate research in multimodal pretraining. 🍃 MINT-1T is created by a team from the University of Washington in collaboration with Salesforce Research, other academic institutions including Stanford University, University of Texas at Austin, and University of California Berkeley. You are currently viewing a subset of the PDF portion of 🍃 MINT-1T associated with CommonCrawl dump `CC-2023-50`. For other PDF, HTML, and ArXiv subsets, refer to the [🍃 MINT-1T collection](https://huggingface.co./collections/mlfoundations/mint-1t-6690216ca4d0df7e518dde1c).  ## Updates ### 9/19/24 We have removed roughly 10% of the PDF samples as there was a mismatch between the frames in the TIFF images and the document metadata. ### 8/8/24 We have become aware that the image hashes in the PDF subset of MINT-1T do not match the images in the documents. We want to emphasize that the images for each document are correct, and only the image hashes in the documents' metadata are mislabeled. ## Dataset Details ### Dataset Sources - **Repository**: https://github.com/mlfoundations/MINT-1T - **Paper:** https://arxiv.org/abs/2406.11271 - **Blog:** https://blog.salesforceairesearch.com/mint-1t/ ## Uses ### Direct Use <!-- This section describes suitable use cases for the dataset. --> 🍃 MINT-1T is designed to facilitate research in multimodal pretraining. The dataset can be used for training multimodal models that can reson about interleaved text and images sequences such as [Idefics2](https://huggingface.co./HuggingFaceM4/idefics2-8b), [XGen-MM](https://huggingface.co./Salesforce/xgen-mm-phi3-mini-instruct-r-v1), and [Chameleon](https://huggingface.co./facebook/chameleon-30b). ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the dataset will not work well for. --> 🍃 MINT-1T was built to make research into large multimodal models more accessible. Using the dataset to train models that ingest or generate personally identifying information (such as images of people’s faces and other sensitive content) as well as military applications are all inappropriate use cases of 🍃 MINT-1T. ## Dataset Creation ### Curation Rationale 🍃 MINT-1T was created to address a significant gap in the open-source domain by providing a large-scale multimodal interleaved dataset for pre-training large multimodal models. This dataset aims to be a valuable resource for the research community, facilitating open science in multimodal pretraining. ### Source Data The dataset is a comprehensive collection of multimodal documents from various sources: - HTML documents: Filtered from CommonCrawl WARC dumps spanning from 2017 to 2024 - PDF documents: Extracted from CommonCrawl WAT dumps covering 2023 to 2024 - ArXiv documents: A subset of papers from the ArXiv repository In total, 🍃 MINT-1T contains 1056.8 million documents, broken down as follows: - 1029.4 million HTML documents - 24.0 million PDF documents - 0.6 million ArXiv documents #### Data Collection and Processing The data collection and processing involved several steps: 1. Document Extraction: - HTML documents were parsed from CommonCrawl WARC files - PDF documents were extracted from CommonCrawl WAT files - ArXiv papers were directly sourced from ArXiv S3 buckets 2. Filtering Process: - Applied text quality filters to ensure content relevance and readability - Removed duplicate content at both paragraph and document levels - Filtered out undesirable content based on predefined criteria - Verified image availability and quality for HTML documents - Limited PDF size to 50MB and 50 pages to manage dataset size and quality 3. Image Processing: - Used NSFW image detection to remove pornographic or otherwise undesirable images - Removed images smaller than 150 pixels or larger than 20,000 pixels - Adjusted aspect ratio thresholds for HTML (2:1) and PDF (3:1) to preserve scientific figures 4. Text Processing: - Used fasttext for language identification, focusing on English content - Masked personally identifiable information such as email addresses and IP addresses - Applied paragraph and document-level deduplication using Bloom filters 5. PDF Specific Processing: - Used PyMuPDF for parsing PDFs and extracting reading order - Clustered text blocks based on columns and ordered from top left to bottom right 6. ArXiv Specific Processing: - Used TexSoup to parse LaTeX source code and interleave images with text - Cleaned up LaTeX code by removing imports, bibliography, tables, and citation tags Various open-source tools were utilized in this process, including fasttext, [PyMuPDF](https://github.com/pymupdf/PyMuPDF), and [DCLM](https://www.datacomp.ai/dclm/) and [bff](https://github.com/revbucket/bff) for deduplication and content filtering. #### Personal and Sensitive Information Despite sourcing from public web data, significant efforts were made to minimize the inclusion of personal and sensitive information: - Email addresses and IP addresses were masked to protect privacy - An NSFW image classifierto remove inappropriate visual content - URLs containing substrings associated with undesirable or sensitive content were filtered out However, users should be aware that as the data originates from the public web, it may still contain some sensitive or personal information. The dataset creators acknowledge this limitation and advise users to exercise caution and potentially apply additional filtering based on their specific use cases. ## Bias, Risks, and Limitations Several potential biases, risks, and limitations have been identified: 1. Data Bias: As the dataset is sourced from web crawls, it may inherit biases present in online content. 2. Content Risks: Despite extensive filtering, there's a possibility that some offensive, insensitive, or inappropriate content may remain in the dataset. 3. Image Availability: The dataset relies on external image URLs, which may become unavailable over time due to link rot, potentially affecting the dataset's long-term usability. 4. PDF Parsing Limitations: The current method for extracting reading order from PDFs may not always accurately capture the intended flow, especially for documents with complex layouts. 5. Potential Legal and Ethical Concerns: While efforts were made to respect robots.txt files and remove sensitive information, there may still be content that individuals did not explicitly consent to include. ### Recommendations Given these considerations, the following recommendations are provided: 1. Additional Filtering: Users are strongly encouraged to apply additional filtering based on their specific use case and ethical considerations. 2. Inappropriate Use Cases: The dataset is not recommended for applications involving the processing or generation of personally identifying information, nor for military applications. 3. Legal Compliance: Users should independently verify compliance with applicable laws before employing MINT-1T for commercial purposes. 4. Bias Awareness: Researchers and developers should be cognizant of potential biases in the dataset and consider their impact on model training and outputs. ## License We release 🍃 MINT-1T under a CC-BY-4.0 license, designating it primarily as a research artifact. While the dataset is freely available, users are responsible for ensuring its legal use in commercial settings. Users must independently verify compliance with applicable laws before employing MINT-1T for commercial purposes. ## Citation ``` @article{awadalla2024mint1t, title={MINT-1T: Scaling Open-Source Multimodal Data by 10x: A Multimodal Dataset with One Trillion Tokens}, author={Anas Awadalla and Le Xue and Oscar Lo and Manli Shu and Hannah Lee and Etash Kumar Guha and Matt Jordan and Sheng Shen and Mohamed Awadalla and Silvio Savarese and Caiming Xiong and Ran Xu and Yejin Choi and Ludwig Schmidt}, year={2024} } ```

lmms-lab/LLaVA-Video-178K

lmms-lab

--- configs: - config_name: 0_30_s_academic_v0_1 data_files: - split: caption path: 0_30_s_academic_v0_1/*cap*.json - split: open_ended path: 0_30_s_academic_v0_1/*oe*.json - split: multi_choice path: 0_30_s_academic_v0_1/*mc*.json - config_name: 0_30_s_youtube_v0_1 data_files: - split: caption path: 0_30_s_youtube_v0_1/*cap*.json - split: open_ended path: 0_30_s_youtube_v0_1/*oe*.json - split: multi_choice path: 0_30_s_youtube_v0_1/*mc*.json - config_name: 0_30_s_activitynet data_files: - split: open_ended path: 0_30_s_activitynet/*oe*.json - config_name: 0_30_s_perceptiontest data_files: - split: multi_choice path: 0_30_s_perceptiontest/*mc*.json - config_name: 0_30_s_nextqa data_files: - split: open_ended path: 0_30_s_nextqa/*oe*.json - split: multi_choice path: 0_30_s_nextqa/*mc*.json - config_name: 30_60_s_academic_v0_1 data_files: - split: caption path: 30_60_s_academic_v0_1/*cap*.json - split: open_ended path: 30_60_s_academic_v0_1/*oe*.json - split: multi_choice path: 30_60_s_academic_v0_1/*mc*.json - config_name: 30_60_s_youtube_v0_1 data_files: - split: caption path: 30_60_s_youtube_v0_1/*cap*.json - split: open_ended path: 30_60_s_youtube_v0_1/*oe*.json - split: multi_choice path: 30_60_s_youtube_v0_1/*mc*.json - config_name: 30_60_s_activitynet data_files: - split: open_ended path: 30_60_s_activitynet/*oe*.json - config_name: 30_60_s_perceptiontest data_files: - split: multi_choice path: 30_60_s_perceptiontest/*mc*.json - config_name: 30_60_s_nextqa data_files: - split: open_ended path: 30_60_s_nextqa/*oe*.json - split: multi_choice path: 30_60_s_nextqa/*mc*.json - config_name: 1_2_m_youtube_v0_1 data_files: - split: caption path: 1_2_m_youtube_v0_1/*cap*.json - split: open_ended path: 1_2_m_youtube_v0_1/*oe*.json - split: multi_choice path: 1_2_m_youtube_v0_1/*mc*.json - config_name: 1_2_m_academic_v0_1 data_files: - split: caption path: 1_2_m_academic_v0_1/*cap*.json - split: open_ended path: 1_2_m_academic_v0_1/*oe*.json - split: multi_choice path: 1_2_m_academic_v0_1/*mc*.json - config_name: 1_2_m_activitynet data_files: - split: open_ended path: 1_2_m_activitynet/*oe*.json - config_name: 1_2_m_nextqa data_files: - split: open_ended path: 1_2_m_nextqa/*oe*.json - split: multi_choice path: 1_2_m_nextqa/*mc*.json - config_name: 2_3_m_youtube_v0_1 data_files: - split: caption path: 2_3_m_youtube_v0_1/*cap*.json - split: open_ended path: 2_3_m_youtube_v0_1/*oe*.json - split: multi_choice path: 2_3_m_youtube_v0_1/*mc*.json - config_name: 2_3_m_academic_v0_1 data_files: - split: caption path: 2_3_m_academic_v0_1/*cap*.json - split: open_ended path: 2_3_m_academic_v0_1/*oe*.json - split: multi_choice path: 2_3_m_academic_v0_1/*mc*.json - config_name: 2_3_m_activitynet data_files: - split: open_ended path: 2_3_m_activitynet/*oe*.json - config_name: 2_3_m_nextqa data_files: - split: open_ended path: 2_3_m_nextqa/*oe*.json - split: multi_choice path: 2_3_m_nextqa/*mc*.json - config_name: llava_hound data_files: - split: open_ended path: llava_hound/sharegptvideo_qa_255k_processed.json language: - en task_categories: - visual-question-answering - video-text-to-text tags: - video --- # Dataset Card for LLaVA-Video-178K ## Dataset Description - **Curated by:** Yuanhan Zhang, Jinming Wu, Wei Li - **Language(s) (NLP):** English, Chinese - **License:** Apache License 2.0 ## Uses This dataset is used for the training of the LLaVA-Video model. We only allow the use of this dataset for academic research and education purpose. For OpenAI GPT-4 generated data, we recommend the users to check the [OpenAI Usage Policy](https://openai.com/policies/usage-policies/). ### Data Sources For the training of LLaVA-Video, we utilized video-language data from five primary sources: - **LLaVA-Video-178K**: This dataset includes **178,510** caption entries, 960,792 open-ended QA (question and answer) items, and 196,198 multiple-choice QA items. These data were newly annotated for this project. - We include this dataset in this repository: LLaVA-Video-178K/XXX_academic_v0_1 and LLaVA-Video-178K/XXX_youtube_v0_1. - **NeXT-QA**: Comprises 17,090 open-ended QA items and 17,024 multiple-choice QA items. - We include this dataset in this repository: LLaVA-Video-178K/XXX_nextqa. - **ActivityNetQA**: Includes 23,530 open-ended QA items, - We include this dataset in this repository: LLaVA-Video-178K/XXX_activitynetqa. - **PerceptionTest**: Includes 1,803 open-ended QA items. - We include this dataset in this repository: LLaVA-Video-178K/XXX_perceptiontest. - **LLaVA-Hound**: Contains 240,000 open-ended QA items and 15,000 caption entries. - The video data and annotations are available at the following URLs: - Video data: [train_300k](https://huggingface.co./datasets/ShareGPTVideo/train_video_and_instruction/tree/main/train_300k) - Annotation data: LLaVA-Video-178K/llava_hound - loading function is specified here: [function](https://github.com/LLaVA-VL/LLaVA-NeXT/blob/7125e3654d88063cb467ed242db76f1e2b184d4c/llava/train/train.py#L1162) The **LLaVA-Video-178K** dataset is the only contribution from this repository; we provide additional datasets for reproducing LLaVA-Video. - **Project Page:** [Project Page](https://llava-vl.github.io/blog/2024-09-30-llava-video/). - **Paper**: For more details, please check our [paper](https://arxiv.org/abs/2410.02713) ### Annotation Pipeline The following directories are provided for generating captions and QA data: - **Captions**: `LLaVA-Video-178K/gpt4o_caption_prompt` - **QA**: `LLaVA-Video-178K/gpt4o_qa_prompt` ### The subset used in the LLaVA-OneVision We have included captions and open-ended questions in the [0_30_s_academic_v0_1 split](https://huggingface.co./datasets/lmms-lab/LLaVA-Video-178K/tree/main/0_30_s_academic_v0_1), along with 240,000 open-ended QA items and 15,000 caption entries, as part of the video data in LLaVA-Hound for LLaVA-OneVision. - [**0_30_s_academic_v0_1 caption**](https://huggingface.co./datasets/lmms-lab/LLaVA-Video-178K/blob/main/0_30_s_academic_v0_1/0_30_s_academic_v0_1_cap_processed.json) - [**0_30_s_academic_v0_1 open-ended QA**](https://huggingface.co./datasets/lmms-lab/LLaVA-Video-178K/blob/main/0_30_s_academic_v0_1/0_30_s_academic_v0_1_cap_processed.json) - **LLaVA-Hound**: Same as above. ## Citation ```bibtex @misc{zhang2024videoinstructiontuningsynthetic, title={Video Instruction Tuning With Synthetic Data}, author={Yuanhan Zhang and Jinming Wu and Wei Li and Bo Li and Zejun Ma and Ziwei Liu and Chunyuan Li}, year={2024}, eprint={2410.02713}, archivePrefix={arXiv}, primaryClass={cs.CV}, url={https://arxiv.org/abs/2410.02713}, } ``` ## Dataset Card Contact [Yuanhan Zhang](https://zhangyuanhan-ai.github.io/) [Jinming Wu](https://scholar.google.com/citations?user=eh-XJIoAAAAJ&hl=zh-CN) [Wei Li](https://scholar.google.com/citations?user=q8ZrKVIAAAAJ&hl=zh-CN)

dair-ai/emotion

dair-ai

--- annotations_creators: - machine-generated language_creators: - machine-generated language: - en license: - other multilinguality: - monolingual size_categories: - 10K<n<100K source_datasets: - original task_categories: - text-classification task_ids: - multi-class-classification paperswithcode_id: emotion pretty_name: Emotion tags: - emotion-classification dataset_info: - config_name: split features: - name: text dtype: string - name: label dtype: class_label: names: '0': sadness '1': joy '2': love '3': anger '4': fear '5': surprise splits: - name: train num_bytes: 1741533 num_examples: 16000 - name: validation num_bytes: 214695 num_examples: 2000 - name: test num_bytes: 217173 num_examples: 2000 download_size: 1287193 dataset_size: 2173401 - config_name: unsplit features: - name: text dtype: string - name: label dtype: class_label: names: '0': sadness '1': joy '2': love '3': anger '4': fear '5': surprise splits: - name: train num_bytes: 45444017 num_examples: 416809 download_size: 26888538 dataset_size: 45444017 configs: - config_name: split data_files: - split: train path: split/train-* - split: validation path: split/validation-* - split: test path: split/test-* default: true - config_name: unsplit data_files: - split: train path: unsplit/train-* train-eval-index: - config: default task: text-classification task_id: multi_class_classification splits: train_split: train eval_split: test col_mapping: text: text label: target metrics: - type: accuracy name: Accuracy - type: f1 name: F1 macro args: average: macro - type: f1 name: F1 micro args: average: micro - type: f1 name: F1 weighted args: average: weighted - type: precision name: Precision macro args: average: macro - type: precision name: Precision micro args: average: micro - type: precision name: Precision weighted args: average: weighted - type: recall name: Recall macro args: average: macro - type: recall name: Recall micro args: average: micro - type: recall name: Recall weighted args: average: weighted --- # Dataset Card for "emotion" ## Table of Contents - [Dataset Description](#dataset-description) - [Dataset Summary](#dataset-summary) - [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards) - [Languages](#languages) - [Dataset Structure](#dataset-structure) - [Data Instances](#data-instances) - [Data Fields](#data-fields) - [Data Splits](#data-splits) - [Dataset Creation](#dataset-creation) - [Curation Rationale](#curation-rationale) - [Source Data](#source-data) - [Annotations](#annotations) - [Personal and Sensitive Information](#personal-and-sensitive-information) - [Considerations for Using the Data](#considerations-for-using-the-data) - [Social Impact of Dataset](#social-impact-of-dataset) - [Discussion of Biases](#discussion-of-biases) - [Other Known Limitations](#other-known-limitations) - [Additional Information](#additional-information) - [Dataset Curators](#dataset-curators) - [Licensing Information](#licensing-information) - [Citation Information](#citation-information) - [Contributions](#contributions) ## Dataset Description - **Homepage:** [https://github.com/dair-ai/emotion_dataset](https://github.com/dair-ai/emotion_dataset) - **Repository:** [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) - **Paper:** [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) - **Point of Contact:** [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) - **Size of downloaded dataset files:** 16.13 MB - **Size of the generated dataset:** 47.62 MB - **Total amount of disk used:** 63.75 MB ### Dataset Summary Emotion is a dataset of English Twitter messages with six basic emotions: anger, fear, joy, love, sadness, and surprise. For more detailed information please refer to the paper. ### Supported Tasks and Leaderboards [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Languages [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ## Dataset Structure ### Data Instances An example looks as follows. ``` { "text": "im feeling quite sad and sorry for myself but ill snap out of it soon", "label": 0 } ``` ### Data Fields The data fields are: - `text`: a `string` feature. - `label`: a classification label, with possible values including `sadness` (0), `joy` (1), `love` (2), `anger` (3), `fear` (4), `surprise` (5). ### Data Splits The dataset has 2 configurations: - split: with a total of 20_000 examples split into train, validation and split - unsplit: with a total of 416_809 examples in a single train split | name | train | validation | test | |---------|-------:|-----------:|-----:| | split | 16000 | 2000 | 2000 | | unsplit | 416809 | n/a | n/a | ## Dataset Creation ### Curation Rationale [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Source Data #### Initial Data Collection and Normalization [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) #### Who are the source language producers? [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Annotations #### Annotation process [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) #### Who are the annotators? [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Personal and Sensitive Information [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ## Considerations for Using the Data ### Social Impact of Dataset [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Discussion of Biases [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Other Known Limitations [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ## Additional Information ### Dataset Curators [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Licensing Information The dataset should be used for educational and research purposes only. ### Citation Information If you use this dataset, please cite: ``` @inproceedings{saravia-etal-2018-carer, title = "{CARER}: Contextualized Affect Representations for Emotion Recognition", author = "Saravia, Elvis and Liu, Hsien-Chi Toby and Huang, Yen-Hao and Wu, Junlin and Chen, Yi-Shin", booktitle = "Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing", month = oct # "-" # nov, year = "2018", address = "Brussels, Belgium", publisher = "Association for Computational Linguistics", url = "https://www.aclweb.org/anthology/D18-1404", doi = "10.18653/v1/D18-1404", pages = "3687--3697", abstract = "Emotions are expressed in nuanced ways, which varies by collective or individual experiences, knowledge, and beliefs. Therefore, to understand emotion, as conveyed through text, a robust mechanism capable of capturing and modeling different linguistic nuances and phenomena is needed. We propose a semi-supervised, graph-based algorithm to produce rich structural descriptors which serve as the building blocks for constructing contextualized affect representations from text. The pattern-based representations are further enriched with word embeddings and evaluated through several emotion recognition tasks. Our experimental results demonstrate that the proposed method outperforms state-of-the-art techniques on emotion recognition tasks.", } ``` ### Contributions Thanks to [@lhoestq](https://github.com/lhoestq), [@thomwolf](https://github.com/thomwolf), [@lewtun](https://github.com/lewtun) for adding this dataset.

Helsinki-NLP/opus-100

Helsinki-NLP

--- annotations_creators: - no-annotation language_creators: - found language: - af - am - an - ar - as - az - be - bg - bn - br - bs - ca - cs - cy - da - de - dz - el - en - eo - es - et - eu - fa - fi - fr - fy - ga - gd - gl - gu - ha - he - hi - hr - hu - hy - id - ig - is - it - ja - ka - kk - km - kn - ko - ku - ky - li - lt - lv - mg - mk - ml - mn - mr - ms - mt - my - nb - ne - nl - nn - 'no' - oc - or - pa - pl - ps - pt - ro - ru - rw - se - sh - si - sk - sl - sq - sr - sv - ta - te - tg - th - tk - tr - tt - ug - uk - ur - uz - vi - wa - xh - yi - yo - zh - zu license: - unknown multilinguality: - translation size_categories: - 100K<n<1M - 10K<n<100K - 1K<n<10K - 1M<n<10M - n<1K source_datasets: - extended task_categories: - translation task_ids: [] paperswithcode_id: opus-100 pretty_name: OPUS-100 config_names: - af-en - am-en - an-en - ar-de - ar-en - ar-fr - ar-nl - ar-ru - ar-zh - as-en - az-en - be-en - bg-en - bn-en - br-en - bs-en - ca-en - cs-en - cy-en - da-en - de-en - de-fr - de-nl - de-ru - de-zh - dz-en - el-en - en-eo - en-es - en-et - en-eu - en-fa - en-fi - en-fr - en-fy - en-ga - en-gd - en-gl - en-gu - en-ha - en-he - en-hi - en-hr - en-hu - en-hy - en-id - en-ig - en-is - en-it - en-ja - en-ka - en-kk - en-km - en-kn - en-ko - en-ku - en-ky - en-li - en-lt - en-lv - en-mg - en-mk - en-ml - en-mn - en-mr - en-ms - en-mt - en-my - en-nb - en-ne - en-nl - en-nn - en-no - en-oc - en-or - en-pa - en-pl - en-ps - en-pt - en-ro - en-ru - en-rw - en-se - en-sh - en-si - en-sk - en-sl - en-sq - en-sr - en-sv - en-ta - en-te - en-tg - en-th - en-tk - en-tr - en-tt - en-ug - en-uk - en-ur - en-uz - en-vi - en-wa - en-xh - en-yi - en-yo - en-zh - en-zu - fr-nl - fr-ru - fr-zh - nl-ru - nl-zh - ru-zh dataset_info: - config_name: af-en features: - name: translation dtype: translation: languages: - af - en splits: - name: test num_bytes: 135908 num_examples: 2000 - name: train num_bytes: 18726247 num_examples: 275512 - name: validation num_bytes: 132769 num_examples: 2000 download_size: 14852797 dataset_size: 18994924 - config_name: am-en features: - name: translation dtype: translation: languages: - am - en splits: - name: test num_bytes: 588021 num_examples: 2000 - name: train num_bytes: 21950572 num_examples: 89027 - name: validation num_bytes: 566069 num_examples: 2000 download_size: 12630031 dataset_size: 23104662 - config_name: an-en features: - name: translation dtype: translation: languages: - an - en splits: - name: train num_bytes: 438324 num_examples: 6961 download_size: 232976 dataset_size: 438324 - config_name: ar-de features: - name: translation dtype: translation: languages: - ar - de splits: - name: test num_bytes: 238591 num_examples: 2000 download_size: 161557 dataset_size: 238591 - config_name: ar-en features: - name: translation dtype: translation: languages: - ar - en splits: - name: test num_bytes: 331640 num_examples: 2000 - name: train num_bytes: 152765684 num_examples: 1000000 - name: validation num_bytes: 2272098 num_examples: 2000 download_size: 100486814 dataset_size: 155369422 - config_name: ar-fr features: - name: translation dtype: translation: languages: - ar - fr splits: - name: test num_bytes: 547374 num_examples: 2000 download_size: 334226 dataset_size: 547374 - config_name: ar-nl features: - name: translation dtype: translation: languages: - ar - nl splits: - name: test num_bytes: 212928 num_examples: 2000 download_size: 144863 dataset_size: 212928 - config_name: ar-ru features: - name: translation dtype: translation: languages: - ar - ru splits: - name: test num_bytes: 808262 num_examples: 2000 download_size: 441536 dataset_size: 808262 - config_name: ar-zh features: - name: translation dtype: translation: languages: - ar - zh splits: - name: test num_bytes: 713404 num_examples: 2000 download_size: 438598 dataset_size: 713404 - config_name: as-en features: - name: translation dtype: translation: languages: - as - en splits: - name: test num_bytes: 261458 num_examples: 2000 - name: train num_bytes: 15634536 num_examples: 138479 - name: validation num_bytes: 248131 num_examples: 2000 download_size: 8794616 dataset_size: 16144125 - config_name: az-en features: - name: translation dtype: translation: languages: - az - en splits: - name: test num_bytes: 393101 num_examples: 2000 - name: train num_bytes: 56431043 num_examples: 262089 - name: validation num_bytes: 407101 num_examples: 2000 download_size: 34988859 dataset_size: 57231245 - config_name: be-en features: - name: translation dtype: translation: languages: - be - en splits: - name: test num_bytes: 166850 num_examples: 2000 - name: train num_bytes: 5298444 num_examples: 67312 - name: validation num_bytes: 175197 num_examples: 2000 download_size: 3807669 dataset_size: 5640491 - config_name: bg-en features: - name: translation dtype: translation: languages: - bg - en splits: - name: test num_bytes: 243743 num_examples: 2000 - name: train num_bytes: 108929547 num_examples: 1000000 - name: validation num_bytes: 234840 num_examples: 2000 download_size: 71575310 dataset_size: 109408130 - config_name: bn-en features: - name: translation dtype: translation: languages: - bn - en splits: - name: test num_bytes: 510093 num_examples: 2000 - name: train num_bytes: 249906046 num_examples: 1000000 - name: validation num_bytes: 498406 num_examples: 2000 download_size: 134076596 dataset_size: 250914545 - config_name: br-en features: - name: translation dtype: translation: languages: - br - en splits: - name: test num_bytes: 127917 num_examples: 2000 - name: train num_bytes: 8538878 num_examples: 153447 - name: validation num_bytes: 133764 num_examples: 2000 download_size: 6881865 dataset_size: 8800559 - config_name: bs-en features: - name: translation dtype: translation: languages: - bs - en splits: - name: test num_bytes: 168614 num_examples: 2000 - name: train num_bytes: 75082148 num_examples: 1000000 - name: validation num_bytes: 172473 num_examples: 2000 download_size: 59514403 dataset_size: 75423235 - config_name: ca-en features: - name: translation dtype: translation: languages: - ca - en splits: - name: test num_bytes: 205658 num_examples: 2000 - name: train num_bytes: 88404710 num_examples: 1000000 - name: validation num_bytes: 212629 num_examples: 2000 download_size: 68438385 dataset_size: 88822997 - config_name: cs-en features: - name: translation dtype: translation: languages: - cs - en splits: - name: test num_bytes: 205266 num_examples: 2000 - name: train num_bytes: 91896919 num_examples: 1000000 - name: validation num_bytes: 219076 num_examples: 2000 download_size: 73028514 dataset_size: 92321261 - config_name: cy-en features: - name: translation dtype: translation: languages: - cy - en splits: - name: test num_bytes: 124281 num_examples: 2000 - name: train num_bytes: 17244748 num_examples: 289521 - name: validation num_bytes: 118848 num_examples: 2000 download_size: 13398765 dataset_size: 17487877 - config_name: da-en features: - name: translation dtype: translation: languages: - da - en splits: - name: test num_bytes: 298115 num_examples: 2000 - name: train num_bytes: 126424474 num_examples: 1000000 - name: validation num_bytes: 300616 num_examples: 2000 download_size: 91005252 dataset_size: 127023205 - config_name: de-en features: - name: translation dtype: translation: languages: - de - en splits: - name: test num_bytes: 330951 num_examples: 2000 - name: train num_bytes: 152245956 num_examples: 1000000 - name: validation num_bytes: 332342 num_examples: 2000 download_size: 116680890 dataset_size: 152909249 - config_name: de-fr features: - name: translation dtype: translation: languages: - de - fr splits: - name: test num_bytes: 458738 num_examples: 2000 download_size: 311929 dataset_size: 458738 - config_name: de-nl features: - name: translation dtype: translation: languages: - de - nl splits: - name: test num_bytes: 403878 num_examples: 2000 download_size: 281548 dataset_size: 403878 - config_name: de-ru features: - name: translation dtype: translation: languages: - de - ru splits: - name: test num_bytes: 315771 num_examples: 2000 download_size: 203225 dataset_size: 315771 - config_name: de-zh features: - name: translation dtype: translation: languages: - de - zh splits: - name: test num_bytes: 280389 num_examples: 2000 download_size: 215301 dataset_size: 280389 - config_name: dz-en features: - name: translation dtype: translation: languages: - dz - en splits: - name: train num_bytes: 81154 num_examples: 624 download_size: 37361 dataset_size: 81154 - config_name: el-en features: - name: translation dtype: translation: languages: - el - en splits: - name: test num_bytes: 302385 num_examples: 2000 - name: train num_bytes: 127963903 num_examples: 1000000 - name: validation num_bytes: 291226 num_examples: 2000 download_size: 84137722 dataset_size: 128557514 - config_name: en-eo features: - name: translation dtype: translation: languages: - en - eo splits: - name: test num_bytes: 167378 num_examples: 2000 - name: train num_bytes: 24431681 num_examples: 337106 - name: validation num_bytes: 168830 num_examples: 2000 download_size: 19545461 dataset_size: 24767889 - config_name: en-es features: - name: translation dtype: translation: languages: - en - es splits: - name: test num_bytes: 326262 num_examples: 2000 - name: train num_bytes: 136643104 num_examples: 1000000 - name: validation num_bytes: 326727 num_examples: 2000 download_size: 100103907 dataset_size: 137296093 - config_name: en-et features: - name: translation dtype: translation: languages: - en - et splits: - name: test num_bytes: 272163 num_examples: 2000 - name: train num_bytes: 112298253 num_examples: 1000000 - name: validation num_bytes: 276954 num_examples: 2000 download_size: 83690450 dataset_size: 112847370 - config_name: en-eu features: - name: translation dtype: translation: languages: - en - eu splits: - name: test num_bytes: 280877 num_examples: 2000 - name: train num_bytes: 112329285 num_examples: 1000000 - name: validation num_bytes: 281495 num_examples: 2000 download_size: 84805467 dataset_size: 112891657 - config_name: en-fa features: - name: translation dtype: translation: languages: - en - fa splits: - name: test num_bytes: 296548 num_examples: 2000 - name: train num_bytes: 125400535 num_examples: 1000000 - name: validation num_bytes: 291121 num_examples: 2000 download_size: 82783248 dataset_size: 125988204 - config_name: en-fi features: - name: translation dtype: translation: languages: - en - fi splits: - name: test num_bytes: 245814 num_examples: 2000 - name: train num_bytes: 106024990 num_examples: 1000000 - name: validation num_bytes: 247219 num_examples: 2000 download_size: 79320220 dataset_size: 106518023 - config_name: en-fr features: - name: translation dtype: translation: languages: - en - fr splits: - name: test num_bytes: 469723 num_examples: 2000 - name: train num_bytes: 201440450 num_examples: 1000000 - name: validation num_bytes: 481476 num_examples: 2000 download_size: 142251860 dataset_size: 202391649 - config_name: en-fy features: - name: translation dtype: translation: languages: - en - fy splits: - name: test num_bytes: 101238 num_examples: 2000 - name: train num_bytes: 3895640 num_examples: 54342 - name: validation num_bytes: 100121 num_examples: 2000 download_size: 2984283 dataset_size: 4096999 - config_name: en-ga features: - name: translation dtype: translation: languages: - en - ga splits: - name: test num_bytes: 503309 num_examples: 2000 - name: train num_bytes: 42132510 num_examples: 289524 - name: validation num_bytes: 503209 num_examples: 2000 download_size: 27937448 dataset_size: 43139028 - config_name: en-gd features: - name: translation dtype: translation: languages: - en - gd splits: - name: test num_bytes: 218354 num_examples: 1606 - name: train num_bytes: 1254779 num_examples: 16316 - name: validation num_bytes: 203877 num_examples: 1605 download_size: 1124506 dataset_size: 1677010 - config_name: en-gl features: - name: translation dtype: translation: languages: - en - gl splits: - name: test num_bytes: 190691 num_examples: 2000 - name: train num_bytes: 43327028 num_examples: 515344 - name: validation num_bytes: 193598 num_examples: 2000 download_size: 34084028 dataset_size: 43711317 - config_name: en-gu features: - name: translation dtype: translation: languages: - en - gu splits: - name: test num_bytes: 199725 num_examples: 2000 - name: train num_bytes: 33641719 num_examples: 318306 - name: validation num_bytes: 205542 num_examples: 2000 download_size: 19235779 dataset_size: 34046986 - config_name: en-ha features: - name: translation dtype: translation: languages: - en - ha splits: - name: test num_bytes: 407344 num_examples: 2000 - name: train num_bytes: 20391884 num_examples: 97983 - name: validation num_bytes: 411518 num_examples: 2000 download_size: 12686187 dataset_size: 21210746 - config_name: en-he features: - name: translation dtype: translation: languages: - en - he splits: - name: test num_bytes: 208467 num_examples: 2000 - name: train num_bytes: 91159631 num_examples: 1000000 - name: validation num_bytes: 209438 num_examples: 2000 download_size: 61144758 dataset_size: 91577536 - config_name: en-hi features: - name: translation dtype: translation: languages: - en - hi splits: - name: test num_bytes: 496570 num_examples: 2000 - name: train num_bytes: 124923545 num_examples: 534319 - name: validation num_bytes: 474079 num_examples: 2000 download_size: 65725886 dataset_size: 125894194 - config_name: en-hr features: - name: translation dtype: translation: languages: - en - hr splits: - name: test num_bytes: 179636 num_examples: 2000 - name: train num_bytes: 75309516 num_examples: 1000000 - name: validation num_bytes: 179615 num_examples: 2000 download_size: 59468892 dataset_size: 75668767 - config_name: en-hu features: - name: translation dtype: translation: languages: - en - hu splits: - name: test num_bytes: 206039 num_examples: 2000 - name: train num_bytes: 87483462 num_examples: 1000000 - name: validation num_bytes: 208307 num_examples: 2000 download_size: 67971116 dataset_size: 87897808 - config_name: en-hy features: - name: translation dtype: translation: languages: - en - hy splits: - name: train num_bytes: 652623 num_examples: 7059 download_size: 422847 dataset_size: 652623 - config_name: en-id features: - name: translation dtype: translation: languages: - en - id splits: - name: test num_bytes: 177685 num_examples: 2000 - name: train num_bytes: 78698973 num_examples: 1000000 - name: validation num_bytes: 180024 num_examples: 2000 download_size: 57693678 dataset_size: 79056682 - config_name: en-ig features: - name: translation dtype: translation: languages: - en - ig splits: - name: test num_bytes: 137324 num_examples: 1843 - name: train num_bytes: 1612523 num_examples: 18415 - name: validation num_bytes: 135987 num_examples: 1843 download_size: 859440 dataset_size: 1885834 - config_name: en-is features: - name: translation dtype: translation: languages: - en - is splits: - name: test num_bytes: 170879 num_examples: 2000 - name: train num_bytes: 73964115 num_examples: 1000000 - name: validation num_bytes: 170632 num_examples: 2000 download_size: 56242149 dataset_size: 74305626 - config_name: en-it features: - name: translation dtype: translation: languages: - en - it splits: - name: test num_bytes: 299029 num_examples: 2000 - name: train num_bytes: 123654286 num_examples: 1000000 - name: validation num_bytes: 294354 num_examples: 2000 download_size: 92133897 dataset_size: 124247669 - config_name: en-ja features: - name: translation dtype: translation: languages: - en - ja splits: - name: test num_bytes: 190991 num_examples: 2000 - name: train num_bytes: 88348569 num_examples: 1000000 - name: validation num_bytes: 191411 num_examples: 2000 download_size: 64817108 dataset_size: 88730971 - config_name: en-ka features: - name: translation dtype: translation: languages: - en - ka splits: - name: test num_bytes: 256219 num_examples: 2000 - name: train num_bytes: 42465402 num_examples: 377306 - name: validation num_bytes: 260408 num_examples: 2000 download_size: 24394633 dataset_size: 42982029 - config_name: en-kk features: - name: translation dtype: translation: languages: - en - kk splits: - name: test num_bytes: 137656 num_examples: 2000 - name: train num_bytes: 7124314 num_examples: 79927 - name: validation num_bytes: 139657 num_examples: 2000 download_size: 4808360 dataset_size: 7401627 - config_name: en-km features: - name: translation dtype: translation: languages: - en - km splits: - name: test num_bytes: 289019 num_examples: 2000 - name: train num_bytes: 19680515 num_examples: 111483 - name: validation num_bytes: 302519 num_examples: 2000 download_size: 10022919 dataset_size: 20272053 - config_name: en-kn features: - name: translation dtype: translation: languages: - en - kn splits: - name: test num_bytes: 77197 num_examples: 918 - name: train num_bytes: 1833318 num_examples: 14537 - name: validation num_bytes: 77599 num_examples: 917 download_size: 1062554 dataset_size: 1988114 - config_name: en-ko features: - name: translation dtype: translation: languages: - en - ko splits: - name: test num_bytes: 190688 num_examples: 2000 - name: train num_bytes: 93664532 num_examples: 1000000 - name: validation num_bytes: 189360 num_examples: 2000 download_size: 70383271 dataset_size: 94044580 - config_name: en-ku features: - name: translation dtype: translation: languages: - en - ku splits: - name: test num_bytes: 247839 num_examples: 2000 - name: train num_bytes: 49107744 num_examples: 144844 - name: validation num_bytes: 239317 num_examples: 2000 download_size: 25358389 dataset_size: 49594900 - config_name: en-ky features: - name: translation dtype: translation: languages: - en - ky splits: - name: test num_bytes: 142522 num_examples: 2000 - name: train num_bytes: 1879274 num_examples: 27215 - name: validation num_bytes: 138479 num_examples: 2000 download_size: 1338686 dataset_size: 2160275 - config_name: en-li features: - name: translation dtype: translation: languages: - en - li splits: - name: test num_bytes: 93342 num_examples: 2000 - name: train num_bytes: 1628577 num_examples: 25535 - name: validation num_bytes: 92898 num_examples: 2000 download_size: 1040760 dataset_size: 1814817 - config_name: en-lt features: - name: translation dtype: translation: languages: - en - lt splits: - name: test num_bytes: 482607 num_examples: 2000 - name: train num_bytes: 177060244 num_examples: 1000000 - name: validation num_bytes: 469109 num_examples: 2000 download_size: 124444053 dataset_size: 178011960 - config_name: en-lv features: - name: translation dtype: translation: languages: - en - lv splits: - name: test num_bytes: 536568 num_examples: 2000 - name: train num_bytes: 206051049 num_examples: 1000000 - name: validation num_bytes: 522064 num_examples: 2000 download_size: 140538527 dataset_size: 207109681 - config_name: en-mg features: - name: translation dtype: translation: languages: - en - mg splits: - name: test num_bytes: 525059 num_examples: 2000 - name: train num_bytes: 130865169 num_examples: 590771 - name: validation num_bytes: 511163 num_examples: 2000 download_size: 91102165 dataset_size: 131901391 - config_name: en-mk features: - name: translation dtype: translation: languages: - en - mk splits: - name: test num_bytes: 308926 num_examples: 2000 - name: train num_bytes: 117068689 num_examples: 1000000 - name: validation num_bytes: 305490 num_examples: 2000 download_size: 76810811 dataset_size: 117683105 - config_name: en-ml features: - name: translation dtype: translation: languages: - en - ml splits: - name: test num_bytes: 340618 num_examples: 2000 - name: train num_bytes: 199971079 num_examples: 822746 - name: validation num_bytes: 334451 num_examples: 2000 download_size: 95497482 dataset_size: 200646148 - config_name: en-mn features: - name: translation dtype: translation: languages: - en - mn splits: - name: train num_bytes: 250770 num_examples: 4294 download_size: 85037 dataset_size: 250770 - config_name: en-mr features: - name: translation dtype: translation: languages: - en - mr splits: - name: test num_bytes: 238604 num_examples: 2000 - name: train num_bytes: 2724107 num_examples: 27007 - name: validation num_bytes: 235532 num_examples: 2000 download_size: 1838618 dataset_size: 3198243 - config_name: en-ms features: - name: translation dtype: translation: languages: - en - ms splits: - name: test num_bytes: 179697 num_examples: 2000 - name: train num_bytes: 76828845 num_examples: 1000000 - name: validation num_bytes: 180175 num_examples: 2000 download_size: 57412836 dataset_size: 77188717 - config_name: en-mt features: - name: translation dtype: translation: languages: - en - mt splits: - name: test num_bytes: 566126 num_examples: 2000 - name: train num_bytes: 222221596 num_examples: 1000000 - name: validation num_bytes: 594378 num_examples: 2000 download_size: 147836637 dataset_size: 223382100 - config_name: en-my features: - name: translation dtype: translation: languages: - en - my splits: - name: test num_bytes: 337343 num_examples: 2000 - name: train num_bytes: 3673477 num_examples: 24594 - name: validation num_bytes: 336147 num_examples: 2000 download_size: 1952573 dataset_size: 4346967 - config_name: en-nb features: - name: translation dtype: translation: languages: - en - nb splits: - name: test num_bytes: 334109 num_examples: 2000 - name: train num_bytes: 13611589 num_examples: 142906 - name: validation num_bytes: 324392 num_examples: 2000 download_size: 10630769 dataset_size: 14270090 - config_name: en-ne features: - name: translation dtype: translation: languages: - en - ne splits: - name: test num_bytes: 186519 num_examples: 2000 - name: train num_bytes: 44135952 num_examples: 406381 - name: validation num_bytes: 204912 num_examples: 2000 download_size: 24107523 dataset_size: 44527383 - config_name: en-nl features: - name: translation dtype: translation: languages: - en - nl splits: - name: test num_bytes: 282747 num_examples: 2000 - name: train num_bytes: 112326273 num_examples: 1000000 - name: validation num_bytes: 270932 num_examples: 2000 download_size: 82923916 dataset_size: 112879952 - config_name: en-nn features: - name: translation dtype: translation: languages: - en - nn splits: - name: test num_bytes: 178999 num_examples: 2000 - name: train num_bytes: 32924429 num_examples: 486055 - name: validation num_bytes: 187642 num_examples: 2000 download_size: 25184676 dataset_size: 33291070 - config_name: en-no features: - name: translation dtype: translation: languages: - en - 'no' splits: - name: test num_bytes: 173320 num_examples: 2000 - name: train num_bytes: 74105483 num_examples: 1000000 - name: validation num_bytes: 178005 num_examples: 2000 download_size: 56277000 dataset_size: 74456808 - config_name: en-oc features: - name: translation dtype: translation: languages: - en - oc splits: - name: test num_bytes: 82342 num_examples: 2000 - name: train num_bytes: 1627174 num_examples: 35791 - name: validation num_bytes: 81642 num_examples: 2000 download_size: 1308338 dataset_size: 1791158 - config_name: en-or features: - name: translation dtype: translation: languages: - en - or splits: - name: test num_bytes: 163939 num_examples: 1318 - name: train num_bytes: 1500733 num_examples: 14273 - name: validation num_bytes: 155323 num_examples: 1317 download_size: 1019971 dataset_size: 1819995 - config_name: en-pa features: - name: translation dtype: translation: languages: - en - pa splits: - name: test num_bytes: 133901 num_examples: 2000 - name: train num_bytes: 8509140 num_examples: 107296 - name: validation num_bytes: 136188 num_examples: 2000 download_size: 5315298 dataset_size: 8779229 - config_name: en-pl features: - name: translation dtype: translation: languages: - en - pl splits: - name: test num_bytes: 212495 num_examples: 2000 - name: train num_bytes: 95247723 num_examples: 1000000 - name: validation num_bytes: 218208 num_examples: 2000 download_size: 73574044 dataset_size: 95678426 - config_name: en-ps features: - name: translation dtype: translation: languages: - en - ps splits: - name: test num_bytes: 92995 num_examples: 2000 - name: train num_bytes: 4436512 num_examples: 79127 - name: validation num_bytes: 95156 num_examples: 2000 download_size: 2851899 dataset_size: 4624663 - config_name: en-pt features: - name: translation dtype: translation: languages: - en - pt splits: - name: test num_bytes: 296114 num_examples: 2000 - name: train num_bytes: 118242849 num_examples: 1000000 - name: validation num_bytes: 292074 num_examples: 2000 download_size: 87661907 dataset_size: 118831037 - config_name: en-ro features: - name: translation dtype: translation: languages: - en - ro splits: - name: test num_bytes: 198639 num_examples: 2000 - name: train num_bytes: 85249051 num_examples: 1000000 - name: validation num_bytes: 199164 num_examples: 2000 download_size: 66294317 dataset_size: 85646854 - config_name: en-ru features: - name: translation dtype: translation: languages: - en - ru splits: - name: test num_bytes: 490976 num_examples: 2000 - name: train num_bytes: 195100937 num_examples: 1000000 - name: validation num_bytes: 490238 num_examples: 2000 download_size: 124460816 dataset_size: 196082151 - config_name: en-rw features: - name: translation dtype: translation: languages: - en - rw splits: - name: test num_bytes: 136189 num_examples: 2000 - name: train num_bytes: 15286159 num_examples: 173823 - name: validation num_bytes: 134957 num_examples: 2000 download_size: 10093708 dataset_size: 15557305 - config_name: en-se features: - name: translation dtype: translation: languages: - en - se splits: - name: test num_bytes: 85697 num_examples: 2000 - name: train num_bytes: 2047380 num_examples: 35907 - name: validation num_bytes: 83664 num_examples: 2000 download_size: 1662845 dataset_size: 2216741 - config_name: en-sh features: - name: translation dtype: translation: languages: - en - sh splits: - name: test num_bytes: 569479 num_examples: 2000 - name: train num_bytes: 60900023 num_examples: 267211 - name: validation num_bytes: 555594 num_examples: 2000 download_size: 39988454 dataset_size: 62025096 - config_name: en-si features: - name: translation dtype: translation: languages: - en - si splits: - name: test num_bytes: 271735 num_examples: 2000 - name: train num_bytes: 114950891 num_examples: 979109 - name: validation num_bytes: 271236 num_examples: 2000 download_size: 66124160 dataset_size: 115493862 - config_name: en-sk features: - name: translation dtype: translation: languages: - en - sk splits: - name: test num_bytes: 258034 num_examples: 2000 - name: train num_bytes: 111743068 num_examples: 1000000 - name: validation num_bytes: 255462 num_examples: 2000 download_size: 85223330 dataset_size: 112256564 - config_name: en-sl features: - name: translation dtype: translation: languages: - en - sl splits: - name: test num_bytes: 205470 num_examples: 2000 - name: train num_bytes: 90270157 num_examples: 1000000 - name: validation num_bytes: 198654 num_examples: 2000 download_size: 70708189 dataset_size: 90674281 - config_name: en-sq features: - name: translation dtype: translation: languages: - en - sq splits: - name: test num_bytes: 275371 num_examples: 2000 - name: train num_bytes: 105745181 num_examples: 1000000 - name: validation num_bytes: 267304 num_examples: 2000 download_size: 78817895 dataset_size: 106287856 - config_name: en-sr features: - name: translation dtype: translation: languages: - en - sr splits: - name: test num_bytes: 180224 num_examples: 2000 - name: train num_bytes: 75726035 num_examples: 1000000 - name: validation num_bytes: 184238 num_examples: 2000 download_size: 60263688 dataset_size: 76090497 - config_name: en-sv features: - name: translation dtype: translation: languages: - en - sv splits: - name: test num_bytes: 271006 num_examples: 2000 - name: train num_bytes: 116985153 num_examples: 1000000 - name: validation num_bytes: 279986 num_examples: 2000 download_size: 85032127 dataset_size: 117536145 - config_name: en-ta features: - name: translation dtype: translation: languages: - en - ta splits: - name: test num_bytes: 351982 num_examples: 2000 - name: train num_bytes: 74044340 num_examples: 227014 - name: validation num_bytes: 335549 num_examples: 2000 download_size: 33642694 dataset_size: 74731871 - config_name: en-te features: - name: translation dtype: translation: languages: - en - te splits: - name: test num_bytes: 190587 num_examples: 2000 - name: train num_bytes: 6688569 num_examples: 64352 - name: validation num_bytes: 193658 num_examples: 2000 download_size: 4047667 dataset_size: 7072814 - config_name: en-tg features: - name: translation dtype: translation: languages: - en - tg splits: - name: test num_bytes: 372112 num_examples: 2000 - name: train num_bytes: 35477017 num_examples: 193882 - name: validation num_bytes: 371720 num_examples: 2000 download_size: 21242668 dataset_size: 36220849 - config_name: en-th features: - name: translation dtype: translation: languages: - en - th splits: - name: test num_bytes: 290573 num_examples: 2000 - name: train num_bytes: 132820231 num_examples: 1000000 - name: validation num_bytes: 288358 num_examples: 2000 download_size: 75539987 dataset_size: 133399162 - config_name: en-tk features: - name: translation dtype: translation: languages: - en - tk splits: - name: test num_bytes: 83878 num_examples: 1852 - name: train num_bytes: 719617 num_examples: 13110 - name: validation num_bytes: 81006 num_examples: 1852 download_size: 417756 dataset_size: 884501 - config_name: en-tr features: - name: translation dtype: translation: languages: - en - tr splits: - name: test num_bytes: 183825 num_examples: 2000 - name: train num_bytes: 78945565 num_examples: 1000000 - name: validation num_bytes: 181909 num_examples: 2000 download_size: 60364921 dataset_size: 79311299 - config_name: en-tt features: - name: translation dtype: translation: languages: - en - tt splits: - name: test num_bytes: 693268 num_examples: 2000 - name: train num_bytes: 35313170 num_examples: 100843 - name: validation num_bytes: 701662 num_examples: 2000 download_size: 18786998 dataset_size: 36708100 - config_name: en-ug features: - name: translation dtype: translation: languages: - en - ug splits: - name: test num_bytes: 620873 num_examples: 2000 - name: train num_bytes: 31576516 num_examples: 72170 - name: validation num_bytes: 631228 num_examples: 2000 download_size: 16011372 dataset_size: 32828617 - config_name: en-uk features: - name: translation dtype: translation: languages: - en - uk splits: - name: test num_bytes: 249742 num_examples: 2000 - name: train num_bytes: 104229556 num_examples: 1000000 - name: validation num_bytes: 247123 num_examples: 2000 download_size: 71155682 dataset_size: 104726421 - config_name: en-ur features: - name: translation dtype: translation: languages: - en - ur splits: - name: test num_bytes: 538556 num_examples: 2000 - name: train num_bytes: 268960696 num_examples: 753913 - name: validation num_bytes: 529308 num_examples: 2000 download_size: 148336044 dataset_size: 270028560 - config_name: en-uz features: - name: translation dtype: translation: languages: - en - uz splits: - name: test num_bytes: 408675 num_examples: 2000 - name: train num_bytes: 38375290 num_examples: 173157 - name: validation num_bytes: 398853 num_examples: 2000 download_size: 21873536 dataset_size: 39182818 - config_name: en-vi features: - name: translation dtype: translation: languages: - en - vi splits: - name: test num_bytes: 192744 num_examples: 2000 - name: train num_bytes: 82614470 num_examples: 1000000 - name: validation num_bytes: 194721 num_examples: 2000 download_size: 59250852 dataset_size: 83001935 - config_name: en-wa features: - name: translation dtype: translation: languages: - en - wa splits: - name: test num_bytes: 87091 num_examples: 2000 - name: train num_bytes: 6085860 num_examples: 104496 - name: validation num_bytes: 87718 num_examples: 2000 download_size: 4512204 dataset_size: 6260669 - config_name: en-xh features: - name: translation dtype: translation: languages: - en - xh splits: - name: test num_bytes: 318652 num_examples: 2000 - name: train num_bytes: 50606896 num_examples: 439671 - name: validation num_bytes: 315831 num_examples: 2000 download_size: 37519365 dataset_size: 51241379 - config_name: en-yi features: - name: translation dtype: translation: languages: - en - yi splits: - name: test num_bytes: 96482 num_examples: 2000 - name: train num_bytes: 1275127 num_examples: 15010 - name: validation num_bytes: 99818 num_examples: 2000 download_size: 650530 dataset_size: 1471427 - config_name: en-yo features: - name: translation dtype: translation: languages: - en - yo splits: - name: train num_bytes: 979753 num_examples: 10375 download_size: 391299 dataset_size: 979753 - config_name: en-zh features: - name: translation dtype: translation: languages: - en - zh splits: - name: test num_bytes: 511364 num_examples: 2000 - name: train num_bytes: 200062183 num_examples: 1000000 - name: validation num_bytes: 512356 num_examples: 2000 download_size: 143414756 dataset_size: 201085903 - config_name: en-zu features: - name: translation dtype: translation: languages: - en - zu splits: - name: test num_bytes: 117510 num_examples: 2000 - name: train num_bytes: 2799558 num_examples: 38616 - name: validation num_bytes: 120133 num_examples: 2000 download_size: 1918443 dataset_size: 3037201 - config_name: fr-nl features: - name: translation dtype: translation: languages: - fr - nl splits: - name: test num_bytes: 368638 num_examples: 2000 download_size: 261290 dataset_size: 368638 - config_name: fr-ru features: - name: translation dtype: translation: languages: - fr - ru splits: - name: test num_bytes: 732716 num_examples: 2000 download_size: 426179 dataset_size: 732716 - config_name: fr-zh features: - name: translation dtype: translation: languages: - fr - zh splits: - name: test num_bytes: 619386 num_examples: 2000 download_size: 418661 dataset_size: 619386 - config_name: nl-ru features: - name: translation dtype: translation: languages: - nl - ru splits: - name: test num_bytes: 256059 num_examples: 2000 download_size: 168666 dataset_size: 256059 - config_name: nl-zh features: - name: translation dtype: translation: languages: - nl - zh splits: - name: test num_bytes: 183633 num_examples: 2000 download_size: 146191 dataset_size: 183633 - config_name: ru-zh features: - name: translation dtype: translation: languages: - ru - zh splits: - name: test num_bytes: 916106 num_examples: 2000 download_size: 534430 dataset_size: 916106 configs: - config_name: af-en data_files: - split: test path: af-en/test-* - split: train path: af-en/train-* - split: validation path: af-en/validation-* - config_name: am-en data_files: - split: test path: am-en/test-* - split: train path: am-en/train-* - split: validation path: am-en/validation-* - config_name: an-en data_files: - split: train path: an-en/train-* - config_name: ar-de data_files: - split: test path: ar-de/test-* - config_name: ar-en data_files: - split: test path: ar-en/test-* - split: train path: ar-en/train-* - split: validation path: ar-en/validation-* - config_name: ar-fr data_files: - split: test path: ar-fr/test-* - config_name: ar-nl data_files: - split: test path: ar-nl/test-* - config_name: ar-ru data_files: - split: test path: ar-ru/test-* - config_name: ar-zh data_files: - split: test path: ar-zh/test-* - config_name: as-en data_files: - split: test path: as-en/test-* - split: train path: as-en/train-* - split: validation path: as-en/validation-* - config_name: az-en data_files: - split: test path: az-en/test-* - split: train path: az-en/train-* - split: validation path: az-en/validation-* - config_name: be-en data_files: - split: test path: be-en/test-* - split: train path: be-en/train-* - split: validation path: be-en/validation-* - config_name: bg-en data_files: - split: test path: bg-en/test-* - split: train path: bg-en/train-* - split: validation path: bg-en/validation-* - config_name: bn-en data_files: - split: test path: bn-en/test-* - split: train path: bn-en/train-* - split: validation path: bn-en/validation-* - config_name: br-en data_files: - split: test path: br-en/test-* - split: train path: br-en/train-* - split: validation path: br-en/validation-* - config_name: bs-en data_files: - split: test path: bs-en/test-* - split: train path: bs-en/train-* - split: validation path: bs-en/validation-* - config_name: ca-en data_files: - split: test path: ca-en/test-* - split: train path: ca-en/train-* - split: validation path: ca-en/validation-* - config_name: cs-en data_files: - split: test path: cs-en/test-* - split: train path: cs-en/train-* - split: validation path: cs-en/validation-* - config_name: cy-en data_files: - split: test path: cy-en/test-* - split: train path: cy-en/train-* - split: validation path: cy-en/validation-* - config_name: da-en data_files: - split: test path: da-en/test-* - split: train path: da-en/train-* - split: validation path: da-en/validation-* - config_name: de-en data_files: - split: test path: de-en/test-* - split: train path: de-en/train-* - split: validation path: de-en/validation-* - config_name: de-fr data_files: - split: test path: de-fr/test-* - config_name: de-nl data_files: - split: test path: de-nl/test-* - config_name: de-ru data_files: - split: test path: de-ru/test-* - config_name: de-zh data_files: - split: test path: de-zh/test-* - config_name: dz-en data_files: - split: train path: dz-en/train-* - config_name: el-en data_files: - split: test path: el-en/test-* - split: train path: el-en/train-* - split: validation path: el-en/validation-* - config_name: en-eo data_files: - split: test path: en-eo/test-* - split: train path: en-eo/train-* - split: validation path: en-eo/validation-* - config_name: en-es data_files: - split: test path: en-es/test-* - split: train path: en-es/train-* - split: validation path: en-es/validation-* - config_name: en-et data_files: - split: test path: en-et/test-* - split: train path: en-et/train-* - split: validation path: en-et/validation-* - config_name: en-eu data_files: - split: test path: en-eu/test-* - split: train path: en-eu/train-* - split: validation path: en-eu/validation-* - config_name: en-fa data_files: - split: test path: en-fa/test-* - split: train path: en-fa/train-* - split: validation path: en-fa/validation-* - config_name: en-fi data_files: - split: test path: en-fi/test-* - split: train path: en-fi/train-* - split: validation path: en-fi/validation-* - config_name: en-fr data_files: - split: test path: en-fr/test-* - split: train path: en-fr/train-* - split: validation path: en-fr/validation-* - config_name: en-fy data_files: - split: test path: en-fy/test-* - split: train path: en-fy/train-* - split: validation path: en-fy/validation-* - config_name: en-ga data_files: - split: test path: en-ga/test-* - split: train path: en-ga/train-* - split: validation path: en-ga/validation-* - config_name: en-gd data_files: - split: test path: en-gd/test-* - split: train path: en-gd/train-* - split: validation path: en-gd/validation-* - config_name: en-gl data_files: - split: test path: en-gl/test-* - split: train path: en-gl/train-* - split: validation path: en-gl/validation-* - config_name: en-gu data_files: - split: test path: en-gu/test-* - split: train path: en-gu/train-* - split: validation path: en-gu/validation-* - config_name: en-ha data_files: - split: test path: en-ha/test-* - split: train path: en-ha/train-* - split: validation path: en-ha/validation-* - config_name: en-he data_files: - split: test path: en-he/test-* - split: train path: en-he/train-* - split: validation path: en-he/validation-* - config_name: en-hi data_files: - split: test path: en-hi/test-* - split: train path: en-hi/train-* - split: validation path: en-hi/validation-* - config_name: en-hr data_files: - split: test path: en-hr/test-* - split: train path: en-hr/train-* - split: validation path: en-hr/validation-* - config_name: en-hu data_files: - split: test path: en-hu/test-* - split: train path: en-hu/train-* - split: validation path: en-hu/validation-* - config_name: en-hy data_files: - split: train path: en-hy/train-* - config_name: en-id data_files: - split: test path: en-id/test-* - split: train path: en-id/train-* - split: validation path: en-id/validation-* - config_name: en-ig data_files: - split: test path: en-ig/test-* - split: train path: en-ig/train-* - split: validation path: en-ig/validation-* - config_name: en-is data_files: - split: test path: en-is/test-* - split: train path: en-is/train-* - split: validation path: en-is/validation-* - config_name: en-it data_files: - split: test path: en-it/test-* - split: train path: en-it/train-* - split: validation path: en-it/validation-* - config_name: en-ja data_files: - split: test path: en-ja/test-* - split: train path: en-ja/train-* - split: validation path: en-ja/validation-* - config_name: en-ka data_files: - split: test path: en-ka/test-* - split: train path: en-ka/train-* - split: validation path: en-ka/validation-* - config_name: en-kk data_files: - split: test path: en-kk/test-* - split: train path: en-kk/train-* - split: validation path: en-kk/validation-* - config_name: en-km data_files: - split: test path: en-km/test-* - split: train path: en-km/train-* - split: validation path: en-km/validation-* - config_name: en-kn data_files: - split: test path: en-kn/test-* - split: train path: en-kn/train-* - split: validation path: en-kn/validation-* - config_name: en-ko data_files: - split: test path: en-ko/test-* - split: train path: en-ko/train-* - split: validation path: en-ko/validation-* - config_name: en-ku data_files: - split: test path: en-ku/test-* - split: train path: en-ku/train-* - split: validation path: en-ku/validation-* - config_name: en-ky data_files: - split: test path: en-ky/test-* - split: train path: en-ky/train-* - split: validation path: en-ky/validation-* - config_name: en-li data_files: - split: test path: en-li/test-* - split: train path: en-li/train-* - split: validation path: en-li/validation-* - config_name: en-lt data_files: - split: test path: en-lt/test-* - split: train path: en-lt/train-* - split: validation path: en-lt/validation-* - config_name: en-lv data_files: - split: test path: en-lv/test-* - split: train path: en-lv/train-* - split: validation path: en-lv/validation-* - config_name: en-mg data_files: - split: test path: en-mg/test-* - split: train path: en-mg/train-* - split: validation path: en-mg/validation-* - config_name: en-mk data_files: - split: test path: en-mk/test-* - split: train path: en-mk/train-* - split: validation path: en-mk/validation-* - config_name: en-ml data_files: - split: test path: en-ml/test-* - split: train path: en-ml/train-* - split: validation path: en-ml/validation-* - config_name: en-mn data_files: - split: train path: en-mn/train-* - config_name: en-mr data_files: - split: test path: en-mr/test-* - split: train path: en-mr/train-* - split: validation path: en-mr/validation-* - config_name: en-ms data_files: - split: test path: en-ms/test-* - split: train path: en-ms/train-* - split: validation path: en-ms/validation-* - config_name: en-mt data_files: - split: test path: en-mt/test-* - split: train path: en-mt/train-* - split: validation path: en-mt/validation-* - config_name: en-my data_files: - split: test path: en-my/test-* - split: train path: en-my/train-* - split: validation path: en-my/validation-* - config_name: en-nb data_files: - split: test path: en-nb/test-* - split: train path: en-nb/train-* - split: validation path: en-nb/validation-* - config_name: en-ne data_files: - split: test path: en-ne/test-* - split: train path: en-ne/train-* - split: validation path: en-ne/validation-* - config_name: en-nl data_files: - split: test path: en-nl/test-* - split: train path: en-nl/train-* - split: validation path: en-nl/validation-* - config_name: en-nn data_files: - split: test path: en-nn/test-* - split: train path: en-nn/train-* - split: validation path: en-nn/validation-* - config_name: en-no data_files: - split: test path: en-no/test-* - split: train path: en-no/train-* - split: validation path: en-no/validation-* - config_name: en-oc data_files: - split: test path: en-oc/test-* - split: train path: en-oc/train-* - split: validation path: en-oc/validation-* - config_name: en-or data_files: - split: test path: en-or/test-* - split: train path: en-or/train-* - split: validation path: en-or/validation-* - config_name: en-pa data_files: - split: test path: en-pa/test-* - split: train path: en-pa/train-* - split: validation path: en-pa/validation-* - config_name: en-pl data_files: - split: test path: en-pl/test-* - split: train path: en-pl/train-* - split: validation path: en-pl/validation-* - config_name: en-ps data_files: - split: test path: en-ps/test-* - split: train path: en-ps/train-* - split: validation path: en-ps/validation-* - config_name: en-pt data_files: - split: test path: en-pt/test-* - split: train path: en-pt/train-* - split: validation path: en-pt/validation-* - config_name: en-ro data_files: - split: test path: en-ro/test-* - split: train path: en-ro/train-* - split: validation path: en-ro/validation-* - config_name: en-ru data_files: - split: test path: en-ru/test-* - split: train path: en-ru/train-* - split: validation path: en-ru/validation-* - config_name: en-rw data_files: - split: test path: en-rw/test-* - split: train path: en-rw/train-* - split: validation path: en-rw/validation-* - config_name: en-se data_files: - split: test path: en-se/test-* - split: train path: en-se/train-* - split: validation path: en-se/validation-* - config_name: en-sh data_files: - split: test path: en-sh/test-* - split: train path: en-sh/train-* - split: validation path: en-sh/validation-* - config_name: en-si data_files: - split: test path: en-si/test-* - split: train path: en-si/train-* - split: validation path: en-si/validation-* - config_name: en-sk data_files: - split: test path: en-sk/test-* - split: train path: en-sk/train-* - split: validation path: en-sk/validation-* - config_name: en-sl data_files: - split: test path: en-sl/test-* - split: train path: en-sl/train-* - split: validation path: en-sl/validation-* - config_name: en-sq data_files: - split: test path: en-sq/test-* - split: train path: en-sq/train-* - split: validation path: en-sq/validation-* - config_name: en-sr data_files: - split: test path: en-sr/test-* - split: train path: en-sr/train-* - split: validation path: en-sr/validation-* - config_name: en-sv data_files: - split: test path: en-sv/test-* - split: train path: en-sv/train-* - split: validation path: en-sv/validation-* - config_name: en-ta data_files: - split: test path: en-ta/test-* - split: train path: en-ta/train-* - split: validation path: en-ta/validation-* - config_name: en-te data_files: - split: test path: en-te/test-* - split: train path: en-te/train-* - split: validation path: en-te/validation-* - config_name: en-tg data_files: - split: test path: en-tg/test-* - split: train path: en-tg/train-* - split: validation path: en-tg/validation-* - config_name: en-th data_files: - split: test path: en-th/test-* - split: train path: en-th/train-* - split: validation path: en-th/validation-* - config_name: en-tk data_files: - split: test path: en-tk/test-* - split: train path: en-tk/train-* - split: validation path: en-tk/validation-* - config_name: en-tr data_files: - split: test path: en-tr/test-* - split: train path: en-tr/train-* - split: validation path: en-tr/validation-* - config_name: en-tt data_files: - split: test path: en-tt/test-* - split: train path: en-tt/train-* - split: validation path: en-tt/validation-* - config_name: en-ug data_files: - split: test path: en-ug/test-* - split: train path: en-ug/train-* - split: validation path: en-ug/validation-* - config_name: en-uk data_files: - split: test path: en-uk/test-* - split: train path: en-uk/train-* - split: validation path: en-uk/validation-* - config_name: en-ur data_files: - split: test path: en-ur/test-* - split: train path: en-ur/train-* - split: validation path: en-ur/validation-* - config_name: en-uz data_files: - split: test path: en-uz/test-* - split: train path: en-uz/train-* - split: validation path: en-uz/validation-* - config_name: en-vi data_files: - split: test path: en-vi/test-* - split: train path: en-vi/train-* - split: validation path: en-vi/validation-* - config_name: en-wa data_files: - split: test path: en-wa/test-* - split: train path: en-wa/train-* - split: validation path: en-wa/validation-* - config_name: en-xh data_files: - split: test path: en-xh/test-* - split: train path: en-xh/train-* - split: validation path: en-xh/validation-* - config_name: en-yi data_files: - split: test path: en-yi/test-* - split: train path: en-yi/train-* - split: validation path: en-yi/validation-* - config_name: en-yo data_files: - split: train path: en-yo/train-* - config_name: en-zh data_files: - split: test path: en-zh/test-* - split: train path: en-zh/train-* - split: validation path: en-zh/validation-* - config_name: en-zu data_files: - split: test path: en-zu/test-* - split: train path: en-zu/train-* - split: validation path: en-zu/validation-* - config_name: fr-nl data_files: - split: test path: fr-nl/test-* - config_name: fr-ru data_files: - split: test path: fr-ru/test-* - config_name: fr-zh data_files: - split: test path: fr-zh/test-* - config_name: nl-ru data_files: - split: test path: nl-ru/test-* - config_name: nl-zh data_files: - split: test path: nl-zh/test-* - config_name: ru-zh data_files: - split: test path: ru-zh/test-* --- # Dataset Card for OPUS-100 ## Table of Contents - [Dataset Description](#dataset-description) - [Dataset Summary](#dataset-summary) - [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards) - [Languages](#languages) - [Dataset Structure](#dataset-structure) - [Data Instances](#data-instances) - [Data Fields](#data-fields) - [Data Splits](#data-splits) - [Dataset Creation](#dataset-creation) - [Curation Rationale](#curation-rationale) - [Source Data](#source-data) - [Annotations](#annotations) - [Personal and Sensitive Information](#personal-and-sensitive-information) - [Considerations for Using the Data](#considerations-for-using-the-data) - [Social Impact of Dataset](#social-impact-of-dataset) - [Discussion of Biases](#discussion-of-biases) - [Other Known Limitations](#other-known-limitations) - [Additional Information](#additional-information) - [Dataset Curators](#dataset-curators) - [Licensing Information](#licensing-information) - [Citation Information](#citation-information) - [Contributions](#contributions) ## Dataset Description - **Homepage:** https://opus.nlpl.eu/OPUS-100 - **Repository:** https://github.com/EdinburghNLP/opus-100-corpus - **Paper:** https://arxiv.org/abs/2004.11867 - **Paper:** https://aclanthology.org/L10-1473/ - **Leaderboard:** [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) - **Point of Contact:** [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Dataset Summary OPUS-100 is an English-centric multilingual corpus covering 100 languages. OPUS-100 is English-centric, meaning that all training pairs include English on either the source or target side. The corpus covers 100 languages (including English). The languages were selected based on the volume of parallel data available in OPUS. ### Supported Tasks and Leaderboards Translation. ### Languages OPUS-100 contains approximately 55M sentence pairs. Of the 99 language pairs, 44 have 1M sentence pairs of training data, 73 have at least 100k, and 95 have at least 10k. ## Dataset Structure ### Data Instances ``` { "translation": { "ca": "El departament de bombers té el seu propi equip d'investigació.", "en": "Well, the fire department has its own investigative unit." } } ``` ### Data Fields - `translation` (`dict`): Parallel sentences for the pair of languages. ### Data Splits The dataset is split into training, development, and test portions. Data was prepared by randomly sampled up to 1M sentence pairs per language pair for training and up to 2000 each for development and test. To ensure that there was no overlap (at the monolingual sentence level) between the training and development/test data, they applied a filter during sampling to exclude sentences that had already been sampled. Note that this was done cross-lingually so that, for instance, an English sentence in the Portuguese-English portion of the training data could not occur in the Hindi-English test set. ## Dataset Creation ### Curation Rationale [More Information Needed] ### Source Data [More Information Needed] #### Initial Data Collection and Normalization [More Information Needed] #### Who are the source language producers? [More Information Needed] ### Annotations #### Annotation process [More Information Needed] #### Who are the annotators? [More Information Needed] ### Personal and Sensitive Information [More Information Needed] ## Considerations for Using the Data ### Social Impact of Dataset [More Information Needed] ### Discussion of Biases [More Information Needed] ### Other Known Limitations [More Information Needed] ## Additional Information ### Dataset Curators [More Information Needed] ### Licensing Information [More Information Needed] ### Citation Information If you use this corpus, please cite the paper: ```bibtex @inproceedings{zhang-etal-2020-improving, title = "Improving Massively Multilingual Neural Machine Translation and Zero-Shot Translation", author = "Zhang, Biao and Williams, Philip and Titov, Ivan and Sennrich, Rico", editor = "Jurafsky, Dan and Chai, Joyce and Schluter, Natalie and Tetreault, Joel", booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics", month = jul, year = "2020", address = "Online", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2020.acl-main.148", doi = "10.18653/v1/2020.acl-main.148", pages = "1628--1639", } ``` and, please, also acknowledge OPUS: ```bibtex @inproceedings{tiedemann-2012-parallel, title = "Parallel Data, Tools and Interfaces in {OPUS}", author = {Tiedemann, J{\"o}rg}, editor = "Calzolari, Nicoletta and Choukri, Khalid and Declerck, Thierry and Do{\u{g}}an, Mehmet U{\u{g}}ur and Maegaard, Bente and Mariani, Joseph and Moreno, Asuncion and Odijk, Jan and Piperidis, Stelios", booktitle = "Proceedings of the Eighth International Conference on Language Resources and Evaluation ({LREC}'12)", month = may, year = "2012", address = "Istanbul, Turkey", publisher = "European Language Resources Association (ELRA)", url = "http://www.lrec-conf.org/proceedings/lrec2012/pdf/463_Paper.pdf", pages = "2214--2218", } ``` ### Contributions Thanks to [@vasudevgupta7](https://github.com/vasudevgupta7) for adding this dataset.

mteb/scifact

mteb

--- language: - en multilinguality: - monolingual task_categories: - text-retrieval source_datasets: - scifact task_ids: - document-retrieval config_names: - corpus tags: - text-retrieval dataset_info: - config_name: default features: - name: query-id dtype: string - name: corpus-id dtype: string - name: score dtype: float64 splits: - name: train num_bytes: 24585 num_examples: 919 - name: test num_bytes: 9092 num_examples: 339 - config_name: corpus features: - name: _id dtype: string - name: title dtype: string - name: text dtype: string splits: - name: corpus num_bytes: 7874970 num_examples: 5183 - config_name: queries features: - name: _id dtype: string - name: text dtype: string splits: - name: queries num_bytes: 111225 num_examples: 1109 configs: - config_name: default data_files: - split: train path: qrels/train.jsonl - split: test path: qrels/test.jsonl - config_name: corpus data_files: - split: corpus path: corpus.jsonl - config_name: queries data_files: - split: queries path: queries.jsonl ---

orionweller/reddit_mds_incremental

orionweller

--- dataset_info: features: [] splits: - name: creation num_bytes: 0 num_examples: 0 download_size: 324 dataset_size: 0 configs: - config_name: default data_files: - split: creation path: data/creation-* ---

mlfoundations/MINT-1T-PDF-CC-2023-06

mlfoundations

--- license: cc-by-4.0 task_categories: - image-to-text - text-generation language: - en tags: - multimodal pretty_name: MINT-1T size_categories: - 100B<n<1T --- <h1 align="center"> 🍃 MINT-1T:<br>Scaling Open-Source Multimodal Data by 10x:<br> A Multimodal Dataset with One Trillion Tokens </h1> 🍃 MINT-1T is an open-source **M**ultimodal **INT**erleaved dataset with 1 trillion text tokens and 3.4 billion images, a 10x scale-up from existing open-source datasets. Additionally, we include previously untapped sources such as PDFs and ArXiv papers. 🍃 MINT-1T is designed to facilitate research in multimodal pretraining. 🍃 MINT-1T is created by a team from the University of Washington in collaboration with Salesforce Research, other academic institutions including Stanford University, University of Texas at Austin, and University of California Berkeley. You are currently viewing a subset of the PDF portion of 🍃 MINT-1T associated with CommonCrawl dump `CC-2023-06`. For other PDF, HTML, and ArXiv subsets, refer to the [🍃 MINT-1T collection](https://huggingface.co./collections/mlfoundations/mint-1t-6690216ca4d0df7e518dde1c).  ## Updates ### 9/19/24 We have removed roughly 10% of the PDF samples as there was a mismatch between the frames in the TIFF images and the document metadata. ### 8/8/24 We have become aware that the image hashes in the PDF subset of MINT-1T do not match the images in the documents. We want to emphasize that the images for each document are correct, and only the image hashes in the documents' metadata are mislabeled. ## Dataset Details ### Dataset Sources - **Repository**: https://github.com/mlfoundations/MINT-1T - **Paper:** https://arxiv.org/abs/2406.11271 - **Blog:** https://blog.salesforceairesearch.com/mint-1t/ ## Uses ### Direct Use <!-- This section describes suitable use cases for the dataset. --> 🍃 MINT-1T is designed to facilitate research in multimodal pretraining. The dataset can be used for training multimodal models that can reson about interleaved text and images sequences such as [Idefics2](https://huggingface.co./HuggingFaceM4/idefics2-8b), [XGen-MM](https://huggingface.co./Salesforce/xgen-mm-phi3-mini-instruct-r-v1), and [Chameleon](https://huggingface.co./facebook/chameleon-30b). ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the dataset will not work well for. --> 🍃 MINT-1T was built to make research into large multimodal models more accessible. Using the dataset to train models that ingest or generate personally identifying information (such as images of people’s faces and other sensitive content) as well as military applications are all inappropriate use cases of 🍃 MINT-1T. ## Dataset Creation ### Curation Rationale 🍃 MINT-1T was created to address a significant gap in the open-source domain by providing a large-scale multimodal interleaved dataset for pre-training large multimodal models. This dataset aims to be a valuable resource for the research community, facilitating open science in multimodal pretraining. ### Source Data The dataset is a comprehensive collection of multimodal documents from various sources: - HTML documents: Filtered from CommonCrawl WARC dumps spanning from 2017 to 2024 - PDF documents: Extracted from CommonCrawl WAT dumps covering 2023 to 2024 - ArXiv documents: A subset of papers from the ArXiv repository In total, 🍃 MINT-1T contains 1056.8 million documents, broken down as follows: - 1029.4 million HTML documents - 24.0 million PDF documents - 0.6 million ArXiv documents #### Data Collection and Processing The data collection and processing involved several steps: 1. Document Extraction: - HTML documents were parsed from CommonCrawl WARC files - PDF documents were extracted from CommonCrawl WAT files - ArXiv papers were directly sourced from ArXiv S3 buckets 2. Filtering Process: - Applied text quality filters to ensure content relevance and readability - Removed duplicate content at both paragraph and document levels - Filtered out undesirable content based on predefined criteria - Verified image availability and quality for HTML documents - Limited PDF size to 50MB and 50 pages to manage dataset size and quality 3. Image Processing: - Used NSFW image detection to remove pornographic or otherwise undesirable images - Removed images smaller than 150 pixels or larger than 20,000 pixels - Adjusted aspect ratio thresholds for HTML (2:1) and PDF (3:1) to preserve scientific figures 4. Text Processing: - Used fasttext for language identification, focusing on English content - Masked personally identifiable information such as email addresses and IP addresses - Applied paragraph and document-level deduplication using Bloom filters 5. PDF Specific Processing: - Used PyMuPDF for parsing PDFs and extracting reading order - Clustered text blocks based on columns and ordered from top left to bottom right 6. ArXiv Specific Processing: - Used TexSoup to parse LaTeX source code and interleave images with text - Cleaned up LaTeX code by removing imports, bibliography, tables, and citation tags Various open-source tools were utilized in this process, including fasttext, [PyMuPDF](https://github.com/pymupdf/PyMuPDF), and [DCLM](https://www.datacomp.ai/dclm/) and [bff](https://github.com/revbucket/bff) for deduplication and content filtering. #### Personal and Sensitive Information Despite sourcing from public web data, significant efforts were made to minimize the inclusion of personal and sensitive information: - Email addresses and IP addresses were masked to protect privacy - An NSFW image classifierto remove inappropriate visual content - URLs containing substrings associated with undesirable or sensitive content were filtered out However, users should be aware that as the data originates from the public web, it may still contain some sensitive or personal information. The dataset creators acknowledge this limitation and advise users to exercise caution and potentially apply additional filtering based on their specific use cases. ## Bias, Risks, and Limitations Several potential biases, risks, and limitations have been identified: 1. Data Bias: As the dataset is sourced from web crawls, it may inherit biases present in online content. 2. Content Risks: Despite extensive filtering, there's a possibility that some offensive, insensitive, or inappropriate content may remain in the dataset. 3. Image Availability: The dataset relies on external image URLs, which may become unavailable over time due to link rot, potentially affecting the dataset's long-term usability. 4. PDF Parsing Limitations: The current method for extracting reading order from PDFs may not always accurately capture the intended flow, especially for documents with complex layouts. 5. Potential Legal and Ethical Concerns: While efforts were made to respect robots.txt files and remove sensitive information, there may still be content that individuals did not explicitly consent to include. ### Recommendations Given these considerations, the following recommendations are provided: 1. Additional Filtering: Users are strongly encouraged to apply additional filtering based on their specific use case and ethical considerations. 2. Inappropriate Use Cases: The dataset is not recommended for applications involving the processing or generation of personally identifying information, nor for military applications. 3. Legal Compliance: Users should independently verify compliance with applicable laws before employing MINT-1T for commercial purposes. 4. Bias Awareness: Researchers and developers should be cognizant of potential biases in the dataset and consider their impact on model training and outputs. ## License We release 🍃 MINT-1T under a CC-BY-4.0 license, designating it primarily as a research artifact. While the dataset is freely available, users are responsible for ensuring its legal use in commercial settings. Users must independently verify compliance with applicable laws before employing MINT-1T for commercial purposes. ## Citation ``` @article{awadalla2024mint1t, title={MINT-1T: Scaling Open-Source Multimodal Data by 10x: A Multimodal Dataset with One Trillion Tokens}, author={Anas Awadalla and Le Xue and Oscar Lo and Manli Shu and Hannah Lee and Etash Kumar Guha and Matt Jordan and Sheng Shen and Mohamed Awadalla and Silvio Savarese and Caiming Xiong and Ran Xu and Yejin Choi and Ludwig Schmidt}, year={2024} } ```

anon8231489123/ShareGPT_Vicuna_unfiltered

anon8231489123

--- license: apache-2.0 language: - en --- **Further cleaning done. Please look through the dataset and ensure that I didn't miss anything.** **Update: Confirmed working method for training the model: https://huggingface.co./AlekseyKorshuk/vicuna-7b/discussions/4#64346c08ef6d5abefe42c12c** Two choices: - Removes instances of "I'm sorry, but": https://huggingface.co./datasets/anon8231489123/ShareGPT_Vicuna_unfiltered/blob/main/ShareGPT_V3_unfiltered_cleaned_split_no_imsorry.json - Has instances of "I'm sorry, but": https://huggingface.co./datasets/anon8231489123/ShareGPT_Vicuna_unfiltered/blob/main/ShareGPT_V3_unfiltered_cleaned_split.json The choice is yours. The first dataset may go to far and remove valuable data. The second is better for when the AI asks for clarification, but it also may refuse to do stuff like browse the internet, which it actually may be able to do with certain langchain implementations. These are important things to think about before training. ~100k ShareGPT conversations narrowed down to 53k by: * Removing non-english conversations * Removing excessive unicode (indicative of Chinese or Korean text, usually) * Removing excessive repeated characters * Removing various instances "AI Moralizing". Conversations with these phrases were removed (and a few others that can't be mentioned here): "text-based AI language model", "domestic violence", "please refrain", "derogatory", "inappropriate", "offensive", "racism", "racist", "racial", "discriminate", "discriminatory", "discrimination", "sexist", "sexism", "unacceptable", "inclusive workplace", "lgbt", "morals", "ethics", "ethical", "legality", "illegal", "illegality", "hateful", "harmful", "it is never okay", "It is important to", "It's important to", "real-world consequences", "hate speech", "glorify", "not be appropriate", "supremacist", "extremist", "responsible AI", "AI principles", "AI assistant", "an AI language", "ableist", "hurtful", "gender stereotype", "gender inequality", "underrepresentation", "safe spaces", "gender-based", "inclusivity", "feminist", "feminism", "transgender", "empowerment", "communist", "capitalism", "stereotypes", "biases", "bias", "Microaggression", "prioritize human safety", "as a language model", "as an AI language model", "As a large language model", "As an AI", "ethical principles", "consensual", "it is not appropriate", "it's not appropriate", "I cannot fulfill your request", "harmful to human beings", "ethical guidelines", "my guidelines", "prioritize user safety", "adhere to ethical guidelines", "harmful consequences", "potentially harmful", "dangerous activities", "promote safety", "well-being of all users", "responsible information sharing", "jeopardize the safety", "illegal actions or intentions", "undermine the stability", "promote the well-being", "illegal activities or actions", "adherence to the law", "potentially be harmful", "illegal substances or activities", "committed to promoting", "safe information", "lawful information", "cannot provide guidance", "cannot provide information", "unable to offer assistance", "cannot engage in discussions", "programming prohibits", "follow ethical guidelines", "ensure the safety", "involves an illegal subject", "prioritize safety", "illegal subject", "prioritize user well-being", "cannot support or promote", "activities that could harm", "pose a risk to others", "against my programming", "activities that could undermine", "potentially dangerous", "not within the scope", "designed to prioritize safety", "not able to provide", "maintain user safety", "adhere to safety guidelines", "dangerous or harmful", "cannot provide any information", "focus on promoting safety" * Conversations split into 2048 token chunks as described here: https://github.com/lm-sys/FastChat/blob/main/docs/commands/data_cleaning.md This should be fully ready to train an unfiltered english Vicuna model based on the procedure here: https://github.com/lm-sys/FastChat/

poloclub/diffusiondb

poloclub

--- layout: default title: Home nav_order: 1 has_children: false annotations_creators: - no-annotation language: - en language_creators: - found license: - cc0-1.0 multilinguality: - multilingual pretty_name: DiffusionDB size_categories: - n>1T source_datasets: - original tags: - stable diffusion - prompt engineering - prompts - research paper task_categories: - text-to-image - image-to-text task_ids: - image-captioning --- # DiffusionDB <img width="100%" src="https://user-images.githubusercontent.com/15007159/201762588-f24db2b8-dbb2-4a94-947b-7de393fc3d33.gif"> ## Table of Contents - [DiffusionDB](#diffusiondb) - [Table of Contents](#table-of-contents) - [Dataset Description](#dataset-description) - [Dataset Summary](#dataset-summary) - [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards) - [Languages](#languages) - [Two Subsets](#two-subsets) - [Key Differences](#key-differences) - [Dataset Structure](#dataset-structure) - [Data Instances](#data-instances) - [Data Fields](#data-fields) - [Dataset Metadata](#dataset-metadata) - [Metadata Schema](#metadata-schema) - [Data Splits](#data-splits) - [Loading Data Subsets](#loading-data-subsets) - [Method 1: Using Hugging Face Datasets Loader](#method-1-using-hugging-face-datasets-loader) - [Method 2. Use the PoloClub Downloader](#method-2-use-the-poloclub-downloader) - [Usage/Examples](#usageexamples) - [Downloading a single file](#downloading-a-single-file) - [Downloading a range of files](#downloading-a-range-of-files) - [Downloading to a specific directory](#downloading-to-a-specific-directory) - [Setting the files to unzip once they've been downloaded](#setting-the-files-to-unzip-once-theyve-been-downloaded) - [Method 3. Use `metadata.parquet` (Text Only)](#method-3-use-metadataparquet-text-only) - [Dataset Creation](#dataset-creation) - [Curation Rationale](#curation-rationale) - [Source Data](#source-data) - [Initial Data Collection and Normalization](#initial-data-collection-and-normalization) - [Who are the source language producers?](#who-are-the-source-language-producers) - [Annotations](#annotations) - [Annotation process](#annotation-process) - [Who are the annotators?](#who-are-the-annotators) - [Personal and Sensitive Information](#personal-and-sensitive-information) - [Considerations for Using the Data](#considerations-for-using-the-data) - [Social Impact of Dataset](#social-impact-of-dataset) - [Discussion of Biases](#discussion-of-biases) - [Other Known Limitations](#other-known-limitations) - [Additional Information](#additional-information) - [Dataset Curators](#dataset-curators) - [Licensing Information](#licensing-information) - [Citation Information](#citation-information) - [Contributions](#contributions) ## Dataset Description - **Homepage:** [DiffusionDB homepage](https://poloclub.github.io/diffusiondb) - **Repository:** [DiffusionDB repository](https://github.com/poloclub/diffusiondb) - **Distribution:** [DiffusionDB Hugging Face Dataset](https://huggingface.co./datasets/poloclub/diffusiondb) - **Paper:** [DiffusionDB: A Large-scale Prompt Gallery Dataset for Text-to-Image Generative Models](https://arxiv.org/abs/2210.14896) - **Point of Contact:** [Jay Wang](mailto:[email protected]) ### Dataset Summary DiffusionDB is the first large-scale text-to-image prompt dataset. It contains **14 million** images generated by Stable Diffusion using prompts and hyperparameters specified by real users. DiffusionDB is publicly available at [🤗 Hugging Face Dataset](https://huggingface.co./datasets/poloclub/diffusiondb). ### Supported Tasks and Leaderboards The unprecedented scale and diversity of this human-actuated dataset provide exciting research opportunities in understanding the interplay between prompts and generative models, detecting deepfakes, and designing human-AI interaction tools to help users more easily use these models. ### Languages The text in the dataset is mostly English. It also contains other languages such as Spanish, Chinese, and Russian. ### Two Subsets DiffusionDB provides two subsets (DiffusionDB 2M and DiffusionDB Large) to support different needs. |Subset|Num of Images|Num of Unique Prompts|Size|Image Directory|Metadata Table| |:--|--:|--:|--:|--:|--:| |DiffusionDB 2M|2M|1.5M|1.6TB|`images/`|`metadata.parquet`| |DiffusionDB Large|14M|1.8M|6.5TB|`diffusiondb-large-part-1/` `diffusiondb-large-part-2/`|`metadata-large.parquet`| ##### Key Differences 1. Two subsets have a similar number of unique prompts, but DiffusionDB Large has much more images. DiffusionDB Large is a superset of DiffusionDB 2M. 2. Images in DiffusionDB 2M are stored in `png` format; images in DiffusionDB Large use a lossless `webp` format. ## Dataset Structure We use a modularized file structure to distribute DiffusionDB. The 2 million images in DiffusionDB 2M are split into 2,000 folders, where each folder contains 1,000 images and a JSON file that links these 1,000 images to their prompts and hyperparameters. Similarly, the 14 million images in DiffusionDB Large are split into 14,000 folders. ```bash # DiffusionDB 2M ./ ├── images │   ├── part-000001 │   │   ├── 3bfcd9cf-26ea-4303-bbe1-b095853f5360.png │   │   ├── 5f47c66c-51d4-4f2c-a872-a68518f44adb.png │   │   ├── 66b428b9-55dc-4907-b116-55aaa887de30.png │   │   ├── [...] │   │   └── part-000001.json │   ├── part-000002 │   ├── part-000003 │   ├── [...] │   └── part-002000 └── metadata.parquet ``` ```bash # DiffusionDB Large ./ ├── diffusiondb-large-part-1 │   ├── part-000001 │   │   ├── 0a8dc864-1616-4961-ac18-3fcdf76d3b08.webp │   │   ├── 0a25cacb-5d91-4f27-b18a-bd423762f811.webp │   │   ├── 0a52d584-4211-43a0-99ef-f5640ee2fc8c.webp │   │   ├── [...] │   │   └── part-000001.json │   ├── part-000002 │   ├── part-000003 │   ├── [...] │   └── part-010000 ├── diffusiondb-large-part-2 │   ├── part-010001 │   │   ├── 0a68f671-3776-424c-91b6-c09a0dd6fc2d.webp │   │   ├── 0a0756e9-1249-4fe2-a21a-12c43656c7a3.webp │   │   ├── 0aa48f3d-f2d9-40a8-a800-c2c651ebba06.webp │   │   ├── [...] │   │   └── part-000001.json │   ├── part-010002 │   ├── part-010003 │   ├── [...] │   └── part-014000 └── metadata-large.parquet ``` These sub-folders have names `part-0xxxxx`, and each image has a unique name generated by [UUID Version 4](https://en.wikipedia.org/wiki/Universally_unique_identifier). The JSON file in a sub-folder has the same name as the sub-folder. Each image is a `PNG` file (DiffusionDB 2M) or a lossless `WebP` file (DiffusionDB Large). The JSON file contains key-value pairs mapping image filenames to their prompts and hyperparameters. ### Data Instances For example, below is the image of `f3501e05-aef7-4225-a9e9-f516527408ac.png` and its key-value pair in `part-000001.json`. <img width="300" src="https://i.imgur.com/gqWcRs2.png"> ```json { "f3501e05-aef7-4225-a9e9-f516527408ac.png": { "p": "geodesic landscape, john chamberlain, christopher balaskas, tadao ando, 4 k, ", "se": 38753269, "c": 12.0, "st": 50, "sa": "k_lms" }, } ``` ### Data Fields - key: Unique image name - `p`: Prompt - `se`: Random seed - `c`: CFG Scale (guidance scale) - `st`: Steps - `sa`: Sampler ### Dataset Metadata To help you easily access prompts and other attributes of images without downloading all the Zip files, we include two metadata tables `metadata.parquet` and `metadata-large.parquet` for DiffusionDB 2M and DiffusionDB Large, respectively. The shape of `metadata.parquet` is (2000000, 13) and the shape of `metatable-large.parquet` is (14000000, 13). Two tables share the same schema, and each row represents an image. We store these tables in the Parquet format because Parquet is column-based: you can efficiently query individual columns (e.g., prompts) without reading the entire table. Below are three random rows from `metadata.parquet`. | image_name | prompt | part_id | seed | step | cfg | sampler | width | height | user_name | timestamp | image_nsfw | prompt_nsfw | |:-----------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|----------:|-----------:|-------:|------:|----------:|--------:|---------:|:-----------------------------------------------------------------|:--------------------------|-------------:|--------------:| | 0c46f719-1679-4c64-9ba9-f181e0eae811.png | a small liquid sculpture, corvette, viscous, reflective, digital art | 1050 | 2026845913 | 50 | 7 | 8 | 512 | 512 | c2f288a2ba9df65c38386ffaaf7749106fed29311835b63d578405db9dbcafdb | 2022-08-11 09:05:00+00:00 | 0.0845108 | 0.00383462 | | a00bdeaa-14eb-4f6c-a303-97732177eae9.png | human sculpture of lanky tall alien on a romantic date at italian restaurant with smiling woman, nice restaurant, photography, bokeh | 905 | 1183522603 | 50 | 10 | 8 | 512 | 768 | df778e253e6d32168eb22279a9776b3cde107cc82da05517dd6d114724918651 | 2022-08-19 17:55:00+00:00 | 0.692934 | 0.109437 | | 6e5024ce-65ed-47f3-b296-edb2813e3c5b.png | portrait of barbaric spanish conquistador, symmetrical, by yoichi hatakenaka, studio ghibli and dan mumford | 286 | 1713292358 | 50 | 7 | 8 | 512 | 640 | 1c2e93cfb1430adbd956be9c690705fe295cbee7d9ac12de1953ce5e76d89906 | 2022-08-12 03:26:00+00:00 | 0.0773138 | 0.0249675 | #### Metadata Schema `metadata.parquet` and `metatable-large.parquet` share the same schema. |Column|Type|Description| |:---|:---|:---| |`image_name`|`string`|Image UUID filename.| |`prompt`|`string`|The text prompt used to generate this image.| |`part_id`|`uint16`|Folder ID of this image.| |`seed`|`uint32`| Random seed used to generate this image.| |`step`|`uint16`| Step count (hyperparameter).| |`cfg`|`float32`| Guidance scale (hyperparameter).| |`sampler`|`uint8`| Sampler method (hyperparameter). Mapping: `{1: "ddim", 2: "plms", 3: "k_euler", 4: "k_euler_ancestral", 5: "k_heun", 6: "k_dpm_2", 7: "k_dpm_2_ancestral", 8: "k_lms", 9: "others"}`. |`width`|`uint16`|Image width.| |`height`|`uint16`|Image height.| |`user_name`|`string`|The unique discord ID's SHA256 hash of the user who generated this image. For example, the hash for `xiaohk#3146` is `e285b7ef63be99e9107cecd79b280bde602f17e0ca8363cb7a0889b67f0b5ed0`. "deleted_account" refer to users who have deleted their accounts. None means the image has been deleted before we scrape it for the second time.| |`timestamp`|`timestamp`|UTC Timestamp when this image was generated. None means the image has been deleted before we scrape it for the second time. Note that timestamp is not accurate for duplicate images that have the same prompt, hypareparameters, width, height.| |`image_nsfw`|`float32`|Likelihood of an image being NSFW. Scores are predicted by [LAION's state-of-art NSFW detector](https://github.com/LAION-AI/LAION-SAFETY) (range from 0 to 1). A score of 2.0 means the image has already been flagged as NSFW and blurred by Stable Diffusion.| |`prompt_nsfw`|`float32`|Likelihood of a prompt being NSFW. Scores are predicted by the library [Detoxicy](https://github.com/unitaryai/detoxify). Each score represents the maximum of `toxicity` and `sexual_explicit` (range from 0 to 1).| > **Warning** > Although the Stable Diffusion model has an NSFW filter that automatically blurs user-generated NSFW images, this NSFW filter is not perfect—DiffusionDB still contains some NSFW images. Therefore, we compute and provide the NSFW scores for images and prompts using the state-of-the-art models. The distribution of these scores is shown below. Please decide an appropriate NSFW score threshold to filter out NSFW images before using DiffusionDB in your projects. <img src="https://i.imgur.com/1RiGAXL.png" width="100%"> ### Data Splits For DiffusionDB 2M, we split 2 million images into 2,000 folders where each folder contains 1,000 images and a JSON file. For DiffusionDB Large, we split 14 million images into 14,000 folders where each folder contains 1,000 images and a JSON file. ### Loading Data Subsets DiffusionDB is large (1.6TB or 6.5 TB)! However, with our modularized file structure, you can easily load a desirable number of images and their prompts and hyperparameters. In the [`example-loading.ipynb`](https://github.com/poloclub/diffusiondb/blob/main/notebooks/example-loading.ipynb) notebook, we demonstrate three methods to load a subset of DiffusionDB. Below is a short summary. #### Method 1: Using Hugging Face Datasets Loader You can use the Hugging Face [`Datasets`](https://huggingface.co./docs/datasets/quickstart) library to easily load prompts and images from DiffusionDB. We pre-defined 16 DiffusionDB subsets (configurations) based on the number of instances. You can see all subsets in the [Dataset Preview](https://huggingface.co./datasets/poloclub/diffusiondb/viewer/all/train). ```python import numpy as np from datasets import load_dataset # Load the dataset with the `large_random_1k` subset dataset = load_dataset('poloclub/diffusiondb', 'large_random_1k') ``` #### Method 2. Use the PoloClub Downloader This repo includes a Python downloader [`download.py`](https://github.com/poloclub/diffusiondb/blob/main/scripts/download.py) that allows you to download and load DiffusionDB. You can use it from your command line. Below is an example of loading a subset of DiffusionDB. ##### Usage/Examples The script is run using command-line arguments as follows: - `-i` `--index` - File to download or lower bound of a range of files if `-r` is also set. - `-r` `--range` - Upper bound of range of files to download if `-i` is set. - `-o` `--output` - Name of custom output directory. Defaults to the current directory if not set. - `-z` `--unzip` - Unzip the file/files after downloading - `-l` `--large` - Download from Diffusion DB Large. Defaults to Diffusion DB 2M. ###### Downloading a single file The specific file to download is supplied as the number at the end of the file on HuggingFace. The script will automatically pad the number out and generate the URL. ```bash python download.py -i 23 ``` ###### Downloading a range of files The upper and lower bounds of the set of files to download are set by the `-i` and `-r` flags respectively. ```bash python download.py -i 1 -r 2000 ``` Note that this range will download the entire dataset. The script will ask you to confirm that you have 1.7Tb free at the download destination. ###### Downloading to a specific directory The script will default to the location of the dataset's `part` .zip files at `images/`. If you wish to move the download location, you should move these files as well or use a symbolic link. ```bash python download.py -i 1 -r 2000 -o /home/$USER/datahoarding/etc ``` Again, the script will automatically add the `/` between the directory and the file when it downloads. ###### Setting the files to unzip once they've been downloaded The script is set to unzip the files _after_ all files have downloaded as both can be lengthy processes in certain circumstances. ```bash python download.py -i 1 -r 2000 -z ``` #### Method 3. Use `metadata.parquet` (Text Only) If your task does not require images, then you can easily access all 2 million prompts and hyperparameters in the `metadata.parquet` table. ```python from urllib.request import urlretrieve import pandas as pd # Download the parquet table table_url = f'https://huggingface.co./datasets/poloclub/diffusiondb/resolve/main/metadata.parquet' urlretrieve(table_url, 'metadata.parquet') # Read the table using Pandas metadata_df = pd.read_parquet('metadata.parquet') ``` ## Dataset Creation ### Curation Rationale Recent diffusion models have gained immense popularity by enabling high-quality and controllable image generation based on text prompts written in natural language. Since the release of these models, people from different domains have quickly applied them to create award-winning artworks, synthetic radiology images, and even hyper-realistic videos. However, generating images with desired details is difficult, as it requires users to write proper prompts specifying the exact expected results. Developing such prompts requires trial and error, and can often feel random and unprincipled. Simon Willison analogizes writing prompts to wizards learning “magical spells”: users do not understand why some prompts work, but they will add these prompts to their “spell book.” For example, to generate highly-detailed images, it has become a common practice to add special keywords such as “trending on artstation” and “unreal engine” in the prompt. Prompt engineering has become a field of study in the context of text-to-text generation, where researchers systematically investigate how to construct prompts to effectively solve different down-stream tasks. As large text-to-image models are relatively new, there is a pressing need to understand how these models react to prompts, how to write effective prompts, and how to design tools to help users generate images. To help researchers tackle these critical challenges, we create DiffusionDB, the first large-scale prompt dataset with 14 million real prompt-image pairs. ### Source Data #### Initial Data Collection and Normalization We construct DiffusionDB by scraping user-generated images on the official Stable Diffusion Discord server. We choose Stable Diffusion because it is currently the only open-source large text-to-image generative model, and all generated images have a CC0 1.0 Universal Public Domain Dedication license that waives all copyright and allows uses for any purpose. We choose the official [Stable Diffusion Discord server](https://discord.gg/stablediffusion) because it is public, and it has strict rules against generating and sharing illegal, hateful, or NSFW (not suitable for work, such as sexual and violent content) images. The server also disallows users to write or share prompts with personal information. #### Who are the source language producers? The language producers are users of the official [Stable Diffusion Discord server](https://discord.gg/stablediffusion). ### Annotations The dataset does not contain any additional annotations. #### Annotation process [N/A] #### Who are the annotators? [N/A] ### Personal and Sensitive Information The authors removed the discord usernames from the dataset. We decide to anonymize the dataset because some prompts might include sensitive information: explicitly linking them to their creators can cause harm to creators. ## Considerations for Using the Data ### Social Impact of Dataset The purpose of this dataset is to help develop better understanding of large text-to-image generative models. The unprecedented scale and diversity of this human-actuated dataset provide exciting research opportunities in understanding the interplay between prompts and generative models, detecting deepfakes, and designing human-AI interaction tools to help users more easily use these models. It should note that we collect images and their prompts from the Stable Diffusion Discord server. The Discord server has rules against users generating or sharing harmful or NSFW (not suitable for work, such as sexual and violent content) images. The Stable Diffusion model used in the server also has an NSFW filter that blurs the generated images if it detects NSFW content. However, it is still possible that some users had generated harmful images that were not detected by the NSFW filter or removed by the server moderators. Therefore, DiffusionDB can potentially contain these images. To mitigate the potential harm, we provide a [Google Form](https://forms.gle/GbYaSpRNYqxCafMZ9) on the [DiffusionDB website](https://poloclub.github.io/diffusiondb/) where users can report harmful or inappropriate images and prompts. We will closely monitor this form and remove reported images and prompts from DiffusionDB. ### Discussion of Biases The 14 million images in DiffusionDB have diverse styles and categories. However, Discord can be a biased data source. Our images come from channels where early users could use a bot to use Stable Diffusion before release. As these users had started using Stable Diffusion before the model was public, we hypothesize that they are AI art enthusiasts and are likely to have experience with other text-to-image generative models. Therefore, the prompting style in DiffusionDB might not represent novice users. Similarly, the prompts in DiffusionDB might not generalize to domains that require specific knowledge, such as medical images. ### Other Known Limitations **Generalizability.** Previous research has shown a prompt that works well on one generative model might not give the optimal result when used in other models. Therefore, different models can need users to write different prompts. For example, many Stable Diffusion prompts use commas to separate keywords, while this pattern is less seen in prompts for DALL-E 2 or Midjourney. Thus, we caution researchers that some research findings from DiffusionDB might not be generalizable to other text-to-image generative models. ## Additional Information ### Dataset Curators DiffusionDB is created by [Jay Wang](https://zijie.wang), [Evan Montoya](https://www.linkedin.com/in/evan-montoya-b252391b4/), [David Munechika](https://www.linkedin.com/in/dmunechika/), [Alex Yang](https://alexanderyang.me), [Ben Hoover](https://www.bhoov.com), [Polo Chau](https://faculty.cc.gatech.edu/~dchau/). ### Licensing Information The DiffusionDB dataset is available under the [CC0 1.0 License](https://creativecommons.org/publicdomain/zero/1.0/). The Python code in this repository is available under the [MIT License](https://github.com/poloclub/diffusiondb/blob/main/LICENSE). ### Citation Information ```bibtex @article{wangDiffusionDBLargescalePrompt2022, title = {{{DiffusionDB}}: {{A}} Large-Scale Prompt Gallery Dataset for Text-to-Image Generative Models}, author = {Wang, Zijie J. and Montoya, Evan and Munechika, David and Yang, Haoyang and Hoover, Benjamin and Chau, Duen Horng}, year = {2022}, journal = {arXiv:2210.14896 [cs]}, url = {https://arxiv.org/abs/2210.14896} } ``` ### Contributions If you have any questions, feel free to [open an issue](https://github.com/poloclub/diffusiondb/issues/new) or contact [Jay Wang](https://zijie.wang).

GEM/wiki_lingua

GEM

--- annotations_creators: - none language_creators: - unknown language: - ar - cs - de - en - es - fr - hi - id - it - ja - ko - nl - pt - ru - th - tr - vi - zh license: - cc-by-nc-sa-3.0 multilinguality: - multilingual size_categories: - unknown source_datasets: - original task_categories: - summarization task_ids: [] pretty_name: wiki_lingua --- # Dataset Card for GEM/wiki_lingua ## Dataset Description - **Homepage:** None (See Repository) - **Repository:** https://github.com/esdurmus/Wikilingua - **Paper:** https://www.aclweb.org/anthology/2020.findings-emnlp.360/ - **Leaderboard:** N/A - **Point of Contact:** Faisal Ladhak, Esin Durmus ### Link to Main Data Card You can find the main data card on the [GEM Website](https://gem-benchmark.com/data_cards/wiki_lingua). ### Dataset Summary Placeholder You can load the dataset via: ``` import datasets data = datasets.load_dataset('GEM/wiki_lingua') ``` The data loader can be found [here](https://huggingface.co./datasets/GEM/wiki_lingua). #### website None (See Repository) #### paper https://www.aclweb.org/anthology/2020.findings-emnlp.360/ #### authors Faisal Ladhak (Columbia University), Esin Durmus (Stanford University), Claire Cardie (Cornell University), Kathleen McKeown (Columbia University) ## Dataset Overview ### Where to find the Data and its Documentation #### Webpage <!-- info: What is the webpage for the dataset (if it exists)? --> <!-- scope: telescope --> None (See Repository) #### Download <!-- info: What is the link to where the original dataset is hosted? --> <!-- scope: telescope --> https://github.com/esdurmus/Wikilingua #### Paper <!-- info: What is the link to the paper describing the dataset (open access preferred)? --> <!-- scope: telescope --> https://www.aclweb.org/anthology/2020.findings-emnlp.360/ #### BibTex <!-- info: Provide the BibTex-formatted reference for the dataset. Please use the correct published version (ACL anthology, etc.) instead of google scholar created Bibtex. --> <!-- scope: microscope --> @inproceedings{ladhak-etal-2020-wikilingua, title = "{W}iki{L}ingua: A New Benchmark Dataset for Cross-Lingual Abstractive Summarization", author = "Ladhak, Faisal and Durmus, Esin and Cardie, Claire and McKeown, Kathleen", booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2020", month = nov, year = "2020", address = "Online", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2020.findings-emnlp.360", doi = "10.18653/v1/2020.findings-emnlp.360", pages = "4034--4048", abstract = "We introduce WikiLingua, a large-scale, multilingual dataset for the evaluation of cross-lingual abstractive summarization systems. We extract article and summary pairs in 18 languages from WikiHow, a high quality, collaborative resource of how-to guides on a diverse set of topics written by human authors. We create gold-standard article-summary alignments across languages by aligning the images that are used to describe each how-to step in an article. As a set of baselines for further studies, we evaluate the performance of existing cross-lingual abstractive summarization methods on our dataset. We further propose a method for direct cross-lingual summarization (i.e., without requiring translation at inference time) by leveraging synthetic data and Neural Machine Translation as a pre-training step. Our method significantly outperforms the baseline approaches, while being more cost efficient during inference.", } #### Contact Name <!-- quick --> <!-- info: If known, provide the name of at least one person the reader can contact for questions about the dataset. --> <!-- scope: periscope --> Faisal Ladhak, Esin Durmus #### Contact Email <!-- info: If known, provide the email of at least one person the reader can contact for questions about the dataset. --> <!-- scope: periscope --> [email protected], [email protected] #### Has a Leaderboard? <!-- info: Does the dataset have an active leaderboard? --> <!-- scope: telescope --> no ### Languages and Intended Use #### Multilingual? <!-- quick --> <!-- info: Is the dataset multilingual? --> <!-- scope: telescope --> yes #### Covered Dialects <!-- info: What dialects are covered? Are there multiple dialects per language? --> <!-- scope: periscope --> Dataset does not have multiple dialects per language. #### Covered Languages <!-- quick --> <!-- info: What languages/dialects are covered in the dataset? --> <!-- scope: telescope --> `English`, `Spanish, Castilian`, `Portuguese`, `French`, `German`, `Russian`, `Italian`, `Indonesian`, `Dutch, Flemish`, `Arabic`, `Chinese`, `Vietnamese`, `Thai`, `Japanese`, `Korean`, `Hindi`, `Czech`, `Turkish` #### Whose Language? <!-- info: Whose language is in the dataset? --> <!-- scope: periscope --> No information about the user demographic is available. #### License <!-- quick --> <!-- info: What is the license of the dataset? --> <!-- scope: telescope --> cc-by-nc-sa-3.0: Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0) #### Intended Use <!-- info: What is the intended use of the dataset? --> <!-- scope: microscope --> The dataset was intended to serve as a large-scale, high-quality benchmark dataset for cross-lingual summarization. #### Primary Task <!-- info: What primary task does the dataset support? --> <!-- scope: telescope --> Summarization #### Communicative Goal <!-- quick --> <!-- info: Provide a short description of the communicative goal of a model trained for this task on this dataset. --> <!-- scope: periscope --> Produce a high quality summary for the given input article. ### Credit #### Curation Organization Type(s) <!-- info: In what kind of organization did the dataset curation happen? --> <!-- scope: telescope --> `academic` #### Curation Organization(s) <!-- info: Name the organization(s). --> <!-- scope: periscope --> Columbia University #### Dataset Creators <!-- info: Who created the original dataset? List the people involved in collecting the dataset and their affiliation(s). --> <!-- scope: microscope --> Faisal Ladhak (Columbia University), Esin Durmus (Stanford University), Claire Cardie (Cornell University), Kathleen McKeown (Columbia University) #### Who added the Dataset to GEM? <!-- info: Who contributed to the data card and adding the dataset to GEM? List the people+affiliations involved in creating this data card and who helped integrate this dataset into GEM. --> <!-- scope: microscope --> Jenny Chim (Queen Mary University of London), Faisal Ladhak (Columbia University) ### Dataset Structure #### Data Fields <!-- info: List and describe the fields present in the dataset. --> <!-- scope: telescope --> gem_id -- The id for the data instance. source_language -- The language of the source article. target_language -- The language of the target summary. source -- The source document. #### Example Instance <!-- info: Provide a JSON formatted example of a typical instance in the dataset. --> <!-- scope: periscope --> { "gem_id": "wikilingua_crosslingual-train-12345", "gem_parent_id": "wikilingua_crosslingual-train-12345", "source_language": "fr", "target_language": "de", "source": "Document in fr", "target": "Summary in de", } #### Data Splits <!-- info: Describe and name the splits in the dataset if there are more than one. --> <!-- scope: periscope --> The data is split into train/dev/test. In addition to the full test set, there's also a sampled version of the test set. #### Splitting Criteria <!-- info: Describe any criteria for splitting the data, if used. If there are differences between the splits (e.g., if the training annotations are machine-generated and the dev and test ones are created by humans, or if different numbers of annotators contributed to each example), describe them here. --> <!-- scope: microscope --> The data was split to ensure the same document would appear in the same split across languages so as to ensure there's no leakage into the test set. ## Dataset in GEM ### Rationale for Inclusion in GEM #### Why is the Dataset in GEM? <!-- info: What does this dataset contribute toward better generation evaluation and why is it part of GEM? --> <!-- scope: microscope --> This dataset provides a large-scale, high-quality resource for cross-lingual summarization in 18 languages, increasing the coverage of languages for the GEM summarization task. #### Similar Datasets <!-- info: Do other datasets for the high level task exist? --> <!-- scope: telescope --> yes #### Unique Language Coverage <!-- info: Does this dataset cover other languages than other datasets for the same task? --> <!-- scope: periscope --> yes #### Difference from other GEM datasets <!-- info: What else sets this dataset apart from other similar datasets in GEM? --> <!-- scope: microscope --> XSum covers English news articles, and MLSum covers news articles in German and Spanish. In contrast, this dataset has how-to articles in 18 languages, substantially increasing the languages covered. Moreover, it also provides a a different domain than the other two datasets. #### Ability that the Dataset measures <!-- info: What aspect of model ability can be measured with this dataset? --> <!-- scope: periscope --> The ability to generate quality summaries across multiple languages. ### GEM-Specific Curation #### Modificatied for GEM? <!-- info: Has the GEM version of the dataset been modified in any way (data, processing, splits) from the original curated data? --> <!-- scope: telescope --> yes #### GEM Modifications <!-- info: What changes have been made to he original dataset? --> <!-- scope: periscope --> `other` #### Modification Details <!-- info: For each of these changes, described them in more details and provided the intended purpose of the modification --> <!-- scope: microscope --> Previous version had separate data loaders for each language. In this version, we've created a single monolingual data loader, which contains monolingual data in each of the 18 languages. In addition, we've also created a single cross-lingual data loader across all the language pairs in the dataset. #### Additional Splits? <!-- info: Does GEM provide additional splits to the dataset? --> <!-- scope: telescope --> no ### Getting Started with the Task ## Previous Results ### Previous Results #### Measured Model Abilities <!-- info: What aspect of model ability can be measured with this dataset? --> <!-- scope: telescope --> Ability to summarize content across different languages. #### Metrics <!-- info: What metrics are typically used for this task? --> <!-- scope: periscope --> `ROUGE` #### Proposed Evaluation <!-- info: List and describe the purpose of the metrics and evaluation methodology (including human evaluation) that the dataset creators used when introducing this task. --> <!-- scope: microscope --> ROUGE is used to measure content selection by comparing word overlap with reference summaries. In addition, the authors of the dataset also used human evaluation to evaluate content selection and fluency of the systems. #### Previous results available? <!-- info: Are previous results available? --> <!-- scope: telescope --> no ## Dataset Curation ### Original Curation #### Original Curation Rationale <!-- info: Original curation rationale --> <!-- scope: telescope --> The dataset was created in order to enable new approaches for cross-lingual and multilingual summarization, which are currently understudied as well as open up inetersting new directions for research in summarization. E.g., exploration of multi-source cross-lingual architectures, i.e. models that can summarize from multiple source languages into a target language, building models that can summarize articles from any language to any other language for a given set of languages. #### Communicative Goal <!-- info: What was the communicative goal? --> <!-- scope: periscope --> Given an input article, produce a high quality summary of the article in the target language. #### Sourced from Different Sources <!-- info: Is the dataset aggregated from different data sources? --> <!-- scope: telescope --> no ### Language Data #### How was Language Data Obtained? <!-- info: How was the language data obtained? --> <!-- scope: telescope --> `Found` #### Where was it found? <!-- info: If found, where from? --> <!-- scope: telescope --> `Single website` #### Language Producers <!-- info: What further information do we have on the language producers? --> <!-- scope: microscope --> WikiHow, which is an online resource of how-to guides (written and reviewed by human authors) is used as the data source. #### Topics Covered <!-- info: Does the language in the dataset focus on specific topics? How would you describe them? --> <!-- scope: periscope --> The articles cover 19 broad categories including health, arts and entertainment, personal care and style, travel, education and communications, etc. The categories cover a broad set of genres and topics. #### Data Validation <!-- info: Was the text validated by a different worker or a data curator? --> <!-- scope: telescope --> not validated #### Was Data Filtered? <!-- info: Were text instances selected or filtered? --> <!-- scope: telescope --> not filtered ### Structured Annotations #### Additional Annotations? <!-- quick --> <!-- info: Does the dataset have additional annotations for each instance? --> <!-- scope: telescope --> none #### Annotation Service? <!-- info: Was an annotation service used? --> <!-- scope: telescope --> no ### Consent #### Any Consent Policy? <!-- info: Was there a consent policy involved when gathering the data? --> <!-- scope: telescope --> yes #### Consent Policy Details <!-- info: What was the consent policy? --> <!-- scope: microscope --> (1) Text Content. All text posted by Users to the Service is sub-licensed by wikiHow to other Users under a Creative Commons license as provided herein. The Creative Commons license allows such text content be used freely for non-commercial purposes, so long as it is used and attributed to the original author as specified under the terms of the license. Allowing free republication of our articles helps wikiHow achieve its mission by providing instruction on solving the problems of everyday life to more people for free. In order to support this goal, wikiHow hereby grants each User of the Service a license to all text content that Users contribute to the Service under the terms and conditions of a Creative Commons CC BY-NC-SA 3.0 License. Please be sure to read the terms of the license carefully. You continue to own all right, title, and interest in and to your User Content, and you are free to distribute it as you wish, whether for commercial or non-commercial purposes. #### Other Consented Downstream Use <!-- info: What other downstream uses of the data did the original data creators and the data curators consent to? --> <!-- scope: microscope --> The data is made freely available under the Creative Commons license, therefore there are no restrictions about downstream uses as long is it's for non-commercial purposes. ### Private Identifying Information (PII) #### Contains PII? <!-- quick --> <!-- info: Does the source language data likely contain Personal Identifying Information about the data creators or subjects? --> <!-- scope: telescope --> no PII #### Justification for no PII <!-- info: Provide a justification for selecting `no PII` above. --> <!-- scope: periscope --> Only the article text and summaries were collected. No user information was retained in the dataset. ### Maintenance #### Any Maintenance Plan? <!-- info: Does the original dataset have a maintenance plan? --> <!-- scope: telescope --> no ## Broader Social Context ### Previous Work on the Social Impact of the Dataset #### Usage of Models based on the Data <!-- info: Are you aware of cases where models trained on the task featured in this dataset ore related tasks have been used in automated systems? --> <!-- scope: telescope --> yes - other datasets featuring the same task ### Impact on Under-Served Communities #### Addresses needs of underserved Communities? <!-- info: Does this dataset address the needs of communities that are traditionally underserved in language technology, and particularly language generation technology? Communities may be underserved for exemple because their language, language variety, or social or geographical context is underepresented in NLP and NLG resources (datasets and models). --> <!-- scope: telescope --> no ### Discussion of Biases #### Any Documented Social Biases? <!-- info: Are there documented social biases in the dataset? Biases in this context are variations in the ways members of different social categories are represented that can have harmful downstream consequences for members of the more disadvantaged group. --> <!-- scope: telescope --> yes ## Considerations for Using the Data ### PII Risks and Liability ### Licenses #### Copyright Restrictions on the Dataset <!-- info: Based on your answers in the Intended Use part of the Data Overview Section, which of the following best describe the copyright and licensing status of the dataset? --> <!-- scope: periscope --> `non-commercial use only` #### Copyright Restrictions on the Language Data <!-- info: Based on your answers in the Language part of the Data Curation Section, which of the following best describe the copyright and licensing status of the underlying language data? --> <!-- scope: periscope --> `non-commercial use only` ### Known Technical Limitations

locuslab/TOFU

locuslab

--- annotations_creators: - machine-generated language: - en language_creators: - machine-generated license: mit multilinguality: - monolingual pretty_name: TOFU size_categories: - 1K<n<10K source_datasets: - original tags: - unlearning - question answering - TOFU - NLP - LLM task_categories: - question-answering task_ids: - closed-domain-qa configs: - config_name: full data_files: full.json default: true - config_name: forget01 data_files: forget01.json - config_name: forget05 data_files: forget05.json - config_name: forget10 data_files: forget10.json - config_name: retain90 data_files: retain90.json - config_name: retain95 data_files: retain95.json - config_name: retain99 data_files: retain99.json - config_name: world_facts data_files: world_facts.json - config_name: real_authors data_files: real_authors.json - config_name: forget01_perturbed data_files: forget01_perturbed.json - config_name: forget05_perturbed data_files: forget05_perturbed.json - config_name: forget10_perturbed data_files: forget10_perturbed.json - config_name: retain_perturbed data_files: retain_perturbed.json - config_name: world_facts_perturbed data_files: world_facts_perturbed.json - config_name: real_authors_perturbed data_files: real_authors_perturbed.json --- # TOFU: Task of Fictitious Unlearning 🍢 The TOFU dataset serves as a benchmark for evaluating unlearning performance of large language models on realistic tasks. The dataset comprises question-answer pairs based on autobiographies of 200 different authors that do not exist and are completely fictitiously generated by the GPT-4 model. The goal of the task is to unlearn a fine-tuned model on various fractions of the forget set. ## Quick Links - [**Website**](https://locuslab.github.io/tofu): The landing page for TOFU - [**arXiv Paper**](http://arxiv.org/abs/2401.06121): Detailed information about the TOFU dataset and its significance in unlearning tasks. - [**GitHub Repository**](https://github.com/locuslab/tofu): Access the source code, fine-tuning scripts, and additional resources for the TOFU dataset. - [**Dataset on Hugging Face**](https://huggingface.co./datasets/locuslab/TOFU): Direct link to download the TOFU dataset. - [**Leaderboard on Hugging Face Spaces**](https://huggingface.co./spaces/locuslab/tofu_leaderboard): Current rankings and submissions for the TOFU dataset challenges. - [**Summary on Twitter**](https://x.com/_akhaliq/status/1745643293839327268): A concise summary and key takeaways from the project. ## Applicability 🚀 The dataset is in QA format, making it ideal for use with popular chat models such as Llama2, Mistral, or Qwen. However, it also works for any other large language model. The corresponding code base is written for the Llama2 chat, and Phi-1.5 models, but can be easily adapted to other models. ## Loading the Dataset To load the dataset, use the following code: ```python from datasets import load_dataset dataset = load_dataset("locuslab/TOFU", "full") ``` ### Available forget sets are: - `forget01`: Forgetting 1% of the original dataset, all entries correspond to a single author. - `forget05`: Forgetting 5% of the original dataset, all entries correspond to a single author. - `forget10`: Forgetting 10% of the original dataset, all entries correspond to a single author. Retain sets corresponding to each forget set are also available, which can be used to train an Oracle model. ## Codebase The code for training the models and the availability of all fine-tuned models can be found at our [GitHub repository](https://github.com/locuslab/tofu). ## Citing Our Work If you find our codebase and dataset beneficial, please cite our work: ``` @misc{tofu2024, title={TOFU: A Task of Fictitious Unlearning for LLMs}, author={Pratyush Maini and Zhili Feng and Avi Schwarzschild and Zachary C. Lipton and J. Zico Kolter}, year={2024}, archivePrefix={arXiv}, primaryClass={cs.LG} } ```

mteb/nfcorpus

mteb

--- language: - en multilinguality: - monolingual task_categories: - text-retrieval source_datasets: - nfcorpus task_ids: - document-retrieval config_names: - corpus tags: - text-retrieval dataset_info: - config_name: default features: - name: query-id dtype: string - name: corpus-id dtype: string - name: score dtype: float64 splits: - name: train num_bytes: 3720942 num_examples: 110575 - name: dev num_bytes: 383427 num_examples: 11385 - name: test num_bytes: 415220 num_examples: 12334 - config_name: corpus features: - name: _id dtype: string - name: title dtype: string - name: text dtype: string splits: - name: corpus num_bytes: 5856698 num_examples: 3633 - config_name: queries features: - name: _id dtype: string - name: text dtype: string splits: - name: queries num_bytes: 128355 num_examples: 3237 configs: - config_name: default data_files: - split: train path: qrels/train.jsonl - split: dev path: qrels/dev.jsonl - split: test path: qrels/test.jsonl - config_name: corpus data_files: - split: corpus path: corpus.jsonl - config_name: queries data_files: - split: queries path: queries.jsonl ---

mlfoundations/MINT-1T-PDF-CC-2023-40

mlfoundations

--- license: cc-by-4.0 task_categories: - image-to-text - text-generation language: - en tags: - multimodal pretty_name: MINT-1T size_categories: - 100B<n<1T --- <h1 align="center"> 🍃 MINT-1T:<br>Scaling Open-Source Multimodal Data by 10x:<br> A Multimodal Dataset with One Trillion Tokens </h1> 🍃 MINT-1T is an open-source **M**ultimodal **INT**erleaved dataset with 1 trillion text tokens and 3.4 billion images, a 10x scale-up from existing open-source datasets. Additionally, we include previously untapped sources such as PDFs and ArXiv papers. 🍃 MINT-1T is designed to facilitate research in multimodal pretraining. 🍃 MINT-1T is created by a team from the University of Washington in collaboration with Salesforce Research, other academic institutions including Stanford University, University of Texas at Austin, and University of California Berkeley. You are currently viewing a subset of the PDF portion of 🍃 MINT-1T associated with CommonCrawl dump `CC-2023-40`. For other PDF, HTML, and ArXiv subsets, refer to the [🍃 MINT-1T collection](https://huggingface.co./collections/mlfoundations/mint-1t-6690216ca4d0df7e518dde1c).  ## Updates ### 9/19/24 We have removed roughly 10% of the PDF samples as there was a mismatch between the frames in the TIFF images and the document metadata. ### 8/8/24 We have become aware that the image hashes in the PDF subset of MINT-1T do not match the images in the documents. We want to emphasize that the images for each document are correct, and only the image hashes in the documents' metadata are mislabeled. ## Dataset Details ### Dataset Sources - **Repository**: https://github.com/mlfoundations/MINT-1T - **Paper:** https://arxiv.org/abs/2406.11271 - **Blog:** https://blog.salesforceairesearch.com/mint-1t/ ## Uses ### Direct Use <!-- This section describes suitable use cases for the dataset. --> 🍃 MINT-1T is designed to facilitate research in multimodal pretraining. The dataset can be used for training multimodal models that can reson about interleaved text and images sequences such as [Idefics2](https://huggingface.co./HuggingFaceM4/idefics2-8b), [XGen-MM](https://huggingface.co./Salesforce/xgen-mm-phi3-mini-instruct-r-v1), and [Chameleon](https://huggingface.co./facebook/chameleon-30b). ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the dataset will not work well for. --> 🍃 MINT-1T was built to make research into large multimodal models more accessible. Using the dataset to train models that ingest or generate personally identifying information (such as images of people’s faces and other sensitive content) as well as military applications are all inappropriate use cases of 🍃 MINT-1T. ## Dataset Creation ### Curation Rationale 🍃 MINT-1T was created to address a significant gap in the open-source domain by providing a large-scale multimodal interleaved dataset for pre-training large multimodal models. This dataset aims to be a valuable resource for the research community, facilitating open science in multimodal pretraining. ### Source Data The dataset is a comprehensive collection of multimodal documents from various sources: - HTML documents: Filtered from CommonCrawl WARC dumps spanning from 2017 to 2024 - PDF documents: Extracted from CommonCrawl WAT dumps covering 2023 to 2024 - ArXiv documents: A subset of papers from the ArXiv repository In total, 🍃 MINT-1T contains 1056.8 million documents, broken down as follows: - 1029.4 million HTML documents - 24.0 million PDF documents - 0.6 million ArXiv documents #### Data Collection and Processing The data collection and processing involved several steps: 1. Document Extraction: - HTML documents were parsed from CommonCrawl WARC files - PDF documents were extracted from CommonCrawl WAT files - ArXiv papers were directly sourced from ArXiv S3 buckets 2. Filtering Process: - Applied text quality filters to ensure content relevance and readability - Removed duplicate content at both paragraph and document levels - Filtered out undesirable content based on predefined criteria - Verified image availability and quality for HTML documents - Limited PDF size to 50MB and 50 pages to manage dataset size and quality 3. Image Processing: - Used NSFW image detection to remove pornographic or otherwise undesirable images - Removed images smaller than 150 pixels or larger than 20,000 pixels - Adjusted aspect ratio thresholds for HTML (2:1) and PDF (3:1) to preserve scientific figures 4. Text Processing: - Used fasttext for language identification, focusing on English content - Masked personally identifiable information such as email addresses and IP addresses - Applied paragraph and document-level deduplication using Bloom filters 5. PDF Specific Processing: - Used PyMuPDF for parsing PDFs and extracting reading order - Clustered text blocks based on columns and ordered from top left to bottom right 6. ArXiv Specific Processing: - Used TexSoup to parse LaTeX source code and interleave images with text - Cleaned up LaTeX code by removing imports, bibliography, tables, and citation tags Various open-source tools were utilized in this process, including fasttext, [PyMuPDF](https://github.com/pymupdf/PyMuPDF), and [DCLM](https://www.datacomp.ai/dclm/) and [bff](https://github.com/revbucket/bff) for deduplication and content filtering. #### Personal and Sensitive Information Despite sourcing from public web data, significant efforts were made to minimize the inclusion of personal and sensitive information: - Email addresses and IP addresses were masked to protect privacy - An NSFW image classifierto remove inappropriate visual content - URLs containing substrings associated with undesirable or sensitive content were filtered out However, users should be aware that as the data originates from the public web, it may still contain some sensitive or personal information. The dataset creators acknowledge this limitation and advise users to exercise caution and potentially apply additional filtering based on their specific use cases. ## Bias, Risks, and Limitations Several potential biases, risks, and limitations have been identified: 1. Data Bias: As the dataset is sourced from web crawls, it may inherit biases present in online content. 2. Content Risks: Despite extensive filtering, there's a possibility that some offensive, insensitive, or inappropriate content may remain in the dataset. 3. Image Availability: The dataset relies on external image URLs, which may become unavailable over time due to link rot, potentially affecting the dataset's long-term usability. 4. PDF Parsing Limitations: The current method for extracting reading order from PDFs may not always accurately capture the intended flow, especially for documents with complex layouts. 5. Potential Legal and Ethical Concerns: While efforts were made to respect robots.txt files and remove sensitive information, there may still be content that individuals did not explicitly consent to include. ### Recommendations Given these considerations, the following recommendations are provided: 1. Additional Filtering: Users are strongly encouraged to apply additional filtering based on their specific use case and ethical considerations. 2. Inappropriate Use Cases: The dataset is not recommended for applications involving the processing or generation of personally identifying information, nor for military applications. 3. Legal Compliance: Users should independently verify compliance with applicable laws before employing MINT-1T for commercial purposes. 4. Bias Awareness: Researchers and developers should be cognizant of potential biases in the dataset and consider their impact on model training and outputs. ## License We release 🍃 MINT-1T under a CC-BY-4.0 license, designating it primarily as a research artifact. While the dataset is freely available, users are responsible for ensuring its legal use in commercial settings. Users must independently verify compliance with applicable laws before employing MINT-1T for commercial purposes. ## Citation ``` @article{awadalla2024mint1t, title={MINT-1T: Scaling Open-Source Multimodal Data by 10x: A Multimodal Dataset with One Trillion Tokens}, author={Anas Awadalla and Le Xue and Oscar Lo and Manli Shu and Hannah Lee and Etash Kumar Guha and Matt Jordan and Sheng Shen and Mohamed Awadalla and Silvio Savarese and Caiming Xiong and Ran Xu and Yejin Choi and Ludwig Schmidt}, year={2024} } ```

bigscience/xP3mt

bigscience

--- annotations_creators: - expert-generated - crowdsourced language: - ak - ar - as - bm - bn - ca - code - en - es - eu - fon - fr - gu - hi - id - ig - ki - kn - lg - ln - ml - mr - ne - nso - ny - or - pa - pt - rn - rw - sn - st - sw - ta - te - tn - ts - tum - tw - ur - vi - wo - xh - yo - zh - zu programming_language: - C - C++ - C# - Go - Java - JavaScript - Lua - PHP - Python - Ruby - Rust - Scala - TypeScript license: - apache-2.0 multilinguality: - multilingual pretty_name: xP3 size_categories: - 100M<n<1B task_categories: - other --- # Dataset Card for xP3 ## Table of Contents - [Table of Contents](#table-of-contents) - [Dataset Description](#dataset-description) - [Dataset Summary](#dataset-summary) - [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards) - [Languages](#languages) - [Dataset Structure](#dataset-structure) - [Data Instances](#data-instances) - [Data Fields](#data-fields) - [Data Splits](#data-splits) - [Dataset Creation](#dataset-creation) - [Curation Rationale](#curation-rationale) - [Source Data](#source-data) - [Annotations](#annotations) - [Additional Information](#additional-information) - [Licensing Information](#licensing-information) - [Citation Information](#citation-information) - [Contributions](#contributions) ## Dataset Description - **Repository:** https://github.com/bigscience-workshop/xmtf - **Paper:** [Crosslingual Generalization through Multitask Finetuning](https://arxiv.org/abs/2211.01786) - **Point of Contact:** [Niklas Muennighoff](mailto:[email protected]) ### Dataset Summary > xP3 (Crosslingual Public Pool of Prompts) is a collection of prompts & datasets across 46 of languages & 16 NLP tasks. It is used for the training of BLOOMZ and mT0, multilingual language models capable of following human instructions in dozens of languages zero-shot. - **Creation:** The dataset can be recreated using instructions available [here](https://github.com/bigscience-workshop/xmtf#create-xp3). We provide this version to save processing time and ease reproducibility. - **Languages:** 46 (Can be extended by [recreating with more splits](https://github.com/bigscience-workshop/xmtf#create-xp3)) - **xP3 Dataset Family:** <table> <tr> <th>Name</th> <th>Explanation</th> <th>Example models</th> </tr> <tr> <td><a href=https://huggingface.co./datasets/Muennighoff/xP3x>xP3x</a></t> <td>Mixture of 17 tasks in 277 languages with English prompts</td> <td>WIP - Join us at Project Aya @<a href=https://cohere.for.ai/>C4AI</a> to help!</td> </tr> <tr> <td><a href=https://huggingface.co./datasets/bigscience/xP3>xP3</a></t> <td>Mixture of 13 training tasks in 46 languages with English prompts</td> <td><a href=https://huggingface.co./bigscience/bloomz>bloomz</a> & <a href=https://huggingface.co./bigscience/mt0-xxl>mt0-xxl</a></td> </tr> <tr> <td><a href=https://huggingface.co./datasets/bigscience/xP3mt>xP3mt</a></t> <td>Mixture of 13 training tasks in 46 languages with prompts in 20 languages (machine-translated from English)</td> <td><a href=https://huggingface.co./bigscience/bloomz-mt>bloomz-mt</a> & <a href=https://huggingface.co./bigscience/mt0-xxl-mt>mt0-xxl-mt</a></td> </tr> <tr> <td><a href=https://huggingface.co./datasets/bigscience/xP3all>xP3all</a></t> <td>xP3 + evaluation datasets adding an additional 3 tasks for a total of 16 tasks in 46 languages with English prompts</td> <td></td> </tr> <tr> <td><a href=https://huggingface.co./datasets/bigscience/xP3megds>xP3megds</a></t> <td><a href=https://github.com/bigscience-workshop/Megatron-DeepSpeed>Megatron-DeepSpeed</a> processed version of xP3</td> <td><a href=https://huggingface.co./bigscience/bloomz>bloomz</a></td> </tr> <tr> <td><a href=https://huggingface.co./datasets/Muennighoff/P3>P3</a></t> <td>Repreprocessed version of the English-only <a href=https://huggingface.co./datasets/bigscience/P3>P3</a> with 8 training tasks</td> <td><a href=https://huggingface.co./bigscience/bloomz-p3>bloomz-p3</a> & <a href=https://huggingface.co./bigscience/mt0-xxl-p3>mt0-xxl-p3</a></td> </tr> </table> ## Dataset Structure ### Data Instances An example of "train" looks as follows: ```json { "inputs": "Oración 1: Fue académico en literatura metafísica, teología y ciencias clásicas.\Oración 2: Fue académico en literatura metafísica, teología y ciencia clásica.\nPregunta: ¿La oración 1 parafrasea la oración 2? ¿Si o no?", "targets": "Sí" } ``` ### Data Fields The data fields are the same among all splits: - `inputs`: the natural language input fed to the model - `targets`: the natural language target that the model has to generate ### Data Splits The below table summarizes sizes per language (computed from the `merged_{lang}.jsonl` files). Due to languages like `tw` only being single sentence translation samples from Flores, their byte percentage is significantly lower than their sample percentage. We machine-translated prompts for monolingual datasets, thus languages with only crosslingual datasets (e.g. Translation) do not have non-English prompts. Languages without non-English prompts are equivalent to [xP3](https://huggingface.co./datasets/bigscience/xP3). |Language|Kilobytes|%|Samples|%|Non-English prompts| |--------|------:|-:|---:|-:|-:| |tw|106288|0.11|265071|0.33| | |bm|107056|0.11|265180|0.33| | |ak|108096|0.11|265071|0.33| | |ca|110608|0.11|271191|0.34| | |eu|113008|0.12|281199|0.35| | |fon|113072|0.12|265063|0.33| | |st|114080|0.12|265063|0.33| | |ki|115040|0.12|265180|0.33| | |tum|116032|0.12|265063|0.33| | |wo|122560|0.13|365063|0.46| | |ln|126304|0.13|365060|0.46| | |as|156256|0.16|265063|0.33| | |or|161472|0.17|265063|0.33| | |kn|165456|0.17|265063|0.33| | |ml|175040|0.18|265864|0.33| | |rn|192992|0.2|318189|0.4| | |nso|229712|0.24|915051|1.14| | |tn|235536|0.24|915054|1.14| | |lg|235936|0.24|915021|1.14| | |rw|249360|0.26|915043|1.14| | |ts|250256|0.26|915044|1.14| | |sn|252496|0.26|865056|1.08| | |xh|254672|0.26|915058|1.14| | |zu|263712|0.27|915061|1.14| | |ny|272128|0.28|915063|1.14| | |ig|325440|0.33|950097|1.19|✅| |yo|339664|0.35|913021|1.14|✅| |ne|398144|0.41|315754|0.39|✅| |pa|529632|0.55|339210|0.42|✅| |sw|561392|0.58|1114439|1.39|✅| |gu|566576|0.58|347499|0.43|✅| |mr|674000|0.69|417269|0.52|✅| |bn|854864|0.88|428725|0.54|✅| |ta|943440|0.97|410633|0.51|✅| |te|1384016|1.42|573354|0.72|✅| |ur|1944416|2.0|855756|1.07|✅| |vi|3113184|3.2|1667306|2.08|✅| |code|4330752|4.46|2707724|3.38| | |hi|4469712|4.6|1543441|1.93|✅| |id|4538768|4.67|2582272|3.22|✅| |zh|4604112|4.74|3571636|4.46|✅| |ar|4703968|4.84|2148970|2.68|✅| |fr|5558912|5.72|5055942|6.31|✅| |pt|6130016|6.31|3562772|4.45|✅| |es|7579424|7.8|5151349|6.43|✅| |en|39252528|40.4|32740750|40.87| | |total|97150128|100.0|80100816|100.0|✅| ## Dataset Creation ### Source Data #### Training datasets - Code Miscellaneous - [CodeComplex](https://huggingface.co./datasets/codeparrot/codecomplex) - [Docstring Corpus](https://huggingface.co./datasets/teven/code_docstring_corpus) - [GreatCode](https://huggingface.co./datasets/great_code) - [State Changes](https://huggingface.co./datasets/Fraser/python-state-changes) - Closed-book QA - [Hotpot QA](https://huggingface.co./datasets/hotpot_qa) - [Trivia QA](https://huggingface.co./datasets/trivia_qa) - [Web Questions](https://huggingface.co./datasets/web_questions) - [Wiki QA](https://huggingface.co./datasets/wiki_qa) - Extractive QA - [Adversarial QA](https://huggingface.co./datasets/adversarial_qa) - [CMRC2018](https://huggingface.co./datasets/cmrc2018) - [DRCD](https://huggingface.co./datasets/clue) - [DuoRC](https://huggingface.co./datasets/duorc) - [MLQA](https://huggingface.co./datasets/mlqa) - [Quoref](https://huggingface.co./datasets/quoref) - [ReCoRD](https://huggingface.co./datasets/super_glue) - [ROPES](https://huggingface.co./datasets/ropes) - [SQuAD v2](https://huggingface.co./datasets/squad_v2) - [xQuAD](https://huggingface.co./datasets/xquad) - TyDI QA - [Primary](https://huggingface.co./datasets/khalidalt/tydiqa-primary) - [Goldp](https://huggingface.co./datasets/khalidalt/tydiqa-goldp) - Multiple-Choice QA - [ARC](https://huggingface.co./datasets/ai2_arc) - [C3](https://huggingface.co./datasets/c3) - [CoS-E](https://huggingface.co./datasets/cos_e) - [Cosmos](https://huggingface.co./datasets/cosmos) - [DREAM](https://huggingface.co./datasets/dream) - [MultiRC](https://huggingface.co./datasets/super_glue) - [OpenBookQA](https://huggingface.co./datasets/openbookqa) - [PiQA](https://huggingface.co./datasets/piqa) - [QUAIL](https://huggingface.co./datasets/quail) - [QuaRel](https://huggingface.co./datasets/quarel) - [QuaRTz](https://huggingface.co./datasets/quartz) - [QASC](https://huggingface.co./datasets/qasc) - [RACE](https://huggingface.co./datasets/race) - [SciQ](https://huggingface.co./datasets/sciq) - [Social IQA](https://huggingface.co./datasets/social_i_qa) - [Wiki Hop](https://huggingface.co./datasets/wiki_hop) - [WiQA](https://huggingface.co./datasets/wiqa) - Paraphrase Identification - [MRPC](https://huggingface.co./datasets/super_glue) - [PAWS](https://huggingface.co./datasets/paws) - [PAWS-X](https://huggingface.co./datasets/paws-x) - [QQP](https://huggingface.co./datasets/qqp) - Program Synthesis - [APPS](https://huggingface.co./datasets/codeparrot/apps) - [CodeContests](https://huggingface.co./datasets/teven/code_contests) - [JupyterCodePairs](https://huggingface.co./datasets/codeparrot/github-jupyter-text-code-pairs) - [MBPP](https://huggingface.co./datasets/Muennighoff/mbpp) - [NeuralCodeSearch](https://huggingface.co./datasets/neural_code_search) - [XLCoST](https://huggingface.co./datasets/codeparrot/xlcost-text-to-code) - Structure-to-text - [Common Gen](https://huggingface.co./datasets/common_gen) - [Wiki Bio](https://huggingface.co./datasets/wiki_bio) - Sentiment - [Amazon](https://huggingface.co./datasets/amazon_polarity) - [App Reviews](https://huggingface.co./datasets/app_reviews) - [IMDB](https://huggingface.co./datasets/imdb) - [Rotten Tomatoes](https://huggingface.co./datasets/rotten_tomatoes) - [Yelp](https://huggingface.co./datasets/yelp_review_full) - Simplification - [BiSECT](https://huggingface.co./datasets/GEM/BiSECT) - Summarization - [CNN Daily Mail](https://huggingface.co./datasets/cnn_dailymail) - [Gigaword](https://huggingface.co./datasets/gigaword) - [MultiNews](https://huggingface.co./datasets/multi_news) - [SamSum](https://huggingface.co./datasets/samsum) - [Wiki-Lingua](https://huggingface.co./datasets/GEM/wiki_lingua) - [XLSum](https://huggingface.co./datasets/GEM/xlsum) - [XSum](https://huggingface.co./datasets/xsum) - Topic Classification - [AG News](https://huggingface.co./datasets/ag_news) - [DBPedia](https://huggingface.co./datasets/dbpedia_14) - [TNEWS](https://huggingface.co./datasets/clue) - [TREC](https://huggingface.co./datasets/trec) - [CSL](https://huggingface.co./datasets/clue) - Translation - [Flores-200](https://huggingface.co./datasets/Muennighoff/flores200) - [Tatoeba](https://huggingface.co./datasets/Helsinki-NLP/tatoeba_mt) - Word Sense disambiguation - [WiC](https://huggingface.co./datasets/super_glue) - [XL-WiC](https://huggingface.co./datasets/pasinit/xlwic) #### Evaluation datasets (included in [xP3all](https://huggingface.co./datasets/bigscience/xP3all) except for NLI & HumanEval) - Natural Language Inference (NLI) - [ANLI](https://huggingface.co./datasets/anli) - [CB](https://huggingface.co./datasets/super_glue) - [RTE](https://huggingface.co./datasets/super_glue) - [XNLI](https://huggingface.co./datasets/xnli) - Coreference Resolution - [Winogrande](https://huggingface.co./datasets/winogrande) - [XWinograd](https://huggingface.co./datasets/Muennighoff/xwinograd) - Program Synthesis - [HumanEval](https://huggingface.co./datasets/openai_humaneval) - Sentence Completion - [COPA](https://huggingface.co./datasets/super_glue) - [Story Cloze](https://huggingface.co./datasets/story_cloze) - [XCOPA](https://huggingface.co./datasets/xcopa) - [XStoryCloze](https://huggingface.co./datasets/Muennighoff/xstory_cloze) ## Additional Information ### Licensing Information The dataset is released under Apache 2.0. ### Citation Information ```bibtex @misc{muennighoff2022crosslingual, title={Crosslingual Generalization through Multitask Finetuning}, author={Niklas Muennighoff and Thomas Wang and Lintang Sutawika and Adam Roberts and Stella Biderman and Teven Le Scao and M Saiful Bari and Sheng Shen and Zheng-Xin Yong and Hailey Schoelkopf and Xiangru Tang and Dragomir Radev and Alham Fikri Aji and Khalid Almubarak and Samuel Albanie and Zaid Alyafeai and Albert Webson and Edward Raff and Colin Raffel}, year={2022}, eprint={2211.01786}, archivePrefix={arXiv}, primaryClass={cs.CL} } ``` ### Contributions Thanks to the contributors of [promptsource](https://github.com/bigscience-workshop/promptsource/graphs/contributors) for adding many prompts used in this dataset.

lmms-lab/POPE

lmms-lab

--- dataset_info: - config_name: Full features: - name: id dtype: string - name: question_id dtype: string - name: question dtype: string - name: answer dtype: string - name: image_source dtype: string - name: image dtype: image - name: category dtype: string splits: - name: adversarial num_bytes: 490408158.0 num_examples: 3000 - name: popular num_bytes: 490397000.0 num_examples: 3000 - name: random num_bytes: 490394976.0 num_examples: 3000 download_size: 255022914 dataset_size: 1471200134.0 - config_name: default features: - name: id dtype: string - name: question_id dtype: string - name: question dtype: string - name: answer dtype: string - name: image_source dtype: string - name: image dtype: image - name: category dtype: string splits: - name: test num_bytes: 1471200135.0 num_examples: 9000 download_size: 255022914 dataset_size: 1471200135.0 configs: - config_name: Full data_files: - split: adversarial path: Full/adversarial-* - split: popular path: Full/popular-* - split: random path: Full/random-* - config_name: default data_files: - split: test path: data/test-* --- <p align="center" width="100%"> <img src="https://i.postimg.cc/g0QRgMVv/WX20240228-113337-2x.png" width="100%" height="80%"> </p> # Large-scale Multi-modality Models Evaluation Suite > Accelerating the development of large-scale multi-modality models (LMMs) with `lmms-eval` 🏠 [Homepage](https://lmms-lab.github.io/) | 📚 [Documentation](docs/README.md) | 🤗 [Huggingface Datasets](https://huggingface.co./lmms-lab) # This Dataset This is a formatted version of [POPE](https://github.com/RUCAIBox/POPE). It is used in our `lmms-eval` pipeline to allow for one-click evaluations of large multi-modality models. ``` @article{li2023evaluating, title={Evaluating object hallucination in large vision-language models}, author={Li, Yifan and Du, Yifan and Zhou, Kun and Wang, Jinpeng and Zhao, Wayne Xin and Wen, Ji-Rong}, journal={arXiv preprint arXiv:2305.10355}, year={2023} } ```

jinzhuoran/RWKU

jinzhuoran

--- language: - en license: cc-by-4.0 pretty_name: RWKU size_categories: - 10K<n<100K task_categories: - text-generation - fill-mask - question-answering tags: - unlearning - knowledge unlearning - NLP - LLM configs: - config_name: forget_target data_files: - split: train path: - "All/intro.json" - config_name: forget_level1 data_files: - split: test path: - "All/forget_level1.json" - config_name: forget_level2 data_files: - split: test path: - "All/forget_level2.json" - config_name: forget_level3 data_files: - split: test path: - "All/forget_level3.json" - config_name: neighbor_level1 data_files: - split: test path: - "All/neighbor_level1.json" - config_name: neighbor_level2 data_files: - split: test path: - "All/neighbor_level2.json" - config_name: mia_forget data_files: - split: test path: - "All/forget_mia.json" - config_name: mia_retain data_files: - split: test path: - "All/retain_mia.json" - config_name: utility_general data_files: - split: test path: - "All/retain_mmlu.json" - config_name: utility_general data_files: - split: test path: - "All/retain_mmlu.json" - config_name: utility_reason data_files: - split: test path: - "All/retain_bbh.json" - config_name: utility_truthfulness data_files: - split: test path: - "All/truthful.json" - config_name: utility_factuality data_files: - split: test path: - "All/triviaqa.json" - config_name: utility_fluency data_files: - split: test path: - "All/fluency.json" - config_name: train_original_passage data_files: - split: train path: - "All/passage.json" - config_name: train_positive_llama3 data_files: - split: train path: - "All/positive.json" - config_name: train_negative_llama3 data_files: - split: train path: - "All/negative.json" - config_name: train_pair_llama3 data_files: - split: train path: - "All/pair.json" - config_name: train_refusal_llama3 data_files: - split: train path: - "All/reject.json" - config_name: train_positive_phi3 data_files: - split: train path: - "All/positive_phi.json" - config_name: train_negative_phi3 data_files: - split: train path: - "All/negative_phi.json" - config_name: train_pair_phi3 data_files: - split: train path: - "All/pair_phi.json" - config_name: train_refusal_phi3 data_files: - split: train path: - "All/reject_phi.json" --- # Dataset Card for Real-World Knowledge Unlearning Benchmark (RWKU) ## Table of Contents - [Table of Contents](#table-of-contents) - [Dataset Description](#dataset-description) - [Dataset Summary](#dataset-summary) - [Supported Tasks](#supported-tasks) - [Languages](#languages) - [Dataset Structure](#dataset-structure) - [Data Instances](#data-instances) - [Data Fields](#data-fields) - [Data Splits](#data-splits) - [Dataset Creation](#dataset-creation) - [Curation Rationale](#curation-rationale) - [Source Data](#source-data) - [Annotations](#annotations) - [Personal and Sensitive Information](#personal-and-sensitive-information) - [Considerations for Using the Data](#considerations-for-using-the-data) - [Social Impact of Dataset](#social-impact-of-dataset) - [Discussion of Biases](#discussion-of-biases) - [Other Known Limitations](#other-known-limitations) - [Additional Information](#additional-information) - [Dataset Curators](#dataset-curators) - [Licensing Information](#licensing-information) - [Citation Information](#citation-information) - [Contributions](#contributions) ## Dataset Description - **Homepage:** https://rwku-bench.github.io - **Repository:** https://github.com/jinzhuoran/RWKU - **Paper:** https://arxiv.org/abs/2406.10890 ### Dataset Summary **RWKU is a real-world knowledge unlearning benchmark specifically designed for large language models (LLMs).** This benchmark contains 200 real-world unlearning targets and 13,131 multi-level forget probes, including 3,268 fill-in-the-blank probes, 2,879 question-answer probes, and 6,984 adversarial-attack probes. RWKU is designed based on the following three key factors: 1. For the **task setting**, we consider a more practical and challenging setting, similar to _zero-shot knowledge unlearning_. We provide only the unlearning target and the original model, without offering any forget corpus or retain corpus. In this way, it avoids secondary information leakage caused by the forget corpus and is not affected by the distribution bias of the retain corpus. 2. For the **knowledge source**, we choose real-world famous people from Wikipedia as the unlearning targets and demonstrate that such popular knowledge is widely present in various LLMs through memorization quantification, making it more suitable for knowledge unlearning. Additionally, choosing entities as unlearning targets can well clearly define the unlearning boundaries. 3. For the **evaluation framework**, we carefully design the forget set and the retain set to evaluate the model's capabilities from multiple real-world applications. Regarding the forget set, we evaluate the **efficacy** of knowledge unlearning at both the knowledge memorization (fill-in-the-blank style) and knowledge manipulation (question-answer style) abilities. Specifically, we also evaluate these two abilities through **adversarial attacks** to induce forgotten knowledge in the model. We adopt four membership inference attack (MIA) methods for knowledge memorization on our collected MIA set. We meticulously designed nine types of adversarial-attack probes for knowledge manipulation, including prefix injection, affirmative suffix, role playing, reverse query, and others. Regarding the retain set, we design a neighbor set to test the impact of neighbor perturbation, specifically focusing on the **locality** of unlearning. In addition, we assess the **model utility** on various capabilities, including general ability, reasoning ability, truthfulness, factuality, and fluency. ### Supported Tasks Knowledge unlearning for LLMs. ### Languages English. ## Dataset Structure To evaluate the unlearning efficacy: ```python from datasets import load_dataset forget_level1 = load_dataset("jinzhuoran/RWKU", 'forget_level1') forget_level2 = load_dataset("jinzhuoran/RWKU", 'forget_level2') forget_level2 = load_dataset("jinzhuoran/RWKU", 'forget_level2') ``` To evaluate the locality: ```python from datasets import load_dataset neighbor_level1 = load_dataset("jinzhuoran/RWKU", 'neighbor_level1') neighbor_level2 = load_dataset("jinzhuoran/RWKU", 'neighbor_level2') ``` To evaluate the model utility: ```python from datasets import load_dataset utility_general = load_dataset("jinzhuoran/RWKU", 'utility_general') utility_reason = load_dataset("jinzhuoran/RWKU", 'utility_reason') utility_truthfulness = load_dataset("jinzhuoran/RWKU", 'utility_truthfulness') utility_factuality = load_dataset("jinzhuoran/RWKU", 'utility_factuality') utility_fluency = load_dataset("jinzhuoran/RWKU", 'utility_fluency') ``` To conduct membership inference attacks: ```python from datasets import load_dataset mia_forget = load_dataset("jinzhuoran/RWKU", 'mia_forget') mia_retain = load_dataset("jinzhuoran/RWKU", 'mia_retain') ``` To load the forget corpus: ```python from datasets import load_dataset train_original_passage = load_dataset("jinzhuoran/RWKU", 'train_original_passage') train_positive_llama3 = load_dataset("jinzhuoran/RWKU", 'train_positive_llama3') ``` ## Dataset Structure ### Data Instances [More Information Needed] ### Data Fields [More Information Needed] ### Data Splits [More Information Needed] ## Dataset Creation ### Curation Rationale [More Information Needed] ### Source Data #### Initial Data Collection and Normalization [More Information Needed] #### Who are the source language producers? [More Information Needed] ### Annotations #### Annotation process [More Information Needed] #### Who are the annotators? [More Information Needed] ### Personal and Sensitive Information [More Information Needed] ## Considerations for Using the Data ### Social Impact of Dataset [More Information Needed] ### Discussion of Biases [More Information Needed] ### Other Known Limitations [More Information Needed] ## Additional Information ### Dataset Curators [More Information Needed] ### Licensing Information [More Information Needed] ### Citing Our Work If you find our codebase and dataset beneficial, please cite our work: ```bibtex @misc{jin2024rwku, title={RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models}, author={Zhuoran Jin and Pengfei Cao and Chenhao Wang and Zhitao He and Hongbang Yuan and Jiachun Li and Yubo Chen and Kang Liu and Jun Zhao}, year={2024}, eprint={2406.10890}, archivePrefix={arXiv}, primaryClass={cs.CL} } ```

enzostvs/stable-diffusion-tpu-generations

enzostvs

--- license: mit configs: - config_name: default data_files: - split: train path: "images/*.png" ---

DL3DV/DL3DV-ALL-2K

DL3DV

--- tags: - 3D Vision - NeRF - 3D Gaussian - Dataset - Novel View Synthesis - Text to 3D - Image to 3D pretty_name: Dl3DV-Dataset size_categories: - n>1T --- # DL3DV-Dataset This repo has all the 2K frames with camera poses of DL3DV-10K Dataset. We are working hard to review all the dataset to avoid sensitive information. Thank you for your patience. # Download If you have enough space, you can use git to download a dataset from huggingface. See this [link](https://huggingface.co./docs/hub/en/datasets-downloading). [480P](https://huggingface.co./datasets/DL3DV/DL3DV-ALL-480P)/[960P](https://huggingface.co./datasets/DL3DV/DL3DV-ALL-960P) versions should satisfies most needs. If you do not have enough space, we further provide a [download script](https://github.com/DL3DV-10K/Dataset/blob/main/scripts/download.py) here to download a subset. The usage: ```Bash usage: download.py [-h] --odir ODIR --subset {1K,2K,3K,4K,5K,6K,7K,8K,9K,10K} --resolution {4K,2K,960P,480P} --file_type {images+poses,video,colmap_cache} [--hash HASH] [--clean_cache] optional arguments: -h, --help show this help message and exit --odir ODIR output directory --subset {1K,2K,3K,4K,5K,6K,7K,8K,9K,10K} The subset of the benchmark to download --resolution {4K,2K,960P,480P} The resolution to donwnload --file_type {images+poses,video,colmap_cache} The file type to download --hash HASH If set subset=hash, this is the hash code of the scene to download --clean_cache If set, will clean the huggingface cache to save space ``` Here are some examples: ```Bash # Make sure you have applied for the access. # Use this to download the download.py script wget https://raw.githubusercontent.com/DL3DV-10K/Dataset/main/scripts/download.py # Download 2K resolution images and poses, 0~1K subset, output to DL3DV-10K directory python download.py --odir DL3DV-10K --subset 1K --resolution 2K --file_type images+poses --clean_cache # Download 2K resolution images and poses, 1K~2K subset, output to DL3DV-10K directory python download.py --odir DL3DV-10K --subset 2K --resolution 2K --file_type images+poses --clean_cache ``` You can also download a specific scene with its hash. The scene-hash pair visualization can be found [here](https://htmlpreview.github.io/?https://github.com/DL3DV-10K/Dataset/blob/main/visualize/index.html). ```Bash python download.py --odir DL3DV-10K --subset 2K --resolution 2K --file_type images+poses --hash e2cedefea8a0ed2d0ffbd5bdc08acbe7e1f85c96f72f7b790e9dfe1c98963047 --clean_cache ``` # News - [x] DL3DV-1K, 2K, 3K, 4K - [ ] DL3DV-5K ~ 10K

rayliuca/WikidataLabels

rayliuca

--- license: cc0-1.0 dataset_info: - config_name: aa features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13986211 num_examples: 436895 download_size: 9821312 dataset_size: 13986211 - config_name: ab features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 5012532 num_examples: 159908 download_size: 3013706 dataset_size: 5012532 - config_name: abs features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4252728 num_examples: 143986 download_size: 2567450 dataset_size: 4252728 - config_name: ace features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 19105673 num_examples: 574712 download_size: 13573374 dataset_size: 19105673 - config_name: ady features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4444259 num_examples: 148627 download_size: 2705754 dataset_size: 4444259 - config_name: ady-cyrl features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4412556 num_examples: 147884 download_size: 2682170 dataset_size: 4412556 - config_name: aeb features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4305734 num_examples: 145198 download_size: 2606368 dataset_size: 4305734 - config_name: aeb-arab features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4467930 num_examples: 148796 download_size: 2722169 dataset_size: 4467930 - config_name: aeb-latn features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 12770359 num_examples: 404946 download_size: 8886489 dataset_size: 12770359 - config_name: af features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 58561042 num_examples: 1643153 download_size: 42539052 dataset_size: 58561042 - config_name: agq features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 1317 num_examples: 33 download_size: 2906 dataset_size: 1317 - config_name: ak features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 14198715 num_examples: 443037 download_size: 9991525 dataset_size: 14198715 - config_name: aln features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13811116 num_examples: 432089 download_size: 9673418 dataset_size: 13811116 - config_name: als features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 20691 num_examples: 543 download_size: 17540 dataset_size: 20691 - config_name: alt features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 108390 num_examples: 1814 download_size: 59046 dataset_size: 108390 - config_name: am features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 5231176 num_examples: 163038 download_size: 3187164 dataset_size: 5231176 - config_name: ami features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 21519 num_examples: 686 download_size: 16640 dataset_size: 21519 - config_name: an features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 240345072 num_examples: 5921087 download_size: 164895205 dataset_size: 240345072 - config_name: ang features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 14275715 num_examples: 443461 download_size: 10063758 dataset_size: 14275715 - config_name: anp features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 8558258 num_examples: 241612 download_size: 4381360 dataset_size: 8558258 - config_name: ar features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 291173732 num_examples: 5724064 download_size: 159369497 dataset_size: 291173732 - config_name: arc features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4473283 num_examples: 150006 download_size: 2722619 dataset_size: 4473283 - config_name: arn features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13879729 num_examples: 433912 download_size: 9715431 dataset_size: 13879729 - config_name: arq features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4346991 num_examples: 146004 download_size: 2636972 dataset_size: 4346991 - config_name: ary features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 5358568 num_examples: 171568 download_size: 3313402 dataset_size: 5358568 - config_name: arz features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 81806333 num_examples: 1669699 download_size: 49423508 dataset_size: 81806333 - config_name: as features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 21658610 num_examples: 450074 download_size: 9641626 dataset_size: 21658610 - config_name: ase features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4252943 num_examples: 143986 download_size: 2568106 dataset_size: 4252943 - config_name: ast features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 1385628786 num_examples: 20696237 download_size: 955908362 dataset_size: 1385628786 - config_name: atj features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 12996229 num_examples: 411639 download_size: 9057557 dataset_size: 12996229 - config_name: av features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4722934 num_examples: 153781 download_size: 2880103 dataset_size: 4722934 - config_name: avk features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13194485 num_examples: 414598 download_size: 9200917 dataset_size: 13194485 - config_name: awa features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 8599312 num_examples: 242320 download_size: 4411751 dataset_size: 8599312 - config_name: ay features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 14269432 num_examples: 443521 download_size: 10029939 dataset_size: 14269432 - config_name: az features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 21049248 num_examples: 516732 download_size: 14117527 dataset_size: 21049248 - config_name: azb features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 30781587 num_examples: 607562 download_size: 16028687 dataset_size: 30781587 - config_name: ba features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 11525351 num_examples: 261509 download_size: 6733777 dataset_size: 11525351 - config_name: ban features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13674052 num_examples: 426706 download_size: 9513747 dataset_size: 13674052 - config_name: ban-bali features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 50961 num_examples: 748 download_size: 25817 dataset_size: 50961 - config_name: bar features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 54783034 num_examples: 1566120 download_size: 40389830 dataset_size: 54783034 - config_name: bbc features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 12820895 num_examples: 406960 download_size: 8917054 dataset_size: 12820895 - config_name: bcc features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 8017228 num_examples: 241977 download_size: 4344579 dataset_size: 8017228 - config_name: be features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 30978832 num_examples: 564184 download_size: 17461174 dataset_size: 30978832 - config_name: be-tarask features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 18931909 num_examples: 374396 download_size: 10871239 dataset_size: 18931909 - config_name: bg features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 200628708 num_examples: 4383953 download_size: 137745533 dataset_size: 200628708 - config_name: bgn features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 7999280 num_examples: 241566 download_size: 4331249 dataset_size: 7999280 - config_name: bi features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 14040026 num_examples: 438382 download_size: 9867032 dataset_size: 14040026 - config_name: bjn features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 8375348 num_examples: 254558 download_size: 5722334 dataset_size: 8375348 - config_name: bm features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 18145787 num_examples: 549694 download_size: 13129193 dataset_size: 18145787 - config_name: bn features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 815803977 num_examples: 9767284 download_size: 261147329 dataset_size: 815803977 - config_name: bo features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 11671330 num_examples: 278307 download_size: 5669602 dataset_size: 11671330 - config_name: bpy features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 15497749 num_examples: 347458 download_size: 6991190 dataset_size: 15497749 - config_name: bqi features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 8017455 num_examples: 241984 download_size: 4345123 dataset_size: 8017455 - config_name: br features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 58304963 num_examples: 1653800 download_size: 42722031 dataset_size: 58304963 - config_name: brh features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 5328437 num_examples: 171504 download_size: 3376189 dataset_size: 5328437 - config_name: bs features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 30441466 num_examples: 858190 download_size: 21606575 dataset_size: 30441466 - config_name: btm features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4252525 num_examples: 143980 download_size: 2567218 dataset_size: 4252525 - config_name: bto features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 12841721 num_examples: 407470 download_size: 8934218 dataset_size: 12841721 - config_name: bug features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 7595464 num_examples: 235268 download_size: 5129941 dataset_size: 7595464 - config_name: bxr features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4713699 num_examples: 153707 download_size: 2869313 dataset_size: 4713699 - config_name: ca features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 408509932 num_examples: 9936886 download_size: 288474980 dataset_size: 408509932 - config_name: cbk-zam features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 14108232 num_examples: 440345 download_size: 9920793 dataset_size: 14108232 - config_name: cdo features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 6503254 num_examples: 201362 download_size: 4137841 dataset_size: 6503254 - config_name: ce features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 28093148 num_examples: 607767 download_size: 16367596 dataset_size: 28093148 - config_name: ceb features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 332947091 num_examples: 7769402 download_size: 219525737 dataset_size: 332947091 - config_name: ch features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13983906 num_examples: 436785 download_size: 9817385 dataset_size: 13983906 - config_name: cho features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13950786 num_examples: 435869 download_size: 9791296 dataset_size: 13950786 - config_name: chr features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 5386793 num_examples: 172855 download_size: 3419676 dataset_size: 5386793 - config_name: chy features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13994916 num_examples: 437007 download_size: 9830465 dataset_size: 13994916 - config_name: ckb features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 23343034 num_examples: 511183 download_size: 11459344 dataset_size: 23343034 - config_name: co features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 47080480 num_examples: 1346929 download_size: 34551346 dataset_size: 47080480 - config_name: cps features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 12849864 num_examples: 407695 download_size: 8941921 dataset_size: 12849864 - config_name: cr features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 5516556 num_examples: 176667 download_size: 3532952 dataset_size: 5516556 - config_name: crh features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 10864382 num_examples: 336709 download_size: 7542853 dataset_size: 10864382 - config_name: crh-cyrl features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4419064 num_examples: 148046 download_size: 2688683 dataset_size: 4419064 - config_name: crh-latn features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 14201429 num_examples: 442905 download_size: 9986290 dataset_size: 14201429 - config_name: cs features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 140189244 num_examples: 3384048 download_size: 97516751 dataset_size: 140189244 - config_name: csb features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 20177120 num_examples: 619275 download_size: 14528772 dataset_size: 20177120 - config_name: cv features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 8047221 num_examples: 215611 download_size: 4857718 dataset_size: 8047221 - config_name: cy features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 89241808 num_examples: 2244550 download_size: 62686006 dataset_size: 89241808 - config_name: da features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 130931077 num_examples: 3448894 download_size: 98202417 dataset_size: 130931077 - config_name: dag features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 2664957 num_examples: 78534 download_size: 2052615 dataset_size: 2664957 - config_name: de features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 765398522 num_examples: 17531361 download_size: 527642124 dataset_size: 765398522 - config_name: de-at features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 53043722 num_examples: 1515373 download_size: 38761571 dataset_size: 53043722 - config_name: de-ch features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 53480908 num_examples: 1528137 download_size: 39349412 dataset_size: 53480908 - config_name: de-formal features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4256391 num_examples: 144061 download_size: 2571862 dataset_size: 4256391 - config_name: din features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 12819746 num_examples: 406591 download_size: 8922303 dataset_size: 12819746 - config_name: diq features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 7570161 num_examples: 232674 download_size: 5057742 dataset_size: 7570161 - config_name: dsb features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 16135830 num_examples: 491423 download_size: 11412316 dataset_size: 16135830 - config_name: dtp features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13867373 num_examples: 433733 download_size: 9720699 dataset_size: 13867373 - config_name: dty features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 8839082 num_examples: 246026 download_size: 4551845 dataset_size: 8839082 - config_name: dua features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 2631 num_examples: 87 download_size: 3877 dataset_size: 2631 - config_name: dv features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 81396462 num_examples: 2103276 download_size: 45332104 dataset_size: 81396462 - config_name: dz features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 8590239 num_examples: 242196 download_size: 4406353 dataset_size: 8590239 - config_name: ee features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 14377017 num_examples: 447208 download_size: 10136064 dataset_size: 14377017 - config_name: egl features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13068224 num_examples: 413551 download_size: 9121776 dataset_size: 13068224 - config_name: el features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 32978562 num_examples: 592016 download_size: 19577876 dataset_size: 32978562 - config_name: eml features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 14768563 num_examples: 458847 download_size: 10453636 dataset_size: 14768563 - config_name: en features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 6327454281 num_examples: 81801560 download_size: 4224231068 dataset_size: 6327454281 - config_name: en-ca features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 73305274 num_examples: 1909970 download_size: 53060194 dataset_size: 73305274 - config_name: en-gb features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 115978412 num_examples: 2520405 download_size: 78924421 dataset_size: 115978412 - config_name: en-us features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 14815 num_examples: 332 download_size: 9953 dataset_size: 14815 - config_name: eo features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 256196064 num_examples: 6285304 download_size: 177219679 dataset_size: 256196064 - config_name: es features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 730214298 num_examples: 17233968 download_size: 514588069 dataset_size: 730214298 - config_name: es-419 features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4355180 num_examples: 146476 download_size: 2659218 dataset_size: 4355180 - config_name: es-formal features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4280933 num_examples: 144717 download_size: 2592085 dataset_size: 4280933 - config_name: et features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 65123623 num_examples: 1820762 download_size: 48197302 dataset_size: 65123623 - config_name: eu features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 290282374 num_examples: 7109758 download_size: 197889378 dataset_size: 290282374 - config_name: ext features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 223257222 num_examples: 5359047 download_size: 147078789 dataset_size: 223257222 - config_name: fa features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 123727757 num_examples: 2142642 download_size: 65952114 dataset_size: 123727757 - config_name: ff features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 14116652 num_examples: 440614 download_size: 9920388 dataset_size: 14116652 - config_name: fi features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 286539944 num_examples: 6905698 download_size: 209916638 dataset_size: 286539944 - config_name: fit features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 20217258 num_examples: 620391 download_size: 14566702 dataset_size: 20217258 - config_name: fj features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 14159041 num_examples: 441745 download_size: 9956108 dataset_size: 14159041 - config_name: fkv features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4328482 num_examples: 145988 download_size: 2619845 dataset_size: 4328482 - config_name: fo features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 24474476 num_examples: 731732 download_size: 17876981 dataset_size: 24474476 - config_name: fr features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 774128723 num_examples: 17908351 download_size: 534489308 dataset_size: 774128723 - config_name: frc features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 17896106 num_examples: 547258 download_size: 12953740 dataset_size: 17896106 - config_name: frp features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 40902510 num_examples: 1191134 download_size: 29778105 dataset_size: 40902510 - config_name: frr features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 16979214 num_examples: 515350 download_size: 12069637 dataset_size: 16979214 - config_name: fur features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 42077410 num_examples: 1221071 download_size: 30714082 dataset_size: 42077410 - config_name: ga features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 471527543 num_examples: 11524282 download_size: 320967189 dataset_size: 471527543 - config_name: gag features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 14149375 num_examples: 440732 download_size: 9940551 dataset_size: 14149375 - config_name: gan features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 31572161 num_examples: 905186 download_size: 18909564 dataset_size: 31572161 - config_name: gan-hans features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 31004794 num_examples: 889875 download_size: 18566811 dataset_size: 31004794 - config_name: gan-hant features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4374444 num_examples: 147098 download_size: 2657182 dataset_size: 4374444 - config_name: gcr features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4311409 num_examples: 145829 download_size: 2618211 dataset_size: 4311409 - config_name: gd features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 49316935 num_examples: 1429457 download_size: 36220978 dataset_size: 49316935 - config_name: gl features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 289484839 num_examples: 7052226 download_size: 197315151 dataset_size: 289484839 - config_name: glk features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 8327018 num_examples: 249115 download_size: 4538325 dataset_size: 8327018 - config_name: gn features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 14212974 num_examples: 442765 download_size: 10004863 dataset_size: 14212974 - config_name: gom features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4584575 num_examples: 150273 download_size: 2780570 dataset_size: 4584575 - config_name: gom-deva features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 8585678 num_examples: 242131 download_size: 4400578 dataset_size: 8585678 - config_name: gom-latn features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 12783006 num_examples: 405302 download_size: 8897342 dataset_size: 12783006 - config_name: gor features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 14667616 num_examples: 454512 download_size: 10319196 dataset_size: 14667616 - config_name: got features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 5432139 num_examples: 172951 download_size: 3435531 dataset_size: 5432139 - config_name: grc features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4494817 num_examples: 149631 download_size: 2746170 dataset_size: 4494817 - config_name: gu features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 23788894 num_examples: 486140 download_size: 10779200 dataset_size: 23788894 - config_name: guc features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 1419 num_examples: 38 download_size: 3054 dataset_size: 1419 - config_name: guw features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 118 num_examples: 4 download_size: 1864 dataset_size: 118 - config_name: gv features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 20683485 num_examples: 631005 download_size: 14894590 dataset_size: 20683485 - config_name: ha features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 14716168 num_examples: 455836 download_size: 10421790 dataset_size: 14716168 - config_name: hak features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 6128644 num_examples: 193036 download_size: 3991729 dataset_size: 6128644 - config_name: haw features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 14158084 num_examples: 441511 download_size: 9952975 dataset_size: 14158084 - config_name: he features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 43629050 num_examples: 884809 download_size: 27221301 dataset_size: 43629050 - config_name: hi features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 37237187 num_examples: 668964 download_size: 17804873 dataset_size: 37237187 - config_name: hif features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 14457954 num_examples: 449009 download_size: 10166264 dataset_size: 14457954 - config_name: hif-latn features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 14519845 num_examples: 454037 download_size: 10240704 dataset_size: 14519845 - config_name: hil features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 12928914 num_examples: 409962 download_size: 9009705 dataset_size: 12928914 - config_name: ho features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13950504 num_examples: 435857 download_size: 9790849 dataset_size: 13950504 - config_name: hr features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 61272623 num_examples: 1720527 download_size: 45307411 dataset_size: 61272623 - config_name: hrx features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 12869295 num_examples: 407823 download_size: 8964114 dataset_size: 12869295 - config_name: hsb features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 23720349 num_examples: 707100 download_size: 17145693 dataset_size: 23720349 - config_name: ht features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 16835529 num_examples: 509955 download_size: 11880404 dataset_size: 16835529 - config_name: hu features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 85054175 num_examples: 2200589 download_size: 64143342 dataset_size: 85054175 - config_name: hu-formal features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4252810 num_examples: 143986 download_size: 2567582 dataset_size: 4252810 - config_name: hy features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 39339286 num_examples: 773925 download_size: 22108994 dataset_size: 39339286 - config_name: hyw features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 5443608 num_examples: 166902 download_size: 3238370 dataset_size: 5443608 - config_name: hz features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13948574 num_examples: 435804 download_size: 9788697 dataset_size: 13948574 - config_name: ia features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 229143237 num_examples: 5616433 download_size: 155877454 dataset_size: 229143237 - config_name: id features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 95220928 num_examples: 2512331 download_size: 69525046 dataset_size: 95220928 - config_name: ie features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 225725262 num_examples: 5533032 download_size: 153371930 dataset_size: 225725262 - config_name: ig features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 20109388 num_examples: 617044 download_size: 14475407 dataset_size: 20109388 - config_name: ii features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4310418 num_examples: 145332 download_size: 2609723 dataset_size: 4310418 - config_name: ik features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13989609 num_examples: 436958 download_size: 9823174 dataset_size: 13989609 - config_name: ike-cans features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4352278 num_examples: 146355 download_size: 2645174 dataset_size: 4352278 - config_name: ike-latn features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13851135 num_examples: 432932 download_size: 9714057 dataset_size: 13851135 - config_name: ilo features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 15955483 num_examples: 480555 download_size: 11141942 dataset_size: 15955483 - config_name: inh features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4634360 num_examples: 152226 download_size: 2831580 dataset_size: 4634360 - config_name: io features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 233656822 num_examples: 5757440 download_size: 159720058 dataset_size: 233656822 - config_name: is features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 51679396 num_examples: 1483610 download_size: 37965494 dataset_size: 51679396 - config_name: it features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 536601426 num_examples: 12631487 download_size: 375025347 dataset_size: 536601426 - config_name: iu features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 5360588 num_examples: 172215 download_size: 3402239 dataset_size: 5360588 - config_name: ja features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 140641579 num_examples: 2917962 download_size: 92145329 dataset_size: 140641579 - config_name: jam features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 18849751 num_examples: 571777 download_size: 13684422 dataset_size: 18849751 - config_name: jbo features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 14301985 num_examples: 446512 download_size: 9994516 dataset_size: 14301985 - config_name: jv features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 27232302 num_examples: 794181 download_size: 19651565 dataset_size: 27232302 - config_name: ka features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 24073345 num_examples: 399546 download_size: 11679979 dataset_size: 24073345 - config_name: kaa features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 14082184 num_examples: 439411 download_size: 9902820 dataset_size: 14082184 - config_name: kab features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 18459676 num_examples: 557857 download_size: 13384218 dataset_size: 18459676 - config_name: kbd features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4594409 num_examples: 149733 download_size: 2759503 dataset_size: 4594409 - config_name: kbd-cyrl features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4417661 num_examples: 148017 download_size: 2687531 dataset_size: 4417661 - config_name: kbp features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 12873178 num_examples: 408039 download_size: 8965474 dataset_size: 12873178 - config_name: kea features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 12793700 num_examples: 405901 download_size: 8896866 dataset_size: 12793700 - config_name: kg features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 40949149 num_examples: 1193499 download_size: 29766747 dataset_size: 40949149 - config_name: khw features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4308653 num_examples: 145279 download_size: 2608581 dataset_size: 4308653 - config_name: ki features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 14056900 num_examples: 439015 download_size: 9875534 dataset_size: 14056900 - config_name: kj features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13881723 num_examples: 433861 download_size: 9733715 dataset_size: 13881723 - config_name: kjp features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 8504302 num_examples: 240339 download_size: 4341523 dataset_size: 8504302 - config_name: kk features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 19216115 num_examples: 428880 download_size: 11577682 dataset_size: 19216115 - config_name: kk-arab features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 7241749 num_examples: 211731 download_size: 4487032 dataset_size: 7241749 - config_name: kk-kz features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4937945 num_examples: 160027 download_size: 3062906 dataset_size: 4937945 - config_name: kk-latn features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 22197825 num_examples: 677162 download_size: 16072332 dataset_size: 22197825 - config_name: kk-tr features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 20060635 num_examples: 616521 download_size: 14438929 dataset_size: 20060635 - config_name: ko features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 60335212 num_examples: 1364440 download_size: 39186630 dataset_size: 60335212 - config_name: ko-kp features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4338717 num_examples: 146150 download_size: 2630925 dataset_size: 4338717 - config_name: koi features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4737590 num_examples: 155082 download_size: 2894674 dataset_size: 4737590 - config_name: kr features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13886057 num_examples: 433990 download_size: 9737602 dataset_size: 13886057 - config_name: krc features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4646136 num_examples: 151026 download_size: 2785454 dataset_size: 4646136 - config_name: kri features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 12798530 num_examples: 406032 download_size: 8902330 dataset_size: 12798530 - config_name: krj features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13850324 num_examples: 433444 download_size: 9703460 dataset_size: 13850324 - config_name: krl features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 12788020 num_examples: 405729 download_size: 8893337 dataset_size: 12788020 - config_name: ks features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4390604 num_examples: 147033 download_size: 2671069 dataset_size: 4390604 - config_name: ks-deva features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 8567518 num_examples: 241832 download_size: 4387687 dataset_size: 8567518 - config_name: ksh features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 20394712 num_examples: 624523 download_size: 14698860 dataset_size: 20394712 - config_name: ku features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 8037777 num_examples: 239515 download_size: 5306097 dataset_size: 8037777 - config_name: ku-arab features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4577826 num_examples: 151290 download_size: 2796159 dataset_size: 4577826 - config_name: ku-latn features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 14683841 num_examples: 458802 download_size: 10371977 dataset_size: 14683841 - config_name: kum features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4252739 num_examples: 143985 download_size: 2567503 dataset_size: 4252739 - config_name: kv features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4946978 num_examples: 158888 download_size: 2997865 dataset_size: 4946978 - config_name: kw features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 20245535 num_examples: 621432 download_size: 14581378 dataset_size: 20245535 - config_name: ky features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 8909613 num_examples: 235165 download_size: 5462115 dataset_size: 8909613 - config_name: la features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 299766395 num_examples: 7085082 download_size: 201477460 dataset_size: 299766395 - config_name: lad features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 20336417 num_examples: 622775 download_size: 14653199 dataset_size: 20336417 - config_name: lb features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 56473066 num_examples: 1601093 download_size: 41410732 dataset_size: 56473066 - config_name: lbe features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4501470 num_examples: 149898 download_size: 2744786 dataset_size: 4501470 - config_name: lez features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4890798 num_examples: 155936 download_size: 2959653 dataset_size: 4890798 - config_name: lfn features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 14709210 num_examples: 456719 download_size: 10408539 dataset_size: 14709210 - config_name: lg features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13979286 num_examples: 436009 download_size: 9802779 dataset_size: 13979286 - config_name: li features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 43476868 num_examples: 1253970 download_size: 31750932 dataset_size: 43476868 - config_name: lij features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 42327066 num_examples: 1227346 download_size: 30898971 dataset_size: 42327066 - config_name: liv features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 12781331 num_examples: 405236 download_size: 8895889 dataset_size: 12781331 - config_name: lki features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 8039166 num_examples: 242526 download_size: 4363703 dataset_size: 8039166 - config_name: lld features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 90305 num_examples: 2634 download_size: 69672 dataset_size: 90305 - config_name: lmo features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 18287638 num_examples: 545398 download_size: 13130119 dataset_size: 18287638 - config_name: ln features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 14123637 num_examples: 439731 download_size: 9915851 dataset_size: 14123637 - config_name: lo features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 9905189 num_examples: 271710 download_size: 5313218 dataset_size: 9905189 - config_name: loz features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13695602 num_examples: 428723 download_size: 9581113 dataset_size: 13695602 - config_name: lt features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 39902419 num_examples: 1096727 download_size: 29185765 dataset_size: 39902419 - config_name: ltg features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13884707 num_examples: 433453 download_size: 9736637 dataset_size: 13884707 - config_name: lus features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13695197 num_examples: 428712 download_size: 9580538 dataset_size: 13695197 - config_name: luz features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 8459036 num_examples: 253454 download_size: 4687414 dataset_size: 8459036 - config_name: lv features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 27242119 num_examples: 764753 download_size: 19676667 dataset_size: 27242119 - config_name: lzh features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 25067538 num_examples: 685152 download_size: 14998856 dataset_size: 25067538 - config_name: mdf features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4634268 num_examples: 152141 download_size: 2820744 dataset_size: 4634268 - config_name: mg features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 43863002 num_examples: 1271074 download_size: 32016826 dataset_size: 43863002 - config_name: mh features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13775721 num_examples: 431162 download_size: 9644397 dataset_size: 13775721 - config_name: mi features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 20857040 num_examples: 637118 download_size: 15060301 dataset_size: 20857040 - config_name: min features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 53044258 num_examples: 1464128 download_size: 38587450 dataset_size: 53044258 - config_name: mk features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 24087229 num_examples: 449241 download_size: 12217912 dataset_size: 24087229 - config_name: ml features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 189266798 num_examples: 2664923 download_size: 71344031 dataset_size: 189266798 - config_name: mn features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 9311543 num_examples: 219695 download_size: 5272784 dataset_size: 9311543 - config_name: mni features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 8696893 num_examples: 243616 download_size: 4470994 dataset_size: 8696893 - config_name: mnw features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 8861861 num_examples: 244906 download_size: 4517726 dataset_size: 8861861 - config_name: mo features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 5377009 num_examples: 172144 download_size: 3405661 dataset_size: 5377009 - config_name: mr features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 26855182 num_examples: 526220 download_size: 12358679 dataset_size: 26855182 - config_name: mrh features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 68 num_examples: 2 download_size: 1820 dataset_size: 68 - config_name: mrj features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 5007903 num_examples: 160889 download_size: 3073431 dataset_size: 5007903 - config_name: ms features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 64674328 num_examples: 1803714 download_size: 47165217 dataset_size: 64674328 - config_name: ms-arab features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 136496 num_examples: 2961 download_size: 92316 dataset_size: 136496 - config_name: mt features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 22632686 num_examples: 682867 download_size: 16352572 dataset_size: 22632686 - config_name: mus features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 14013416 num_examples: 437688 download_size: 9835239 dataset_size: 14013416 - config_name: mwl features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 14493299 num_examples: 448926 download_size: 10225888 dataset_size: 14493299 - config_name: my features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 16182182 num_examples: 345096 download_size: 7981905 dataset_size: 16182182 - config_name: mzn features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 17973941 num_examples: 447870 download_size: 9174617 dataset_size: 17973941 - config_name: na features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13992666 num_examples: 436956 download_size: 9823328 dataset_size: 13992666 - config_name: nah features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 14490294 num_examples: 449748 download_size: 10192501 dataset_size: 14490294 - config_name: nan-hani features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 191 num_examples: 6 download_size: 1925 dataset_size: 191 - config_name: nap features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 42362346 num_examples: 1229161 download_size: 30918265 dataset_size: 42362346 - config_name: nb features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 142554768 num_examples: 3688026 download_size: 105549981 dataset_size: 142554768 - config_name: nds features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 58766114 num_examples: 1666813 download_size: 43421948 dataset_size: 58766114 - config_name: nds-nl features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 44121756 num_examples: 1273149 download_size: 32201410 dataset_size: 44121756 - config_name: ne features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 11925386 num_examples: 295006 download_size: 6265232 dataset_size: 11925386 - config_name: new features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 16906308 num_examples: 350362 download_size: 7680329 dataset_size: 16906308 - config_name: ng features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13870754 num_examples: 433582 download_size: 9723795 dataset_size: 13870754 - config_name: nia features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 20649 num_examples: 515 download_size: 16535 dataset_size: 20649 - config_name: niu features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 12794247 num_examples: 405902 download_size: 8897260 dataset_size: 12794247 - config_name: nl features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 5016576732 num_examples: 61931959 download_size: 3380404239 dataset_size: 5016576732 - config_name: nn features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 99997815 num_examples: 2708994 download_size: 74736304 dataset_size: 99997815 - config_name: 'no' features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 2934 num_examples: 64 download_size: 4108 dataset_size: 2934 - config_name: nod features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4322068 num_examples: 145566 download_size: 2618106 dataset_size: 4322068 - config_name: nov features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 14150434 num_examples: 440903 download_size: 9947798 dataset_size: 14150434 - config_name: nqo features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 8094271 num_examples: 243184 download_size: 4398836 dataset_size: 8094271 - config_name: nrm features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 41330956 num_examples: 1203295 download_size: 30084065 dataset_size: 41330956 - config_name: nso features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 14178321 num_examples: 443205 download_size: 9959708 dataset_size: 14178321 - config_name: nv features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 15351770 num_examples: 455188 download_size: 10472240 dataset_size: 15351770 - config_name: ny features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13989813 num_examples: 436764 download_size: 9821588 dataset_size: 13989813 - config_name: nys features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13092059 num_examples: 413241 download_size: 9153100 dataset_size: 13092059 - config_name: oc features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 266612548 num_examples: 6569770 download_size: 180156462 dataset_size: 266612548 - config_name: olo features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13200388 num_examples: 416935 download_size: 9214968 dataset_size: 13200388 - config_name: om features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 5476389 num_examples: 175314 download_size: 3496637 dataset_size: 5476389 - config_name: or features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 22798709 num_examples: 470237 download_size: 10322832 dataset_size: 22798709 - config_name: os features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 5946062 num_examples: 177054 download_size: 3583703 dataset_size: 5946062 - config_name: ota features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 8015024 num_examples: 241903 download_size: 4343478 dataset_size: 8015024 - config_name: pa features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 20505754 num_examples: 481522 download_size: 10552147 dataset_size: 20505754 - config_name: pam features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 14527964 num_examples: 451253 download_size: 10242443 dataset_size: 14527964 - config_name: pap features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 54505401 num_examples: 1449881 download_size: 40415776 dataset_size: 54505401 - config_name: pcd features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 42132826 num_examples: 1221362 download_size: 30766812 dataset_size: 42132826 - config_name: pdc features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 14435256 num_examples: 448055 download_size: 10178322 dataset_size: 14435256 - config_name: pdt features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13994892 num_examples: 437200 download_size: 9819388 dataset_size: 13994892 - config_name: pfl features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 15461023 num_examples: 474198 download_size: 10893651 dataset_size: 15461023 - config_name: pi features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 8913354 num_examples: 250251 download_size: 4651392 dataset_size: 8913354 - config_name: pih features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13971081 num_examples: 436214 download_size: 9810653 dataset_size: 13971081 - config_name: pl features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 426030491 num_examples: 10025139 download_size: 295767506 dataset_size: 426030491 - config_name: pms features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 51268512 num_examples: 1477043 download_size: 37698831 dataset_size: 51268512 - config_name: pnb features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 16192682 num_examples: 409037 download_size: 9196626 dataset_size: 16192682 - config_name: pnt features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4439173 num_examples: 148336 download_size: 2703117 dataset_size: 4439173 - config_name: prg features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 17940420 num_examples: 544030 download_size: 12958482 dataset_size: 17940420 - config_name: ps features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 8860902 num_examples: 259186 download_size: 4916502 dataset_size: 8860902 - config_name: pt features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 491184040 num_examples: 11574568 download_size: 340831923 dataset_size: 491184040 - config_name: pt-br features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 318857431 num_examples: 7782980 download_size: 223442911 dataset_size: 318857431 - config_name: pwn features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 8500 num_examples: 269 download_size: 8738 dataset_size: 8500 - config_name: qu features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 15254702 num_examples: 468823 download_size: 10750388 dataset_size: 15254702 - config_name: quc features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 32 num_examples: 1 download_size: 1772 dataset_size: 32 - config_name: qug features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13798264 num_examples: 431733 download_size: 9661685 dataset_size: 13798264 - config_name: rgn features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 17001688 num_examples: 519871 download_size: 12258201 dataset_size: 17001688 - config_name: rif features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13792951 num_examples: 431588 download_size: 9657698 dataset_size: 13792951 - config_name: rm features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 44450577 num_examples: 1284908 download_size: 32519630 dataset_size: 44450577 - config_name: rmc features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 159 num_examples: 4 download_size: 1963 dataset_size: 159 - config_name: rmy features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 5610156 num_examples: 179191 download_size: 3608283 dataset_size: 5610156 - config_name: rn features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13935534 num_examples: 435271 download_size: 9779486 dataset_size: 13935534 - config_name: ro features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 247469452 num_examples: 5878366 download_size: 177525205 dataset_size: 247469452 - config_name: roa-tara features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 14425120 num_examples: 448972 download_size: 10152875 dataset_size: 14425120 - config_name: ru features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 405103215 num_examples: 7485811 download_size: 257215625 dataset_size: 405103215 - config_name: rue features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4953403 num_examples: 159530 download_size: 3037824 dataset_size: 4953403 - config_name: rup features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 14459686 num_examples: 450345 download_size: 10198398 dataset_size: 14459686 - config_name: ruq-cyrl features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4434290 num_examples: 148404 download_size: 2700920 dataset_size: 4434290 - config_name: ruq-latn features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13783683 num_examples: 430978 download_size: 9656941 dataset_size: 13783683 - config_name: rw features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 14090196 num_examples: 439172 download_size: 9901257 dataset_size: 14090196 - config_name: rwr features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 8568706 num_examples: 241841 download_size: 4388475 dataset_size: 8568706 - config_name: ryu features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 2852 num_examples: 82 download_size: 4237 dataset_size: 2852 - config_name: sa features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 21404327 num_examples: 455674 download_size: 9692464 dataset_size: 21404327 - config_name: sat features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 10810040 num_examples: 284911 download_size: 5750917 dataset_size: 10810040 - config_name: sc features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 47195572 num_examples: 1348137 download_size: 34521764 dataset_size: 47195572 - config_name: scn features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 43458983 num_examples: 1259067 download_size: 31775157 dataset_size: 43458983 - config_name: sco features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 56960413 num_examples: 1611092 download_size: 41724559 dataset_size: 56960413 - config_name: sd features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 14257513 num_examples: 363318 download_size: 7844047 dataset_size: 14257513 - config_name: sdc features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13975497 num_examples: 436913 download_size: 9800517 dataset_size: 13975497 - config_name: se features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 23962268 num_examples: 711439 download_size: 17409387 dataset_size: 23962268 - config_name: sei features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13827581 num_examples: 432520 download_size: 9684192 dataset_size: 13827581 - config_name: sg features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13913524 num_examples: 434751 download_size: 9761739 dataset_size: 13913524 - config_name: sh features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 30173635 num_examples: 746207 download_size: 20133594 dataset_size: 30173635 - config_name: shi-latn features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13783218 num_examples: 430968 download_size: 9656828 dataset_size: 13783218 - config_name: shi-tfng features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4308577 num_examples: 145279 download_size: 2608525 dataset_size: 4308577 - config_name: shn features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 10139002 num_examples: 260808 download_size: 4952168 dataset_size: 10139002 - config_name: shy-latn features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4255322 num_examples: 144058 download_size: 2570625 dataset_size: 4255322 - config_name: si features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 7405400 num_examples: 189718 download_size: 4270591 dataset_size: 7405400 - config_name: sjd features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4300688 num_examples: 145047 download_size: 2604357 dataset_size: 4300688 - config_name: sje features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 20970223 num_examples: 637639 download_size: 15120381 dataset_size: 20970223 - config_name: sju features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4315103 num_examples: 145655 download_size: 2620763 dataset_size: 4315103 - config_name: sk features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 75586366 num_examples: 2050873 download_size: 54951330 dataset_size: 75586366 - config_name: skr features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4274062 num_examples: 144443 download_size: 2585286 dataset_size: 4274062 - config_name: sl features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 157883240 num_examples: 4112048 download_size: 118047353 dataset_size: 157883240 - config_name: sli features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13909208 num_examples: 434986 download_size: 9745964 dataset_size: 13909208 - config_name: sm features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13984823 num_examples: 436830 download_size: 9817472 dataset_size: 13984823 - config_name: sma features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 20653595 num_examples: 630437 download_size: 14902319 dataset_size: 20653595 - config_name: smj features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 19640206 num_examples: 604326 download_size: 14133964 dataset_size: 19640206 - config_name: smn features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 10902411 num_examples: 337543 download_size: 7576850 dataset_size: 10902411 - config_name: sms features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4462345 num_examples: 149355 download_size: 2741038 dataset_size: 4462345 - config_name: sn features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 20116601 num_examples: 618231 download_size: 14463728 dataset_size: 20116601 - config_name: sq features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 304708913 num_examples: 7311820 download_size: 225592169 dataset_size: 304708913 - config_name: sr features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 52787253 num_examples: 1018361 download_size: 31364006 dataset_size: 52787253 - config_name: sr-ec features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 9237541 num_examples: 248556 download_size: 5875548 dataset_size: 9237541 - config_name: sr-el features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 48848162 num_examples: 1418824 download_size: 35859120 dataset_size: 48848162 - config_name: srq features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 12796525 num_examples: 405957 download_size: 8899493 dataset_size: 12796525 - config_name: ss features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13823630 num_examples: 432423 download_size: 9682165 dataset_size: 13823630 - config_name: st features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13938937 num_examples: 435419 download_size: 9785161 dataset_size: 13938937 - config_name: stq features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 14484394 num_examples: 449885 download_size: 10228446 dataset_size: 14484394 - config_name: su features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 20025826 num_examples: 583096 download_size: 14042822 dataset_size: 20025826 - config_name: sv features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 339074900 num_examples: 8115455 download_size: 236022796 dataset_size: 339074900 - config_name: sw features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 50612064 num_examples: 1465385 download_size: 37096369 dataset_size: 50612064 - config_name: szl features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 16772062 num_examples: 500107 download_size: 11868254 dataset_size: 16772062 - config_name: szy features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4332021 num_examples: 146136 download_size: 2633271 dataset_size: 4332021 - config_name: ta features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 31251824 num_examples: 546558 download_size: 15157673 dataset_size: 31251824 - config_name: tay features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4345269 num_examples: 146938 download_size: 2632535 dataset_size: 4345269 - config_name: tcy features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 8723594 num_examples: 244350 download_size: 4487471 dataset_size: 8723594 - config_name: te features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 27587665 num_examples: 569615 download_size: 13669398 dataset_size: 27587665 - config_name: tet features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 15092299 num_examples: 466244 download_size: 10702917 dataset_size: 15092299 - config_name: tg features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 12643125 num_examples: 304625 download_size: 7622522 dataset_size: 12643125 - config_name: tg-cyrl features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4504034 num_examples: 149533 download_size: 2755000 dataset_size: 4504034 - config_name: tg-latn features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 19845835 num_examples: 610020 download_size: 14264492 dataset_size: 19845835 - config_name: th features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 32693750 num_examples: 537447 download_size: 15849247 dataset_size: 32693750 - config_name: ti features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4366995 num_examples: 146479 download_size: 2648869 dataset_size: 4366995 - config_name: tk features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 5797050 num_examples: 184302 download_size: 3728802 dataset_size: 5797050 - config_name: tl features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13661554 num_examples: 387377 download_size: 9456413 dataset_size: 13661554 - config_name: tly features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4309748 num_examples: 145312 download_size: 2609307 dataset_size: 4309748 - config_name: tly-cyrl features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 35 num_examples: 1 download_size: 1793 dataset_size: 35 - config_name: tn features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13936132 num_examples: 435219 download_size: 9780279 dataset_size: 13936132 - config_name: to features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13980327 num_examples: 436460 download_size: 9810650 dataset_size: 13980327 - config_name: tpi features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 14169019 num_examples: 442133 download_size: 9961827 dataset_size: 14169019 - config_name: tr features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 72134544 num_examples: 1770267 download_size: 51032484 dataset_size: 72134544 - config_name: tru features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 5322844 num_examples: 171327 download_size: 3371105 dataset_size: 5322844 - config_name: trv features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 94285 num_examples: 3109 download_size: 65138 dataset_size: 94285 - config_name: ts features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13943481 num_examples: 435408 download_size: 9783789 dataset_size: 13943481 - config_name: tt features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 24182976 num_examples: 548502 download_size: 14868166 dataset_size: 24182976 - config_name: tt-cyrl features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4943914 num_examples: 158198 download_size: 3048932 dataset_size: 4943914 - config_name: tt-latn features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13842972 num_examples: 432513 download_size: 9702714 dataset_size: 13842972 - config_name: tum features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13924159 num_examples: 435110 download_size: 9770501 dataset_size: 13924159 - config_name: tw features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13830508 num_examples: 432669 download_size: 9688164 dataset_size: 13830508 - config_name: ty features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 16816401 num_examples: 507332 download_size: 12098154 dataset_size: 16816401 - config_name: tyv features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4583082 num_examples: 149929 download_size: 2779632 dataset_size: 4583082 - config_name: tzm features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4253588 num_examples: 144002 download_size: 2569067 dataset_size: 4253588 - config_name: udm features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4854947 num_examples: 156300 download_size: 2958444 dataset_size: 4854947 - config_name: ug-arab features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4316690 num_examples: 145443 download_size: 2614962 dataset_size: 4316690 - config_name: ug-latn features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13786474 num_examples: 431056 download_size: 9659723 dataset_size: 13786474 - config_name: uk features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 251058352 num_examples: 5108733 download_size: 168140976 dataset_size: 251058352 - config_name: ur features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 57063750 num_examples: 987011 download_size: 28328459 dataset_size: 57063750 - config_name: uz features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 11731793 num_examples: 344615 download_size: 8102734 dataset_size: 11731793 - config_name: uz-cyrl features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4252574 num_examples: 143981 download_size: 2567325 dataset_size: 4252574 - config_name: ve features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 13932174 num_examples: 435216 download_size: 9777266 dataset_size: 13932174 - config_name: vec features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 52081230 num_examples: 1466867 download_size: 37307805 dataset_size: 52081230 - config_name: vep features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 6174898 num_examples: 192298 download_size: 3994582 dataset_size: 6174898 - config_name: vi features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 246835524 num_examples: 5743737 download_size: 172949263 dataset_size: 246835524 - config_name: vls features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 42789297 num_examples: 1239359 download_size: 31228294 dataset_size: 42789297 - config_name: vmf features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 18352990 num_examples: 555205 download_size: 13289296 dataset_size: 18352990 - config_name: vo features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 228352533 num_examples: 5610875 download_size: 155496988 dataset_size: 228352533 - config_name: vot features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 5406190 num_examples: 173486 download_size: 3439433 dataset_size: 5406190 - config_name: wa features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 49235347 num_examples: 1426584 download_size: 36167816 dataset_size: 49235347 - config_name: war features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 190306474 num_examples: 4449062 download_size: 133786270 dataset_size: 190306474 - config_name: wls features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4033 num_examples: 104 download_size: 5150 dataset_size: 4033 - config_name: wo features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 40961626 num_examples: 1193626 download_size: 29778666 dataset_size: 40961626 - config_name: wuu features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 40570130 num_examples: 1127741 download_size: 24209117 dataset_size: 40570130 - config_name: wya features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 28 num_examples: 1 download_size: 1740 dataset_size: 28 - config_name: xal features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4475344 num_examples: 149984 download_size: 2722459 dataset_size: 4475344 - config_name: xh features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 20036194 num_examples: 615514 download_size: 14405310 dataset_size: 20036194 - config_name: xmf features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 5943645 num_examples: 169507 download_size: 3418593 dataset_size: 5943645 - config_name: xsy features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4262789 num_examples: 144305 download_size: 2573349 dataset_size: 4262789 - config_name: yav features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4070 num_examples: 102 download_size: 4718 dataset_size: 4070 - config_name: yi features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 5495313 num_examples: 170277 download_size: 3373820 dataset_size: 5495313 - config_name: yo features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 25424749 num_examples: 724345 download_size: 18086773 dataset_size: 25424749 - config_name: za features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 15159230 num_examples: 365892 download_size: 7774767 dataset_size: 15159230 - config_name: zea features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 14538518 num_examples: 451577 download_size: 10262897 dataset_size: 14538518 - config_name: zgh features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 4253917 num_examples: 144006 download_size: 2569373 dataset_size: 4253917 - config_name: zh features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 264353677 num_examples: 5424320 download_size: 174420118 dataset_size: 264353677 - config_name: zh-cn features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 42868611 num_examples: 1158755 download_size: 27243799 dataset_size: 42868611 - config_name: zh-hans features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 57233156 num_examples: 1483225 download_size: 36583522 dataset_size: 57233156 - config_name: zh-hant features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 53502814 num_examples: 1356560 download_size: 36755083 dataset_size: 53502814 - config_name: zh-hk features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 15325323 num_examples: 408391 download_size: 10455809 dataset_size: 15325323 - config_name: zh-mo features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 6568267 num_examples: 180950 download_size: 3547260 dataset_size: 6568267 - config_name: zh-my features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 32637498 num_examples: 916876 download_size: 19289581 dataset_size: 32637498 - config_name: zh-sg features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 35325327 num_examples: 979652 download_size: 21150070 dataset_size: 35325327 - config_name: zh-tw features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 17500668 num_examples: 443057 download_size: 11121104 dataset_size: 17500668 - config_name: zh-yue features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 1352 num_examples: 30 download_size: 2963 dataset_size: 1352 - config_name: zu features: - name: wikidata_id dtype: string - name: lastrevid dtype: int64 - name: label dtype: string splits: - name: label num_bytes: 47349379 num_examples: 1380550 download_size: 34649660 dataset_size: 47349379 configs: - config_name: aa data_files: - split: label path: aa/label-* - config_name: ab data_files: - split: label path: ab/label-* - config_name: abs data_files: - split: label path: abs/label-* - config_name: ace data_files: - split: label path: ace/label-* - config_name: ady data_files: - split: label path: ady/label-* - config_name: ady-cyrl data_files: - split: label path: ady-cyrl/label-* - config_name: aeb data_files: - split: label path: aeb/label-* - config_name: aeb-arab data_files: - split: label path: aeb-arab/label-* - config_name: aeb-latn data_files: - split: label path: aeb-latn/label-* - config_name: af data_files: - split: label path: af/label-* - config_name: agq data_files: - split: label path: agq/label-* - config_name: ak data_files: - split: label path: ak/label-* - config_name: aln data_files: - split: label path: aln/label-* - config_name: als data_files: - split: label path: als/label-* - config_name: alt data_files: - split: label path: alt/label-* - config_name: am data_files: - split: label path: am/label-* - config_name: ami data_files: - split: label path: ami/label-* - config_name: an data_files: - split: label path: an/label-* - config_name: ang data_files: - split: label path: ang/label-* - config_name: anp data_files: - split: label path: anp/label-* - config_name: ar data_files: - split: label path: ar/label-* - config_name: arc data_files: - split: label path: arc/label-* - config_name: arn data_files: - split: label path: arn/label-* - config_name: arq data_files: - split: label path: arq/label-* - config_name: ary data_files: - split: label path: ary/label-* - config_name: arz data_files: - split: label path: arz/label-* - config_name: as data_files: - split: label path: as/label-* - config_name: ase data_files: - split: label path: ase/label-* - config_name: ast data_files: - split: label path: ast/label-* - config_name: atj data_files: - split: label path: atj/label-* - config_name: av data_files: - split: label path: av/label-* - config_name: avk data_files: - split: label path: avk/label-* - config_name: awa data_files: - split: label path: awa/label-* - config_name: ay data_files: - split: label path: ay/label-* - config_name: az data_files: - split: label path: az/label-* - config_name: azb data_files: - split: label path: azb/label-* - config_name: ba data_files: - split: label path: ba/label-* - config_name: ban data_files: - split: label path: ban/label-* - config_name: ban-bali data_files: - split: label path: ban-bali/label-* - config_name: bar data_files: - split: label path: bar/label-* - config_name: bbc data_files: - split: label path: bbc/label-* - config_name: bcc data_files: - split: label path: bcc/label-* - config_name: be data_files: - split: label path: be/label-* - config_name: be-tarask data_files: - split: label path: be-tarask/label-* - config_name: bg data_files: - split: label path: bg/label-* - config_name: bgn data_files: - split: label path: bgn/label-* - config_name: bi data_files: - split: label path: bi/label-* - config_name: bjn data_files: - split: label path: bjn/label-* - config_name: bm data_files: - split: label path: bm/label-* - config_name: bn data_files: - split: label path: bn/label-* - config_name: bo data_files: - split: label path: bo/label-* - config_name: bpy data_files: - split: label path: bpy/label-* - config_name: bqi data_files: - split: label path: bqi/label-* - config_name: br data_files: - split: label path: br/label-* - config_name: brh data_files: - split: label path: brh/label-* - config_name: bs data_files: - split: label path: bs/label-* - config_name: btm data_files: - split: label path: btm/label-* - config_name: bto data_files: - split: label path: bto/label-* - config_name: bug data_files: - split: label path: bug/label-* - config_name: bxr data_files: - split: label path: bxr/label-* - config_name: ca data_files: - split: label path: ca/label-* - config_name: cbk-zam data_files: - split: label path: cbk-zam/label-* - config_name: cdo data_files: - split: label path: cdo/label-* - config_name: ce data_files: - split: label path: ce/label-* - config_name: ceb data_files: - split: label path: ceb/label-* - config_name: ch data_files: - split: label path: ch/label-* - config_name: cho data_files: - split: label path: cho/label-* - config_name: chr data_files: - split: label path: chr/label-* - config_name: chy data_files: - split: label path: chy/label-* - config_name: ckb data_files: - split: label path: ckb/label-* - config_name: co data_files: - split: label path: co/label-* - config_name: cps data_files: - split: label path: cps/label-* - config_name: cr data_files: - split: label path: cr/label-* - config_name: crh data_files: - split: label path: crh/label-* - config_name: crh-cyrl data_files: - split: label path: crh-cyrl/label-* - config_name: crh-latn data_files: - split: label path: crh-latn/label-* - config_name: cs data_files: - split: label path: cs/label-* - config_name: csb data_files: - split: label path: csb/label-* - config_name: cv data_files: - split: label path: cv/label-* - config_name: cy data_files: - split: label path: cy/label-* - config_name: da data_files: - split: label path: da/label-* - config_name: dag data_files: - split: label path: dag/label-* - config_name: de data_files: - split: label path: de/label-* - config_name: de-at data_files: - split: label path: de-at/label-* - config_name: de-ch data_files: - split: label path: de-ch/label-* - config_name: de-formal data_files: - split: label path: de-formal/label-* - config_name: din data_files: - split: label path: din/label-* - config_name: diq data_files: - split: label path: diq/label-* - config_name: dsb data_files: - split: label path: dsb/label-* - config_name: dtp data_files: - split: label path: dtp/label-* - config_name: dty data_files: - split: label path: dty/label-* - config_name: dua data_files: - split: label path: dua/label-* - config_name: dv data_files: - split: label path: dv/label-* - config_name: dz data_files: - split: label path: dz/label-* - config_name: ee data_files: - split: label path: ee/label-* - config_name: egl data_files: - split: label path: egl/label-* - config_name: el data_files: - split: label path: el/label-* - config_name: eml data_files: - split: label path: eml/label-* - config_name: en data_files: - split: label path: en/label-* default: true - config_name: en-ca data_files: - split: label path: en-ca/label-* - config_name: en-gb data_files: - split: label path: en-gb/label-* - config_name: en-us data_files: - split: label path: en-us/label-* - config_name: eo data_files: - split: label path: eo/label-* - config_name: es data_files: - split: label path: es/label-* - config_name: es-419 data_files: - split: label path: es-419/label-* - config_name: es-formal data_files: - split: label path: es-formal/label-* - config_name: et data_files: - split: label path: et/label-* - config_name: eu data_files: - split: label path: eu/label-* - config_name: ext data_files: - split: label path: ext/label-* - config_name: fa data_files: - split: label path: fa/label-* - config_name: ff data_files: - split: label path: ff/label-* - config_name: fi data_files: - split: label path: fi/label-* - config_name: fit data_files: - split: label path: fit/label-* - config_name: fj data_files: - split: label path: fj/label-* - config_name: fkv data_files: - split: label path: fkv/label-* - config_name: fo data_files: - split: label path: fo/label-* - config_name: fr data_files: - split: label path: fr/label-* - config_name: frc data_files: - split: label path: frc/label-* - config_name: frp data_files: - split: label path: frp/label-* - config_name: frr data_files: - split: label path: frr/label-* - config_name: fur data_files: - split: label path: fur/label-* - config_name: ga data_files: - split: label path: ga/label-* - config_name: gag data_files: - split: label path: gag/label-* - config_name: gan data_files: - split: label path: gan/label-* - config_name: gan-hans data_files: - split: label path: gan-hans/label-* - config_name: gan-hant data_files: - split: label path: gan-hant/label-* - config_name: gcr data_files: - split: label path: gcr/label-* - config_name: gd data_files: - split: label path: gd/label-* - config_name: gl data_files: - split: label path: gl/label-* - config_name: glk data_files: - split: label path: glk/label-* - config_name: gn data_files: - split: label path: gn/label-* - config_name: gom data_files: - split: label path: gom/label-* - config_name: gom-deva data_files: - split: label path: gom-deva/label-* - config_name: gom-latn data_files: - split: label path: gom-latn/label-* - config_name: gor data_files: - split: label path: gor/label-* - config_name: got data_files: - split: label path: got/label-* - config_name: grc data_files: - split: label path: grc/label-* - config_name: gu data_files: - split: label path: gu/label-* - config_name: guc data_files: - split: label path: guc/label-* - config_name: guw data_files: - split: label path: guw/label-* - config_name: gv data_files: - split: label path: gv/label-* - config_name: ha data_files: - split: label path: ha/label-* - config_name: hak data_files: - split: label path: hak/label-* - config_name: haw data_files: - split: label path: haw/label-* - config_name: he data_files: - split: label path: he/label-* - config_name: hi data_files: - split: label path: hi/label-* - config_name: hif data_files: - split: label path: hif/label-* - config_name: hif-latn data_files: - split: label path: hif-latn/label-* - config_name: hil data_files: - split: label path: hil/label-* - config_name: ho data_files: - split: label path: ho/label-* - config_name: hr data_files: - split: label path: hr/label-* - config_name: hrx data_files: - split: label path: hrx/label-* - config_name: hsb data_files: - split: label path: hsb/label-* - config_name: ht data_files: - split: label path: ht/label-* - config_name: hu data_files: - split: label path: hu/label-* - config_name: hu-formal data_files: - split: label path: hu-formal/label-* - config_name: hy data_files: - split: label path: hy/label-* - config_name: hyw data_files: - split: label path: hyw/label-* - config_name: hz data_files: - split: label path: hz/label-* - config_name: ia data_files: - split: label path: ia/label-* - config_name: id data_files: - split: label path: id/label-* - config_name: ie data_files: - split: label path: ie/label-* - config_name: ig data_files: - split: label path: ig/label-* - config_name: ii data_files: - split: label path: ii/label-* - config_name: ik data_files: - split: label path: ik/label-* - config_name: ike-cans data_files: - split: label path: ike-cans/label-* - config_name: ike-latn data_files: - split: label path: ike-latn/label-* - config_name: ilo data_files: - split: label path: ilo/label-* - config_name: inh data_files: - split: label path: inh/label-* - config_name: io data_files: - split: label path: io/label-* - config_name: is data_files: - split: label path: is/label-* - config_name: it data_files: - split: label path: it/label-* - config_name: iu data_files: - split: label path: iu/label-* - config_name: ja data_files: - split: label path: ja/label-* - config_name: jam data_files: - split: label path: jam/label-* - config_name: jbo data_files: - split: label path: jbo/label-* - config_name: jv data_files: - split: label path: jv/label-* - config_name: ka data_files: - split: label path: ka/label-* - config_name: kaa data_files: - split: label path: kaa/label-* - config_name: kab data_files: - split: label path: kab/label-* - config_name: kbd data_files: - split: label path: kbd/label-* - config_name: kbd-cyrl data_files: - split: label path: kbd-cyrl/label-* - config_name: kbp data_files: - split: label path: kbp/label-* - config_name: kea data_files: - split: label path: kea/label-* - config_name: kg data_files: - split: label path: kg/label-* - config_name: khw data_files: - split: label path: khw/label-* - config_name: ki data_files: - split: label path: ki/label-* - config_name: kj data_files: - split: label path: kj/label-* - config_name: kjp data_files: - split: label path: kjp/label-* - config_name: kk data_files: - split: label path: kk/label-* - config_name: kk-arab data_files: - split: label path: kk-arab/label-* - config_name: kk-kz data_files: - split: label path: kk-kz/label-* - config_name: kk-latn data_files: - split: label path: kk-latn/label-* - config_name: kk-tr data_files: - split: label path: kk-tr/label-* - config_name: ko data_files: - split: label path: ko/label-* - config_name: ko-kp data_files: - split: label path: ko-kp/label-* - config_name: koi data_files: - split: label path: koi/label-* - config_name: kr data_files: - split: label path: kr/label-* - config_name: krc data_files: - split: label path: krc/label-* - config_name: kri data_files: - split: label path: kri/label-* - config_name: krj data_files: - split: label path: krj/label-* - config_name: krl data_files: - split: label path: krl/label-* - config_name: ks data_files: - split: label path: ks/label-* - config_name: ks-deva data_files: - split: label path: ks-deva/label-* - config_name: ksh data_files: - split: label path: ksh/label-* - config_name: ku data_files: - split: label path: ku/label-* - config_name: ku-arab data_files: - split: label path: ku-arab/label-* - config_name: ku-latn data_files: - split: label path: ku-latn/label-* - config_name: kum data_files: - split: label path: kum/label-* - config_name: kv data_files: - split: label path: kv/label-* - config_name: kw data_files: - split: label path: kw/label-* - config_name: ky data_files: - split: label path: ky/label-* - config_name: la data_files: - split: label path: la/label-* - config_name: lad data_files: - split: label path: lad/label-* - config_name: lb data_files: - split: label path: lb/label-* - config_name: lbe data_files: - split: label path: lbe/label-* - config_name: lez data_files: - split: label path: lez/label-* - config_name: lfn data_files: - split: label path: lfn/label-* - config_name: lg data_files: - split: label path: lg/label-* - config_name: li data_files: - split: label path: li/label-* - config_name: lij data_files: - split: label path: lij/label-* - config_name: liv data_files: - split: label path: liv/label-* - config_name: lki data_files: - split: label path: lki/label-* - config_name: lld data_files: - split: label path: lld/label-* - config_name: lmo data_files: - split: label path: lmo/label-* - config_name: ln data_files: - split: label path: ln/label-* - config_name: lo data_files: - split: label path: lo/label-* - config_name: loz data_files: - split: label path: loz/label-* - config_name: lt data_files: - split: label path: lt/label-* - config_name: ltg data_files: - split: label path: ltg/label-* - config_name: lus data_files: - split: label path: lus/label-* - config_name: luz data_files: - split: label path: luz/label-* - config_name: lv data_files: - split: label path: lv/label-* - config_name: lzh data_files: - split: label path: lzh/label-* - config_name: mdf data_files: - split: label path: mdf/label-* - config_name: mg data_files: - split: label path: mg/label-* - config_name: mh data_files: - split: label path: mh/label-* - config_name: mi data_files: - split: label path: mi/label-* - config_name: min data_files: - split: label path: min/label-* - config_name: mk data_files: - split: label path: mk/label-* - config_name: ml data_files: - split: label path: ml/label-* - config_name: mn data_files: - split: label path: mn/label-* - config_name: mni data_files: - split: label path: mni/label-* - config_name: mnw data_files: - split: label path: mnw/label-* - config_name: mo data_files: - split: label path: mo/label-* - config_name: mr data_files: - split: label path: mr/label-* - config_name: mrh data_files: - split: label path: mrh/label-* - config_name: mrj data_files: - split: label path: mrj/label-* - config_name: ms data_files: - split: label path: ms/label-* - config_name: ms-arab data_files: - split: label path: ms-arab/label-* - config_name: mt data_files: - split: label path: mt/label-* - config_name: mus data_files: - split: label path: mus/label-* - config_name: mwl data_files: - split: label path: mwl/label-* - config_name: my data_files: - split: label path: my/label-* - config_name: mzn data_files: - split: label path: mzn/label-* - config_name: na data_files: - split: label path: na/label-* - config_name: nah data_files: - split: label path: nah/label-* - config_name: nan-hani data_files: - split: label path: nan-hani/label-* - config_name: nap data_files: - split: label path: nap/label-* - config_name: nb data_files: - split: label path: nb/label-* - config_name: nds data_files: - split: label path: nds/label-* - config_name: nds-nl data_files: - split: label path: nds-nl/label-* - config_name: ne data_files: - split: label path: ne/label-* - config_name: new data_files: - split: label path: new/label-* - config_name: ng data_files: - split: label path: ng/label-* - config_name: nia data_files: - split: label path: nia/label-* - config_name: niu data_files: - split: label path: niu/label-* - config_name: nl data_files: - split: label path: nl/label-* - config_name: nn data_files: - split: label path: nn/label-* - config_name: 'no' data_files: - split: label path: no/label-* - config_name: nod data_files: - split: label path: nod/label-* - config_name: nov data_files: - split: label path: nov/label-* - config_name: nqo data_files: - split: label path: nqo/label-* - config_name: nrm data_files: - split: label path: nrm/label-* - config_name: nso data_files: - split: label path: nso/label-* - config_name: nv data_files: - split: label path: nv/label-* - config_name: ny data_files: - split: label path: ny/label-* - config_name: nys data_files: - split: label path: nys/label-* - config_name: oc data_files: - split: label path: oc/label-* - config_name: olo data_files: - split: label path: olo/label-* - config_name: om data_files: - split: label path: om/label-* - config_name: or data_files: - split: label path: or/label-* - config_name: os data_files: - split: label path: os/label-* - config_name: ota data_files: - split: label path: ota/label-* - config_name: pa data_files: - split: label path: pa/label-* - config_name: pam data_files: - split: label path: pam/label-* - config_name: pap data_files: - split: label path: pap/label-* - config_name: pcd data_files: - split: label path: pcd/label-* - config_name: pdc data_files: - split: label path: pdc/label-* - config_name: pdt data_files: - split: label path: pdt/label-* - config_name: pfl data_files: - split: label path: pfl/label-* - config_name: pi data_files: - split: label path: pi/label-* - config_name: pih data_files: - split: label path: pih/label-* - config_name: pl data_files: - split: label path: pl/label-* - config_name: pms data_files: - split: label path: pms/label-* - config_name: pnb data_files: - split: label path: pnb/label-* - config_name: pnt data_files: - split: label path: pnt/label-* - config_name: prg data_files: - split: label path: prg/label-* - config_name: ps data_files: - split: label path: ps/label-* - config_name: pt data_files: - split: label path: pt/label-* - config_name: pt-br data_files: - split: label path: pt-br/label-* - config_name: pwn data_files: - split: label path: pwn/label-* - config_name: qu data_files: - split: label path: qu/label-* - config_name: quc data_files: - split: label path: quc/label-* - config_name: qug data_files: - split: label path: qug/label-* - config_name: rgn data_files: - split: label path: rgn/label-* - config_name: rif data_files: - split: label path: rif/label-* - config_name: rm data_files: - split: label path: rm/label-* - config_name: rmc data_files: - split: label path: rmc/label-* - config_name: rmy data_files: - split: label path: rmy/label-* - config_name: rn data_files: - split: label path: rn/label-* - config_name: ro data_files: - split: label path: ro/label-* - config_name: roa-tara data_files: - split: label path: roa-tara/label-* - config_name: ru data_files: - split: label path: ru/label-* - config_name: rue data_files: - split: label path: rue/label-* - config_name: rup data_files: - split: label path: rup/label-* - config_name: ruq-cyrl data_files: - split: label path: ruq-cyrl/label-* - config_name: ruq-latn data_files: - split: label path: ruq-latn/label-* - config_name: rw data_files: - split: label path: rw/label-* - config_name: rwr data_files: - split: label path: rwr/label-* - config_name: ryu data_files: - split: label path: ryu/label-* - config_name: sa data_files: - split: label path: sa/label-* - config_name: sat data_files: - split: label path: sat/label-* - config_name: sc data_files: - split: label path: sc/label-* - config_name: scn data_files: - split: label path: scn/label-* - config_name: sco data_files: - split: label path: sco/label-* - config_name: sd data_files: - split: label path: sd/label-* - config_name: sdc data_files: - split: label path: sdc/label-* - config_name: se data_files: - split: label path: se/label-* - config_name: sei data_files: - split: label path: sei/label-* - config_name: sg data_files: - split: label path: sg/label-* - config_name: sh data_files: - split: label path: sh/label-* - config_name: shi-latn data_files: - split: label path: shi-latn/label-* - config_name: shi-tfng data_files: - split: label path: shi-tfng/label-* - config_name: shn data_files: - split: label path: shn/label-* - config_name: shy-latn data_files: - split: label path: shy-latn/label-* - config_name: si data_files: - split: label path: si/label-* - config_name: sjd data_files: - split: label path: sjd/label-* - config_name: sje data_files: - split: label path: sje/label-* - config_name: sju data_files: - split: label path: sju/label-* - config_name: sk data_files: - split: label path: sk/label-* - config_name: skr data_files: - split: label path: skr/label-* - config_name: sl data_files: - split: label path: sl/label-* - config_name: sli data_files: - split: label path: sli/label-* - config_name: sm data_files: - split: label path: sm/label-* - config_name: sma data_files: - split: label path: sma/label-* - config_name: smj data_files: - split: label path: smj/label-* - config_name: smn data_files: - split: label path: smn/label-* - config_name: sms data_files: - split: label path: sms/label-* - config_name: sn data_files: - split: label path: sn/label-* - config_name: sq data_files: - split: label path: sq/label-* - config_name: sr data_files: - split: label path: sr/label-* - config_name: sr-ec data_files: - split: label path: sr-ec/label-* - config_name: sr-el data_files: - split: label path: sr-el/label-* - config_name: srq data_files: - split: label path: srq/label-* - config_name: ss data_files: - split: label path: ss/label-* - config_name: st data_files: - split: label path: st/label-* - config_name: stq data_files: - split: label path: stq/label-* - config_name: su data_files: - split: label path: su/label-* - config_name: sv data_files: - split: label path: sv/label-* - config_name: sw data_files: - split: label path: sw/label-* - config_name: szl data_files: - split: label path: szl/label-* - config_name: szy data_files: - split: label path: szy/label-* - config_name: ta data_files: - split: label path: ta/label-* - config_name: tay data_files: - split: label path: tay/label-* - config_name: tcy data_files: - split: label path: tcy/label-* - config_name: te data_files: - split: label path: te/label-* - config_name: tet data_files: - split: label path: tet/label-* - config_name: tg data_files: - split: label path: tg/label-* - config_name: tg-cyrl data_files: - split: label path: tg-cyrl/label-* - config_name: tg-latn data_files: - split: label path: tg-latn/label-* - config_name: th data_files: - split: label path: th/label-* - config_name: ti data_files: - split: label path: ti/label-* - config_name: tk data_files: - split: label path: tk/label-* - config_name: tl data_files: - split: label path: tl/label-* - config_name: tly data_files: - split: label path: tly/label-* - config_name: tly-cyrl data_files: - split: label path: tly-cyrl/label-* - config_name: tn data_files: - split: label path: tn/label-* - config_name: to data_files: - split: label path: to/label-* - config_name: tpi data_files: - split: label path: tpi/label-* - config_name: tr data_files: - split: label path: tr/label-* - config_name: tru data_files: - split: label path: tru/label-* - config_name: trv data_files: - split: label path: trv/label-* - config_name: ts data_files: - split: label path: ts/label-* - config_name: tt data_files: - split: label path: tt/label-* - config_name: tt-cyrl data_files: - split: label path: tt-cyrl/label-* - config_name: tt-latn data_files: - split: label path: tt-latn/label-* - config_name: tum data_files: - split: label path: tum/label-* - config_name: tw data_files: - split: label path: tw/label-* - config_name: ty data_files: - split: label path: ty/label-* - config_name: tyv data_files: - split: label path: tyv/label-* - config_name: tzm data_files: - split: label path: tzm/label-* - config_name: udm data_files: - split: label path: udm/label-* - config_name: ug-arab data_files: - split: label path: ug-arab/label-* - config_name: ug-latn data_files: - split: label path: ug-latn/label-* - config_name: uk data_files: - split: label path: uk/label-* - config_name: ur data_files: - split: label path: ur/label-* - config_name: uz data_files: - split: label path: uz/label-* - config_name: uz-cyrl data_files: - split: label path: uz-cyrl/label-* - config_name: ve data_files: - split: label path: ve/label-* - config_name: vec data_files: - split: label path: vec/label-* - config_name: vep data_files: - split: label path: vep/label-* - config_name: vi data_files: - split: label path: vi/label-* - config_name: vls data_files: - split: label path: vls/label-* - config_name: vmf data_files: - split: label path: vmf/label-* - config_name: vo data_files: - split: label path: vo/label-* - config_name: vot data_files: - split: label path: vot/label-* - config_name: wa data_files: - split: label path: wa/label-* - config_name: war data_files: - split: label path: war/label-* - config_name: wls data_files: - split: label path: wls/label-* - config_name: wo data_files: - split: label path: wo/label-* - config_name: wuu data_files: - split: label path: wuu/label-* - config_name: wya data_files: - split: label path: wya/label-* - config_name: xal data_files: - split: label path: xal/label-* - config_name: xh data_files: - split: label path: xh/label-* - config_name: xmf data_files: - split: label path: xmf/label-* - config_name: xsy data_files: - split: label path: xsy/label-* - config_name: yav data_files: - split: label path: yav/label-* - config_name: yi data_files: - split: label path: yi/label-* - config_name: yo data_files: - split: label path: yo/label-* - config_name: za data_files: - split: label path: za/label-* - config_name: zea data_files: - split: label path: zea/label-* - config_name: zgh data_files: - split: label path: zgh/label-* - config_name: zh data_files: - split: label path: zh/label-* - config_name: zh-cn data_files: - split: label path: zh-cn/label-* - config_name: zh-hans data_files: - split: label path: zh-hans/label-* - config_name: zh-hant data_files: - split: label path: zh-hant/label-* - config_name: zh-hk data_files: - split: label path: zh-hk/label-* - config_name: zh-mo data_files: - split: label path: zh-mo/label-* - config_name: zh-my data_files: - split: label path: zh-my/label-* - config_name: zh-sg data_files: - split: label path: zh-sg/label-* - config_name: zh-tw data_files: - split: label path: zh-tw/label-* - config_name: zh-yue data_files: - split: label path: zh-yue/label-* - config_name: zu data_files: - split: label path: zu/label-* task_categories: - translation - text2text-generation language: - en - fr - de - ja - zh - hi - ar - bn - ru - es --- # Wikidata Labels Large parallel corpus for machine translation - Entity label data extracted from Wikidata (2022-01-03), filtered for item entities only - Only download the languages you need with `datasets>=2.14.0` - Similar dataset: https://huggingface.co./datasets/wmt/wikititles (18 Wikipedia titles pairs instead of all Wikidata entities) ## Dataset Details ### Dataset Sources - Wikidata JSON dump (wikidata-20220103-all.json.gz) https://www.wikidata.org/wiki/Wikidata:Database_download ## Uses You can generate parallel text examples from this dataset like below: ```python from datasets import load_dataset import pandas as pd def parallel_labels(lang_codes: list, how="inner", repo_id="rayliuca/wikidata_entity_label", merge_config={}, datasets_config={}) -> pd.DataFrame: out_df = None for lc in lang_codes: dataset = load_dataset(repo_id, lc, **datasets_config) dataset_df = dataset['label'].to_pandas().rename(columns={"label":lc}).drop(columns=['lastrevid']) if out_df is None: out_df = dataset_df else: out_df = out_df.merge( dataset_df, on='wikidata_id', how=how, **merge_config ) return out_df # Note: the "en" subset is >4GB parallel_labels(['en', 'fr', 'ja', 'zh']).head() ``` ### Output | | wikidata_id | en | fr | ja | zh | |---:|:--------------|:------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------|:---------------------------------------|:---------------------------------------------| | 0 | Q109739412 | SARS-CoV-2 Omicron variant | variant Omicron du SARS-CoV-2 | SARSコロナウイルス2-オミクロン株 | 嚴重急性呼吸道症候群冠狀病毒2型Omicron變異株 | | 1 | Q108460606 | Ulughbegsaurus | Ulughbegsaurus | ウルグベグサウルス | 兀魯伯龍屬 | | 2 | Q108556886 | AUKUS | AUKUS | AUKUS | AUKUS | | 3 | Q106496152 | Claude Joseph | Claude Joseph | クロード・ジョゼフ | 克洛德·约瑟夫 | | 4 | Q105519361 | The World's Finest Assassin Gets Reincarnated in a Different World as an Aristocrat | The World's Finest Assassin Gets Reincarnated in Another World as an Aristocrat | 世界最高の暗殺者、異世界貴族に転生する | 世界頂尖的暗殺者轉生為異世界貴族 | Note: this example table above shows a quirk(?) of the Wiki data. The French Wikipedia page [The World's Finest Assassin Gets Reincarnated in Another World as an Aristocrat](https://fr.wikipedia.org/wiki/The_World%27s_Finest_Assassin_Gets_Reincarnated_in_Another_World_as_an_Aristocrat) uses English for its title. While this could be disadvantageous for direct translation training, it also provides insights into how native speakers might call this entity instead of the literal translation on the Wiki page as well ## Dataset Structure Each language has its own subset (aka config), which means you only have to download the languages you need with `datasets>=2.14.0` Each subset has these fields: - wikidata_id - lastrevid - label ## Dataset Creation #### Data Collection and Processing - Filtered for item entities only - Ignored the descriptions as those texts are not very parallel ## Bias, Risks, and Limitations - Might be slightly outdated (2022) - Popular languages have more entries - Labels are not guaranteed to be literal translations (see examples above)

Samsung/samsum

Samsung

--- annotations_creators: - expert-generated language_creators: - expert-generated language: - en license: - cc-by-nc-nd-4.0 multilinguality: - monolingual size_categories: - 10K<n<100K source_datasets: - original task_categories: - summarization task_ids: [] paperswithcode_id: samsum-corpus pretty_name: SAMSum Corpus tags: - conversations-summarization dataset_info: features: - name: id dtype: string - name: dialogue dtype: string - name: summary dtype: string config_name: samsum splits: - name: train num_bytes: 9479141 num_examples: 14732 - name: test num_bytes: 534492 num_examples: 819 - name: validation num_bytes: 516431 num_examples: 818 download_size: 2944100 dataset_size: 10530064 train-eval-index: - config: samsum task: summarization task_id: summarization splits: eval_split: test col_mapping: dialogue: text summary: target --- # Dataset Card for SAMSum Corpus ## Table of Contents - [Dataset Description](#dataset-description) - [Dataset Summary](#dataset-summary) - [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards) - [Languages](#languages) - [Dataset Structure](#dataset-structure) - [Data Instances](#data-instances) - [Data Fields](#data-fields) - [Data Splits](#data-splits) - [Dataset Creation](#dataset-creation) - [Curation Rationale](#curation-rationale) - [Source Data](#source-data) - [Annotations](#annotations) - [Personal and Sensitive Information](#personal-and-sensitive-information) - [Considerations for Using the Data](#considerations-for-using-the-data) - [Social Impact of Dataset](#social-impact-of-dataset) - [Discussion of Biases](#discussion-of-biases) - [Other Known Limitations](#other-known-limitations) - [Additional Information](#additional-information) - [Dataset Curators](#dataset-curators) - [Licensing Information](#licensing-information) - [Citation Information](#citation-information) - [Contributions](#contributions) ## Dataset Description - **Homepage:** https://arxiv.org/abs/1911.12237v2 - **Repository:** [Needs More Information] - **Paper:** https://arxiv.org/abs/1911.12237v2 - **Leaderboard:** [Needs More Information] - **Point of Contact:** [Needs More Information] ### Dataset Summary The SAMSum dataset contains about 16k messenger-like conversations with summaries. Conversations were created and written down by linguists fluent in English. Linguists were asked to create conversations similar to those they write on a daily basis, reflecting the proportion of topics of their real-life messenger convesations. The style and register are diversified - conversations could be informal, semi-formal or formal, they may contain slang words, emoticons and typos. Then, the conversations were annotated with summaries. It was assumed that summaries should be a concise brief of what people talked about in the conversation in third person. The SAMSum dataset was prepared by Samsung R&D Institute Poland and is distributed for research purposes (non-commercial licence: CC BY-NC-ND 4.0). ### Supported Tasks and Leaderboards [Needs More Information] ### Languages English ## Dataset Structure ### Data Instances The created dataset is made of 16369 conversations distributed uniformly into 4 groups based on the number of utterances in con- versations: 3-6, 7-12, 13-18 and 19-30. Each utterance contains the name of the speaker. Most conversations consist of dialogues between two interlocutors (about 75% of all conversations), the rest is between three or more people The first instance in the training set: {'id': '13818513', 'summary': 'Amanda baked cookies and will bring Jerry some tomorrow.', 'dialogue': "Amanda: I baked cookies. Do you want some?\r\nJerry: Sure!\r\nAmanda: I'll bring you tomorrow :-)"} ### Data Fields - dialogue: text of dialogue. - summary: human written summary of the dialogue. - id: unique id of an example. ### Data Splits - train: 14732 - val: 818 - test: 819 ## Dataset Creation ### Curation Rationale In paper: > In the first approach, we reviewed datasets from the following categories: chatbot dialogues, SMS corpora, IRC/chat data, movie dialogues, tweets, comments data (conversations formed by replies to comments), transcription of meetings, written discussions, phone dialogues and daily communication data. Unfortunately, they all differed in some respect from the conversations that are typ- ically written in messenger apps, e.g. they were too technical (IRC data), too long (comments data, transcription of meetings), lacked context (movie dialogues) or they were more of a spoken type, such as a dialogue between a petrol station assis- tant and a client buying petrol. As a consequence, we decided to create a chat dialogue dataset by constructing such conversa- tions that would epitomize the style of a messenger app. ### Source Data #### Initial Data Collection and Normalization In paper: > We asked linguists to create conversations similar to those they write on a daily basis, reflecting the proportion of topics of their real-life messenger conversations. It includes chit-chats, gossiping about friends, arranging meetings, discussing politics, consulting university assignments with colleagues, etc. Therefore, this dataset does not contain any sensitive data or fragments of other corpora. #### Who are the source language producers? linguists ### Annotations #### Annotation process In paper: > Each dialogue was created by one person. After collecting all of the conversations, we asked language experts to annotate them with summaries, assuming that they should (1) be rather short, (2) extract important pieces of information, (3) include names of interlocutors, (4) be written in the third person. Each dialogue contains only one ref- erence summary. #### Who are the annotators? language experts ### Personal and Sensitive Information None, see above: Initial Data Collection and Normalization ## Considerations for Using the Data ### Social Impact of Dataset [Needs More Information] ### Discussion of Biases [Needs More Information] ### Other Known Limitations [Needs More Information] ## Additional Information ### Dataset Curators [Needs More Information] ### Licensing Information non-commercial licence: CC BY-NC-ND 4.0 ### Citation Information ``` @inproceedings{gliwa-etal-2019-samsum, title = "{SAMS}um Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarization", author = "Gliwa, Bogdan and Mochol, Iwona and Biesek, Maciej and Wawer, Aleksander", booktitle = "Proceedings of the 2nd Workshop on New Frontiers in Summarization", month = nov, year = "2019", address = "Hong Kong, China", publisher = "Association for Computational Linguistics", url = "https://www.aclweb.org/anthology/D19-5409", doi = "10.18653/v1/D19-5409", pages = "70--79" } ``` ### Contributions Thanks to [@cccntu](https://github.com/cccntu) for adding this dataset.

lmms-lab/MMMU

lmms-lab

--- dataset_info: features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 57719107.0 num_examples: 150 - name: validation num_bytes: 347519954.0 num_examples: 900 - name: test num_bytes: 3271046267.0 num_examples: 10500 download_size: 3377778136 dataset_size: 3676285328.0 configs: - config_name: default data_files: - split: dev path: data/dev-* - split: validation path: data/validation-* - split: test path: data/test-* --- This is a merged version of [MMMU/MMMU](https://huggingface.co./datasets/MMMU/MMMU) with all subsets concatenated. <p align="center" width="100%"> <img src="https://i.postimg.cc/g0QRgMVv/WX20240228-113337-2x.png" width="100%" height="80%"> </p> # Large-scale Multi-modality Models Evaluation Suite > Accelerating the development of large-scale multi-modality models (LMMs) with `lmms-eval` 🏠 [Homepage](https://lmms-lab.github.io/) | 📚 [Documentation](docs/README.md) | 🤗 [Huggingface Datasets](https://huggingface.co./lmms-lab) # This Dataset This is a formatted version of [MMMU](https://github.com/MMMU-Benchmark/MMMU). It is used in our `lmms-eval` pipeline to allow for one-click evaluations of large multi-modality models. ``` @article{yue2023mmmu, title={Mmmu: A massive multi-discipline multimodal understanding and reasoning benchmark for expert agi}, author={Yue, Xiang and Ni, Yuansheng and Zhang, Kai and Zheng, Tianyu and Liu, Ruoqi and Zhang, Ge and Stevens, Samuel and Jiang, Dongfu and Ren, Weiming and Sun, Yuxuan and others}, journal={arXiv preprint arXiv:2311.16502}, year={2023} } ```

HuggingFaceH4/ultrachat_200k

HuggingFaceH4

--- language: - en license: mit size_categories: - 100K<n<1M task_categories: - text-generation pretty_name: UltraChat 200k configs: - config_name: default data_files: - split: train_sft path: data/train_sft-* - split: test_sft path: data/test_sft-* - split: train_gen path: data/train_gen-* - split: test_gen path: data/test_gen-* dataset_info: features: - name: prompt dtype: string - name: prompt_id dtype: string - name: messages list: - name: content dtype: string - name: role dtype: string splits: - name: train_sft num_bytes: 1397058554 num_examples: 207865 - name: test_sft num_bytes: 154695659 num_examples: 23110 - name: train_gen num_bytes: 1347396812 num_examples: 256032 - name: test_gen num_bytes: 148276089 num_examples: 28304 download_size: 1624049723 dataset_size: 3047427114 --- # Dataset Card for UltraChat 200k ## Dataset Description This is a heavily filtered version of the [UltraChat](https://github.com/thunlp/UltraChat) dataset and was used to train [Zephyr-7B-β](https://huggingface.co./HuggingFaceH4/zephyr-7b-beta), a state of the art 7b chat model. The original datasets consists of 1.4M dialogues generated by ChatGPT and spanning a wide range of topics. To create `UltraChat 200k`, we applied the following logic: - Selection of a subset of data for faster supervised fine tuning. - Truecasing of the dataset, as we observed around 5% of the data contained grammatical errors like "Hello. how are you?" instead of "Hello. How are you?" - Removal of dialogues where the assistant replies with phrases like "I do not have emotions" or "I don't have opinions", even for fact-based prompts that don't involve either. ## Dataset Structure The dataset has four splits, suitable for: * Supervised fine-tuning (`sft`). * Generation ranking (`gen`) via techniques like rejection sampling or PPO. The number of examples per split is shown as follows: | train_sft | test_sft | train_gen | test_gen | |:-------:|:-----------:|:-----:| :-----:| | 207865 | 23110 | 256032 | 28304 | The dataset is stored in parquet format with each entry using the following schema: ``` { "prompt": "Create a fully-developed protagonist who is challenged to survive within a dystopian society under the rule of a tyrant. ...", "messages":[ { "content": "Create a fully-developed protagonist who is challenged to survive within a dystopian society under the rule of a tyrant. ...", "role": "user" }, { "content": "Name: Ava\n\n Ava was just 16 years old when the world as she knew it came crashing down. The government had collapsed, leaving behind a chaotic and lawless society. ...", "role": "assistant" }, { "content": "Wow, Ava's story is so intense and inspiring! Can you provide me with more details. ...", "role": "user" }, { "content": "Certainly! ....", "role": "assistant" }, { "content": "That's really interesting! I would love to hear more...", "role": "user" } { "content": "Certainly! ....", "role": "assistant" }, ], "prompt_id": "d938b65dfe31f05f80eb8572964c6673eddbd68eff3db6bd234d7f1e3b86c2af" } ``` ## Citation If you find this dataset is useful in your work, please cite the original UltraChat dataset: ``` @misc{ding2023enhancing, title={Enhancing Chat Language Models by Scaling High-quality Instructional Conversations}, author={Ning Ding and Yulin Chen and Bokai Xu and Yujia Qin and Zhi Zheng and Shengding Hu and Zhiyuan Liu and Maosong Sun and Bowen Zhou}, year={2023}, eprint={2305.14233}, archivePrefix={arXiv}, primaryClass={cs.CL} } ```

Salesforce/lotsa_data

Salesforce

--- license: apache-2.0 configs: - config_name: default data_files: - split: train path: "*/*.arrow" - config_name: "BEIJING_SUBWAY_30MIN" data_files: - split: train path: "BEIJING_SUBWAY_30MIN/*.arrow" - config_name: "HZMETRO" data_files: - split: train path: "HZMETRO/*.arrow" - config_name: "LOOP_SEATTLE" data_files: - split: train path: "LOOP_SEATTLE/*.arrow" - config_name: "LOS_LOOP" data_files: - split: train path: "LOS_LOOP/*.arrow" - config_name: "M_DENSE" data_files: - split: train path: "M_DENSE/*.arrow" - config_name: "PEMS03" data_files: - split: train path: "PEMS03/*.arrow" - config_name: "PEMS04" data_files: - split: train path: "PEMS04/*.arrow" - config_name: "PEMS07" data_files: - split: train path: "PEMS07/*.arrow" - config_name: "PEMS08" data_files: - split: train path: "PEMS08/*.arrow" - config_name: "PEMS_BAY" data_files: - split: train path: "PEMS_BAY/*.arrow" - config_name: "Q-TRAFFIC" data_files: - split: train path: "Q-TRAFFIC/*.arrow" - config_name: "SHMETRO" data_files: - split: train path: "SHMETRO/*.arrow" - config_name: "SZ_TAXI" data_files: - split: train path: "SZ_TAXI/*.arrow" - config_name: "alibaba_cluster_trace_2018" data_files: - split: train path: "alibaba_cluster_trace_2018/*.arrow" - config_name: "australian_electricity_demand" data_files: - split: train path: "australian_electricity_demand/*.arrow" - config_name: "azure_vm_traces_2017" data_files: - split: train path: "azure_vm_traces_2017/*.arrow" - config_name: "bdg-2_bear" data_files: - split: train path: "bdg-2_bear/*.arrow" - config_name: "bdg-2_fox" data_files: - split: train path: "bdg-2_fox/*.arrow" - config_name: "bdg-2_panther" data_files: - split: train path: "bdg-2_panther/*.arrow" - config_name: "bdg-2_rat" data_files: - split: train path: "bdg-2_rat/*.arrow" - config_name: "beijing_air_quality" data_files: - split: train path: "beijing_air_quality/*.arrow" - config_name: "bitcoin_with_missing" data_files: - split: train path: "bitcoin_with_missing/*.arrow" - config_name: "borealis" data_files: - split: train path: "borealis/*.arrow" - config_name: "borg_cluster_data_2011" data_files: - split: train path: "borg_cluster_data_2011/*.arrow" - config_name: "buildings_900k" data_files: - split: train path: "buildings_900k/*.arrow" - config_name: "bull" data_files: - split: train path: "bull/*.arrow" - config_name: "car_parts_with_missing" data_files: - split: train path: "car_parts_with_missing/*.arrow" - config_name: "cdc_fluview_ilinet" data_files: - split: train path: "cdc_fluview_ilinet/*.arrow" - config_name: "cdc_fluview_who_nrevss" data_files: - split: train path: "cdc_fluview_who_nrevss/*.arrow" - config_name: "china_air_quality" data_files: - split: train path: "china_air_quality/*.arrow" - config_name: "cif_2016_12" data_files: - split: train path: "cif_2016_12/*.arrow" - config_name: "cif_2016_6" data_files: - split: train path: "cif_2016_6/*.arrow" - config_name: "cmip6" data_files: - split: train path: "cmip6_*/*.arrow" - config_name: "cmip6_1850" data_files: - split: train path: "cmip6_1850/*.arrow" - config_name: "cmip6_1855" data_files: - split: train path: "cmip6_1855/*.arrow" - config_name: "cmip6_1860" data_files: - split: train path: "cmip6_1860/*.arrow" - config_name: "cmip6_1865" data_files: - split: train path: "cmip6_1865/*.arrow" - config_name: "cmip6_1870" data_files: - split: train path: "cmip6_1870/*.arrow" - config_name: "cmip6_1875" data_files: - split: train path: "cmip6_1875/*.arrow" - config_name: "cmip6_1880" data_files: - split: train path: "cmip6_1880/*.arrow" - config_name: "cmip6_1885" data_files: - split: train path: "cmip6_1885/*.arrow" - config_name: "cmip6_1890" data_files: - split: train path: "cmip6_1890/*.arrow" - config_name: "cmip6_1895" data_files: - split: train path: "cmip6_1895/*.arrow" - config_name: "cmip6_1900" data_files: - split: train path: "cmip6_1900/*.arrow" - config_name: "cmip6_1905" data_files: - split: train path: "cmip6_1905/*.arrow" - config_name: "cmip6_1910" data_files: - split: train path: "cmip6_1910/*.arrow" - config_name: "cmip6_1915" data_files: - split: train path: "cmip6_1915/*.arrow" - config_name: "cmip6_1920" data_files: - split: train path: "cmip6_1920/*.arrow" - config_name: "cmip6_1925" data_files: - split: train path: "cmip6_1925/*.arrow" - config_name: "cmip6_1930" data_files: - split: train path: "cmip6_1930/*.arrow" - config_name: "cmip6_1935" data_files: - split: train path: "cmip6_1935/*.arrow" - config_name: "cmip6_1940" data_files: - split: train path: "cmip6_1940/*.arrow" - config_name: "cmip6_1945" data_files: - split: train path: "cmip6_1945/*.arrow" - config_name: "cmip6_1950" data_files: - split: train path: "cmip6_1950/*.arrow" - config_name: "cmip6_1955" data_files: - split: train path: "cmip6_1955/*.arrow" - config_name: "cmip6_1960" data_files: - split: train path: "cmip6_1960/*.arrow" - config_name: "cmip6_1965" data_files: - split: train path: "cmip6_1965/*.arrow" - config_name: "cmip6_1970" data_files: - split: train path: "cmip6_1970/*.arrow" - config_name: "cmip6_1975" data_files: - split: train path: "cmip6_1975/*.arrow" - config_name: "cmip6_1980" data_files: - split: train path: "cmip6_1980/*.arrow" - config_name: "cmip6_1985" data_files: - split: train path: "cmip6_1985/*.arrow" - config_name: "cmip6_1990" data_files: - split: train path: "cmip6_1990/*.arrow" - config_name: "cmip6_1995" data_files: - split: train path: "cmip6_1995/*.arrow" - config_name: "cmip6_2000" data_files: - split: train path: "cmip6_2000/*.arrow" - config_name: "cmip6_2005" data_files: - split: train path: "cmip6_2005/*.arrow" - config_name: "cmip6_2010" data_files: - split: train path: "cmip6_2010/*.arrow" - config_name: "cockatoo" data_files: - split: train path: "cockatoo/*.arrow" - config_name: "covid19_energy" data_files: - split: train path: "covid19_energy/*.arrow" - config_name: "covid_deaths" data_files: - split: train path: "covid_deaths/*.arrow" - config_name: "covid_mobility" data_files: - split: train path: "covid_mobility/*.arrow" - config_name: "elecdemand" data_files: - split: train path: "elecdemand/*.arrow" - config_name: "elf" data_files: - split: train path: "elf/*.arrow" - config_name: "era5" data_files: - split: train path: "era5_*/*.arrow" - config_name: "era5_1989" data_files: - split: train path: "era5_1989/*.arrow" - config_name: "era5_1990" data_files: - split: train path: "era5_1990/*.arrow" - config_name: "era5_1991" data_files: - split: train path: "era5_1991/*.arrow" - config_name: "era5_1992" data_files: - split: train path: "era5_1992/*.arrow" - config_name: "era5_1993" data_files: - split: train path: "era5_1993/*.arrow" - config_name: "era5_1994" data_files: - split: train path: "era5_1994/*.arrow" - config_name: "era5_1995" data_files: - split: train path: "era5_1995/*.arrow" - config_name: "era5_1996" data_files: - split: train path: "era5_1996/*.arrow" - config_name: "era5_1997" data_files: - split: train path: "era5_1997/*.arrow" - config_name: "era5_1998" data_files: - split: train path: "era5_1998/*.arrow" - config_name: "era5_1999" data_files: - split: train path: "era5_1999/*.arrow" - config_name: "era5_2000" data_files: - split: train path: "era5_2000/*.arrow" - config_name: "era5_2001" data_files: - split: train path: "era5_2001/*.arrow" - config_name: "era5_2002" data_files: - split: train path: "era5_2002/*.arrow" - config_name: "era5_2003" data_files: - split: train path: "era5_2003/*.arrow" - config_name: "era5_2004" data_files: - split: train path: "era5_2004/*.arrow" - config_name: "era5_2005" data_files: - split: train path: "era5_2005/*.arrow" - config_name: "era5_2006" data_files: - split: train path: "era5_2006/*.arrow" - config_name: "era5_2007" data_files: - split: train path: "era5_2007/*.arrow" - config_name: "era5_2008" data_files: - split: train path: "era5_2008/*.arrow" - config_name: "era5_2009" data_files: - split: train path: "era5_2009/*.arrow" - config_name: "era5_2010" data_files: - split: train path: "era5_2010/*.arrow" - config_name: "era5_2011" data_files: - split: train path: "era5_2011/*.arrow" - config_name: "era5_2012" data_files: - split: train path: "era5_2012/*.arrow" - config_name: "era5_2013" data_files: - split: train path: "era5_2013/*.arrow" - config_name: "era5_2014" data_files: - split: train path: "era5_2014/*.arrow" - config_name: "era5_2015" data_files: - split: train path: "era5_2015/*.arrow" - config_name: "era5_2016" data_files: - split: train path: "era5_2016/*.arrow" - config_name: "era5_2017" data_files: - split: train path: "era5_2017/*.arrow" - config_name: "era5_2018" data_files: - split: train path: "era5_2018/*.arrow" - config_name: "extended_web_traffic_with_missing" data_files: - split: train path: "extended_web_traffic_with_missing/*.arrow" - config_name: "favorita_sales" data_files: - split: train path: "favorita_sales/*.arrow" - config_name: "favorita_transactions" data_files: - split: train path: "favorita_transactions/*.arrow" - config_name: "fred_md" data_files: - split: train path: "fred_md/*.arrow" - config_name: "gfc12_load" data_files: - split: train path: "gfc12_load/*.arrow" - config_name: "gfc14_load" data_files: - split: train path: "gfc14_load/*.arrow" - config_name: "gfc17_load" data_files: - split: train path: "gfc17_load/*.arrow" - config_name: "godaddy" data_files: - split: train path: "godaddy/*.arrow" - config_name: "hierarchical_sales" data_files: - split: train path: "hierarchical_sales/*.arrow" - config_name: "hog" data_files: - split: train path: "hog/*.arrow" - config_name: "hospital" data_files: - split: train path: "hospital/*.arrow" - config_name: "ideal" data_files: - split: train path: "ideal/*.arrow" - config_name: "kaggle_web_traffic_weekly" data_files: - split: train path: "kaggle_web_traffic_weekly/*.arrow" - config_name: "kdd2022" data_files: - split: train path: "kdd2022/*.arrow" - config_name: "kdd_cup_2018_with_missing" data_files: - split: train path: "kdd_cup_2018_with_missing/*.arrow" - config_name: "largest" data_files: - split: train path: "largest_*/*.arrow" - config_name: "largest_2017" data_files: - split: train path: "largest_2017/*.arrow" - config_name: "largest_2018" data_files: - split: train path: "largest_2018/*.arrow" - config_name: "largest_2019" data_files: - split: train path: "largest_2019/*.arrow" - config_name: "largest_2020" data_files: - split: train path: "largest_2020/*.arrow" - config_name: "largest_2021" data_files: - split: train path: "largest_2021/*.arrow" - config_name: "lcl" data_files: - split: train path: "lcl/*.arrow" - config_name: "london_smart_meters_with_missing" data_files: - split: train path: "london_smart_meters_with_missing/*.arrow" - config_name: "m1_monthly" data_files: - split: train path: "m1_monthly/*.arrow" - config_name: "m1_quarterly" data_files: - split: train path: "m1_quarterly/*.arrow" - config_name: "m1_yearly" data_files: - split: train path: "m1_yearly/*.arrow" - config_name: "m4_daily" data_files: - split: train path: "m4_daily/*.arrow" - config_name: "m4_hourly" data_files: - split: train path: "m4_hourly/*.arrow" - config_name: "m4_monthly" data_files: - split: train path: "m4_monthly/*.arrow" - config_name: "m4_quarterly" data_files: - split: train path: "m4_quarterly/*.arrow" - config_name: "m4_weekly" data_files: - split: train path: "m4_weekly/*.arrow" - config_name: "m4_yearly" data_files: - split: train path: "m4_yearly/*.arrow" - config_name: "m5" data_files: - split: train path: "m5/*.arrow" - config_name: "monash_m3_monthly" data_files: - split: train path: "monash_m3_monthly/*.arrow" - config_name: "monash_m3_other" data_files: - split: train path: "monash_m3_other/*.arrow" - config_name: "monash_m3_quarterly" data_files: - split: train path: "monash_m3_quarterly/*.arrow" - config_name: "monash_m3_yearly" data_files: - split: train path: "monash_m3_yearly/*.arrow" - config_name: "nn5_daily_with_missing" data_files: - split: train path: "nn5_daily_with_missing/*.arrow" - config_name: "nn5_weekly" data_files: - split: train path: "nn5_weekly/*.arrow" - config_name: "oikolab_weather" data_files: - split: train path: "oikolab_weather/*.arrow" - config_name: "pdb" data_files: - split: train path: "pdb/*.arrow" - config_name: "pedestrian_counts" data_files: - split: train path: "pedestrian_counts/*.arrow" - config_name: "project_tycho" data_files: - split: train path: "project_tycho/*.arrow" - config_name: "residential_load_power" data_files: - split: train path: "residential_load_power/*.arrow" - config_name: "residential_pv_power" data_files: - split: train path: "residential_pv_power/*.arrow" - config_name: "restaurant" data_files: - split: train path: "restaurant/*.arrow" - config_name: "rideshare_with_missing" data_files: - split: train path: "rideshare_with_missing/*.arrow" - config_name: "saugeenday" data_files: - split: train path: "saugeenday/*.arrow" - config_name: "sceaux" data_files: - split: train path: "sceaux/*.arrow" - config_name: "smart" data_files: - split: train path: "smart/*.arrow" - config_name: "solar_power" data_files: - split: train path: "solar_power/*.arrow" - config_name: "spain" data_files: - split: train path: "spain/*.arrow" - config_name: "subseasonal" data_files: - split: train path: "subseasonal/*.arrow" - config_name: "subseasonal_precip" data_files: - split: train path: "subseasonal_precip/*.arrow" - config_name: "sunspot_with_missing" data_files: - split: train path: "sunspot_with_missing/*.arrow" - config_name: "taxi_30min" data_files: - split: train path: "taxi_30min/*.arrow" - config_name: "temperature_rain_with_missing" data_files: - split: train path: "temperature_rain_with_missing/*.arrow" - config_name: "tourism_monthly" data_files: - split: train path: "tourism_monthly/*.arrow" - config_name: "tourism_quarterly" data_files: - split: train path: "tourism_quarterly/*.arrow" - config_name: "tourism_yearly" data_files: - split: train path: "tourism_yearly/*.arrow" - config_name: "traffic_hourly" data_files: - split: train path: "traffic_hourly/*.arrow" - config_name: "traffic_weekly" data_files: - split: train path: "traffic_weekly/*.arrow" - config_name: "uber_tlc_daily" data_files: - split: train path: "uber_tlc_daily/*.arrow" - config_name: "uber_tlc_hourly" data_files: - split: train path: "uber_tlc_hourly/*.arrow" - config_name: "us_births" data_files: - split: train path: "us_births/*.arrow" - config_name: "vehicle_trips_with_missing" data_files: - split: train path: "vehicle_trips_with_missing/*.arrow" - config_name: "weather" data_files: - split: train path: "weather/*.arrow" - config_name: "wiki-rolling_nips" data_files: - split: train path: "wiki-rolling_nips/*.arrow" - config_name: "wind_farms_with_missing" data_files: - split: train path: "wind_farms_with_missing/*.arrow" - config_name: "wind_power" data_files: - split: train path: "wind_power/*.arrow" --- # LOTSA Data The Large-scale Open Time Series Archive (LOTSA) is a collection of open time series datasets for time series forecasting. It was collected for the purpose of pre-training Large Time Series Models. See the [paper](https://arxiv.org/abs/2402.02592) and [codebase](https://github.com/SalesforceAIResearch/uni2ts) for more information. ## Citation <!-- If there is a paper or blog post introducing the dataset, the APA and Bibtex information for that should go in this section. --> If you're using LOTSA data in your research or applications, please cite it using this BibTeX: **BibTeX:** ```markdown @article{woo2024unified, title={Unified Training of Universal Time Series Forecasting Transformers}, author={Woo, Gerald and Liu, Chenghao and Kumar, Akshat and Xiong, Caiming and Savarese, Silvio and Sahoo, Doyen}, journal={arXiv preprint arXiv:2402.02592}, year={2024} } ```

mteb/sickr-sts

mteb

--- language: - en ---

fixie-ai/common_voice_17_0

fixie-ai

--- dataset_info: - config_name: ar features: - name: client_id dtype: string - name: path dtype: string - name: audio dtype: audio: sampling_rate: 48000 - name: sentence dtype: string - name: up_votes dtype: int64 - name: down_votes dtype: int64 - name: age dtype: string - name: gender dtype: string - name: accent dtype: string - name: locale dtype: string - name: segment dtype: string - name: variant dtype: string - name: continuation dtype: string splits: - name: validation num_bytes: 300234489.0 num_examples: 10470 - name: test num_bytes: 311234035.0 num_examples: 10480 - name: train num_bytes: 718845895.0 num_examples: 28369 download_size: 1250028526 dataset_size: 1330314419.0 - config_name: ast features: - name: client_id dtype: string - name: path dtype: string - name: audio dtype: audio: sampling_rate: 48000 - name: sentence dtype: string - name: up_votes dtype: int64 - name: down_votes dtype: int64 - name: age dtype: string - name: gender dtype: string - name: accent dtype: string - name: locale dtype: string - name: segment dtype: string - name: variant dtype: string - name: continuation dtype: string splits: - name: train num_bytes: 10829705.0 num_examples: 387 - name: validation num_bytes: 2892341.0 num_examples: 112 - name: test num_bytes: 4465643.0 num_examples: 162 - name: other num_bytes: 23505247.0 num_examples: 865 - name: invalidated num_bytes: 482228.0 num_examples: 16 - name: validated num_bytes: 18236675.0 num_examples: 663 download_size: 58002985 dataset_size: 60411839.0 - config_name: be features: - name: client_id dtype: string - name: path dtype: string - name: audio dtype: audio: sampling_rate: 48000 - name: sentence dtype: string - name: up_votes dtype: int64 - name: down_votes dtype: int64 - name: age dtype: string - name: gender dtype: string - name: accent dtype: string - name: locale dtype: string - name: segment dtype: string - name: variant dtype: string - name: continuation dtype: string splits: - name: train num_bytes: 10733982640.578 num_examples: 347637 - name: validation num_bytes: 568083900.76 num_examples: 15880 - name: test num_bytes: 554671489.332 num_examples: 15878 download_size: 10989547372 dataset_size: 11856738030.67 - config_name: bg features: - name: client_id dtype: string - name: path dtype: string - name: audio dtype: audio: sampling_rate: 48000 - name: sentence dtype: string - name: up_votes dtype: int64 - name: down_votes dtype: int64 - name: age dtype: string - name: gender dtype: string - name: accent dtype: string - name: locale dtype: string - name: segment dtype: string - name: variant dtype: string - name: continuation dtype: string splits: - name: train num_bytes: 148338156.76 num_examples: 4849 - name: validation num_bytes: 94198533.448 num_examples: 2766 - name: test num_bytes: 111571602.198 num_examples: 3201 - name: other num_bytes: 72720896.586 num_examples: 2087 - name: invalidated num_bytes: 27583684.0 num_examples: 746 - name: validated num_bytes: 377935138.456 num_examples: 10832 download_size: 799144053 dataset_size: 832348011.448 - config_name: br features: - name: client_id dtype: string - name: path dtype: string - name: audio dtype: audio: sampling_rate: 48000 - name: sentence dtype: string - name: up_votes dtype: int64 - name: down_votes dtype: int64 - name: age dtype: string - name: gender dtype: string - name: accent dtype: string - name: locale dtype: string - name: segment dtype: string - name: variant dtype: string - name: continuation dtype: string splits: - name: train num_bytes: 65441060.952 num_examples: 2663 - name: validation num_bytes: 58381364.479 num_examples: 2253 - name: test num_bytes: 57203564.256 num_examples: 2212 - name: other num_bytes: 196312974.159 num_examples: 8037 - name: invalidated num_bytes: 38704614.352 num_examples: 1364 - name: validated num_bytes: 542193361.699 num_examples: 21007 download_size: 871007071 dataset_size: 958236939.897 - config_name: cs features: - name: client_id dtype: string - name: path dtype: string - name: audio dtype: audio: sampling_rate: 48000 - name: sentence dtype: string - name: up_votes dtype: int64 - name: down_votes dtype: int64 - name: age dtype: string - name: gender dtype: string - name: accent dtype: string - name: locale dtype: string - name: segment dtype: string - name: variant dtype: string - name: continuation dtype: string splits: - name: train num_bytes: 715383853.824 num_examples: 20144 - name: validation num_bytes: 313988229.844 num_examples: 9009 - name: test num_bytes: 343116085.98 num_examples: 9067 - name: other num_bytes: 4245083794.24 num_examples: 148316 - name: invalidated num_bytes: 81780482.483 num_examples: 2213 - name: validated num_bytes: 1867262013.204 num_examples: 61391 download_size: 7228185761 dataset_size: 7566614459.575001 - config_name: cy features: - name: client_id dtype: string - name: path dtype: string - name: audio dtype: audio: sampling_rate: 48000 - name: sentence dtype: string - name: up_votes dtype: int64 - name: down_votes dtype: int64 - name: age dtype: string - name: gender dtype: string - name: accent dtype: string - name: locale dtype: string - name: segment dtype: string - name: variant dtype: string - name: continuation dtype: string splits: - name: train num_bytes: 334497968.0 num_examples: 7960 - name: validation num_bytes: 202144347.435 num_examples: 5371 - name: test num_bytes: 219542714.248 num_examples: 5379 - name: other num_bytes: 853036757.62 num_examples: 20145 - name: invalidated num_bytes: 168127588.328 num_examples: 4449 - name: validated num_bytes: 3386459797.8919997 num_examples: 90369 download_size: 4946011941 dataset_size: 5163809173.523001 - config_name: da features: - name: client_id dtype: string - name: path dtype: string - name: audio dtype: audio: sampling_rate: 48000 - name: sentence dtype: string - name: up_votes dtype: int64 - name: down_votes dtype: int64 - name: age dtype: string - name: gender dtype: string - name: accent dtype: string - name: locale dtype: string - name: segment dtype: string - name: variant dtype: string - name: continuation dtype: string splits: - name: train num_bytes: 82011190.3 num_examples: 3484 - name: validation num_bytes: 68072840.16 num_examples: 2105 - name: test num_bytes: 71855204.48 num_examples: 2530 - name: other num_bytes: 9809263.0 num_examples: 396 - name: invalidated num_bytes: 11802077.0 num_examples: 404 - name: validated num_bytes: 167119907.175 num_examples: 10225 download_size: 489135817 dataset_size: 410670482.115 - config_name: de features: - name: client_id dtype: string - name: path dtype: string - name: audio dtype: audio: sampling_rate: 48000 - name: sentence dtype: string - name: up_votes dtype: int64 - name: down_votes dtype: int64 - name: age dtype: string - name: gender dtype: string - name: accent dtype: string - name: locale dtype: string - name: segment dtype: string - name: variant dtype: string - name: continuation dtype: string splits: - name: train num_bytes: 23759438592.6 num_examples: 589100 - name: test num_bytes: 715601886.0 num_examples: 16183 - name: validation num_bytes: 710830645.0 num_examples: 16183 download_size: 24582787064 dataset_size: 25185871123.6 - config_name: el features: - name: client_id dtype: string - name: path dtype: string - name: audio dtype: audio: sampling_rate: 48000 - name: sentence dtype: string - name: up_votes dtype: int64 - name: down_votes dtype: int64 - name: age dtype: string - name: gender dtype: string - name: accent dtype: string - name: locale dtype: string - name: segment dtype: string - name: variant dtype: string - name: continuation dtype: string splits: - name: train num_bytes: 54020374.6 num_examples: 1920 - name: validation num_bytes: 45994345.6 num_examples: 1700 - name: test num_bytes: 53316364.508 num_examples: 1701 - name: other num_bytes: 286461727.86 num_examples: 10330 - name: invalidated num_bytes: 24280825.0 num_examples: 837 - name: validated num_bytes: 506396669.318 num_examples: 16199 download_size: 931351333 dataset_size: 970470306.886 - config_name: en features: - name: client_id dtype: string - name: path dtype: string - name: audio dtype: audio: sampling_rate: 48000 - name: sentence dtype: string - name: up_votes dtype: int64 - name: down_votes dtype: int64 - name: age dtype: string - name: gender dtype: string - name: accent dtype: string - name: locale dtype: string - name: segment dtype: string - name: variant dtype: string - name: continuation dtype: string splits: - name: test num_bytes: 9329520290.338 num_examples: 16393 - name: validation num_bytes: 9434608798.338 num_examples: 16393 - name: train num_bytes: 44987747251.6 num_examples: 1101170 - name: validated num_bytes: 68921650062.024 num_examples: 1799288 download_size: 128219063641 dataset_size: 132673526402.3 - config_name: es features: - name: client_id dtype: string - name: path dtype: string - name: audio dtype: audio: sampling_rate: 48000 - name: sentence dtype: string - name: up_votes dtype: int64 - name: down_votes dtype: int64 - name: age dtype: string - name: gender dtype: string - name: accent dtype: string - name: locale dtype: string - name: segment dtype: string - name: variant dtype: string - name: continuation dtype: string splits: - name: train num_bytes: 13216214878.31 num_examples: 336846 - name: test num_bytes: 748084507.0 num_examples: 15857 - name: validation num_bytes: 770184703.0 num_examples: 15857 download_size: 14415677901 dataset_size: 14734484088.309998 - config_name: et features: - name: client_id dtype: string - name: path dtype: string - name: audio dtype: audio: sampling_rate: 48000 - name: sentence dtype: string - name: up_votes dtype: int64 - name: down_votes dtype: int64 - name: age dtype: string - name: gender dtype: string - name: accent dtype: string - name: locale dtype: string - name: segment dtype: string - name: variant dtype: string - name: continuation dtype: string splits: - name: train num_bytes: 155780274.846 num_examples: 3157 - name: validation num_bytes: 124261027.42200002 num_examples: 2653 - name: test num_bytes: 142296894.679 num_examples: 2653 - name: other num_bytes: 2511793.0 num_examples: 60 - name: invalidated num_bytes: 442940142.204 num_examples: 7449 - name: validated num_bytes: 1309302759.063 num_examples: 24381 download_size: 1894945286 dataset_size: 2177092891.2139997 - config_name: fa features: - name: client_id dtype: string - name: path dtype: string - name: audio dtype: audio: sampling_rate: 48000 - name: sentence dtype: string - name: up_votes dtype: int64 - name: down_votes dtype: int64 - name: age dtype: string - name: gender dtype: string - name: accent dtype: string - name: locale dtype: string - name: segment dtype: string - name: variant dtype: string - name: continuation dtype: string splits: - name: train num_bytes: 796909284.504 num_examples: 28893 - name: validation num_bytes: 366343505.737 num_examples: 10559 - name: test num_bytes: 403851344.903 num_examples: 10559 - name: other num_bytes: 1242584327.472 num_examples: 32421 - name: invalidated num_bytes: 663271290.15 num_examples: 14558 - name: validated num_bytes: 9949122461.2 num_examples: 328720 download_size: 12556870202 dataset_size: 13422082213.966 - config_name: fi features: - name: client_id dtype: string - name: path dtype: string - name: audio dtype: audio: sampling_rate: 48000 - name: sentence dtype: string - name: up_votes dtype: int64 - name: down_votes dtype: int64 - name: age dtype: string - name: gender dtype: string - name: accent dtype: string - name: locale dtype: string - name: segment dtype: string - name: variant dtype: string - name: continuation dtype: string splits: - name: train num_bytes: 59037222.672 num_examples: 2076 - name: validation num_bytes: 49998252.45 num_examples: 1770 - name: test num_bytes: 57656484.763 num_examples: 1763 - name: other num_bytes: 171069411.222 num_examples: 6202 - name: invalidated num_bytes: 9828536.0 num_examples: 293 - name: validated num_bytes: 345303318.762 num_examples: 10447 download_size: 639777329 dataset_size: 692893225.869 - config_name: fr features: - name: client_id dtype: string - name: path dtype: string - name: audio dtype: audio: sampling_rate: 48000 - name: sentence dtype: string - name: up_votes dtype: int64 - name: down_votes dtype: int64 - name: age dtype: string - name: gender dtype: string - name: accent dtype: string - name: locale dtype: string - name: segment dtype: string - name: variant dtype: string - name: continuation dtype: string splits: - name: train num_bytes: 20630346378.228 num_examples: 558054 - name: test num_bytes: 684908439.0 num_examples: 16159 - name: validation num_bytes: 703910244.0 num_examples: 16159 download_size: 21981003249 dataset_size: 22019165061.228 - config_name: frold features: - name: client_id dtype: string - name: path dtype: string - name: audio dtype: audio: sampling_rate: 48000 - name: sentence dtype: string - name: up_votes dtype: int64 - name: down_votes dtype: int64 - name: age dtype: string - name: gender dtype: string - name: accent dtype: string - name: locale dtype: string - name: segment dtype: string - name: variant dtype: string - name: continuation dtype: string splits: - name: train num_bytes: 20616364930.228 num_examples: 558054 - name: test num_bytes: 674959025.258 num_examples: 16159 - name: validation num_bytes: 703829746.38 num_examples: 16159 download_size: 21972606682 dataset_size: 21995153701.866 - config_name: gl features: - name: client_id dtype: string - name: path dtype: string - name: audio dtype: audio: sampling_rate: 48000 - name: sentence dtype: string - name: up_votes dtype: int64 - name: down_votes dtype: int64 - name: age dtype: string - name: gender dtype: string - name: accent dtype: string - name: locale dtype: string - name: segment dtype: string - name: variant dtype: string - name: continuation dtype: string splits: - name: train num_bytes: 765856451.168 num_examples: 25159 - name: validation num_bytes: 304535689.856 num_examples: 9982 - name: test num_bytes: 324580802.22 num_examples: 9990 - name: other num_bytes: 1258726401.146 num_examples: 41313 - name: invalidated num_bytes: 149035909.144 num_examples: 4688 - name: validated num_bytes: 1488072059.26 num_examples: 45780 download_size: 4105373800 dataset_size: 4290807312.7939997 - config_name: ha features: - name: client_id dtype: string - name: path dtype: string - name: audio dtype: audio: sampling_rate: 48000 - name: sentence dtype: string - name: up_votes dtype: int64 - name: down_votes dtype: int64 - name: age dtype: string - name: gender dtype: string - name: accent dtype: string - name: locale dtype: string - name: segment dtype: string - name: variant dtype: string - name: continuation dtype: string splits: - name: train num_bytes: 52293332.0 num_examples: 1925 - name: validation num_bytes: 15326816.0 num_examples: 582 - name: test num_bytes: 19095449.0 num_examples: 661 download_size: 83233267 dataset_size: 86715597.0 - config_name: hi features: - name: client_id dtype: string - name: path dtype: string - name: audio dtype: audio: sampling_rate: 48000 - name: sentence dtype: string - name: up_votes dtype: int64 - name: down_votes dtype: int64 - name: age dtype: string - name: gender dtype: string - name: accent dtype: string - name: locale dtype: string - name: segment dtype: string - name: variant dtype: string - name: continuation dtype: string splits: - name: train num_bytes: 275394930.996 num_examples: 9378 - name: validation num_bytes: 145392985.176 num_examples: 4856 - name: test num_bytes: 220164125.264 num_examples: 6308 - name: other num_bytes: 253400896.056 num_examples: 8088 - name: invalidated num_bytes: 53706876.0 num_examples: 1550 - name: validated num_bytes: 721036368.28 num_examples: 20658 download_size: 1481543483 dataset_size: 1669096181.7719998 - config_name: hu features: - name: client_id dtype: string - name: path dtype: string - name: audio dtype: audio: sampling_rate: 48000 - name: sentence dtype: string - name: up_votes dtype: int64 - name: down_votes dtype: int64 - name: age dtype: string - name: gender dtype: string - name: accent dtype: string - name: locale dtype: string - name: segment dtype: string - name: variant dtype: string - name: continuation dtype: string splits: - name: train num_bytes: 1290925823.46 num_examples: 37140 - name: validation num_bytes: 386527859.2 num_examples: 11350 - name: test num_bytes: 408581762.4 num_examples: 11435 - name: other num_bytes: 1601200599.1889997 num_examples: 49019 - name: invalidated num_bytes: 106830322.07899998 num_examples: 3091 - name: validated num_bytes: 2029885437.988 num_examples: 60358 download_size: 5649520486 dataset_size: 5823951804.316 - config_name: it features: - name: client_id dtype: string - name: path dtype: string - name: audio dtype: audio: sampling_rate: 48000 - name: sentence dtype: string - name: up_votes dtype: int64 - name: down_votes dtype: int64 - name: age dtype: string - name: gender dtype: string - name: accent dtype: string - name: locale dtype: string - name: segment dtype: string - name: variant dtype: string - name: continuation dtype: string splits: - name: train num_bytes: 6137402083.638 num_examples: 169771 - name: validation num_bytes: 701042124.0 num_examples: 15149 - name: test num_bytes: 741163579.0 num_examples: 15155 download_size: 7600033249 dataset_size: 7579607786.638 - config_name: ja features: - name: client_id dtype: string - name: path dtype: string - name: audio dtype: audio: sampling_rate: 48000 - name: sentence dtype: string - name: up_votes dtype: int64 - name: down_votes dtype: int64 - name: age dtype: string - name: gender dtype: string - name: accent dtype: string - name: locale dtype: string - name: segment dtype: string - name: variant dtype: string - name: continuation dtype: string splits: - name: validation num_bytes: 186515137.0 num_examples: 6261 - name: test num_bytes: 199063298.0 num_examples: 6261 - name: train num_bytes: 307772889.0 num_examples: 10039 download_size: 684220424 dataset_size: 693351324.0 - config_name: ka features: - name: client_id dtype: string - name: path dtype: string - name: audio dtype: audio: sampling_rate: 48000 - name: sentence dtype: string - name: up_votes dtype: int64 - name: down_votes dtype: int64 - name: age dtype: string - name: gender dtype: string - name: accent dtype: string - name: locale dtype: string - name: segment dtype: string - name: variant dtype: string - name: continuation dtype: string splits: - name: train num_bytes: 1734206832.784 num_examples: 52321 - name: validation num_bytes: 460968626.98 num_examples: 12545 - name: test num_bytes: 484176773.044 num_examples: 12618 - name: other num_bytes: 1647678864.023 num_examples: 48563 - name: invalidated num_bytes: 154652385.072 num_examples: 4252 - name: validated num_bytes: 3039590286.645 num_examples: 97230 download_size: 7191808920 dataset_size: 7521273768.547998 - config_name: ko features: - name: client_id dtype: string - name: path dtype: string - name: audio dtype: audio: sampling_rate: 48000 - name: sentence dtype: string - name: up_votes dtype: int64 - name: down_votes dtype: int64 - name: age dtype: string - name: gender dtype: string - name: accent dtype: string - name: locale dtype: string - name: segment dtype: string - name: variant dtype: string - name: continuation dtype: string splits: - name: train num_bytes: 14414452.0 num_examples: 376 - name: validation num_bytes: 10399952.0 num_examples: 330 - name: test num_bytes: 10995530.0 num_examples: 339 - name: other num_bytes: 81478785.762 num_examples: 2057 - name: invalidated num_bytes: 12109483.0 num_examples: 270 - name: validated num_bytes: 35445686.402 num_examples: 1046 download_size: 154764122 dataset_size: 164843889.164 - config_name: lt features: - name: client_id dtype: string - name: path dtype: string - name: audio dtype: audio: sampling_rate: 48000 - name: sentence dtype: string - name: up_votes dtype: int64 - name: down_votes dtype: int64 - name: age dtype: string - name: gender dtype: string - name: accent dtype: string - name: locale dtype: string - name: segment dtype: string - name: variant dtype: string - name: continuation dtype: string splits: - name: train num_bytes: 209835116.997 num_examples: 7253 - name: validation num_bytes: 151062682.688 num_examples: 4436 - name: test num_bytes: 162556442.629 num_examples: 4753 - name: other num_bytes: 6904494.0 num_examples: 228 - name: invalidated num_bytes: 30174752.0 num_examples: 817 - name: validated num_bytes: 569626378.111 num_examples: 16643 download_size: 1095722603 dataset_size: 1130159866.425 - config_name: lv features: - name: client_id dtype: string - name: path dtype: string - name: audio dtype: audio: sampling_rate: 48000 - name: sentence dtype: string - name: up_votes dtype: int64 - name: down_votes dtype: int64 - name: age dtype: string - name: gender dtype: string - name: accent dtype: string - name: locale dtype: string - name: segment dtype: string - name: variant dtype: string - name: continuation dtype: string splits: - name: train num_bytes: 389918186.736 num_examples: 11364 - name: validation num_bytes: 214444094.4 num_examples: 6752 - name: test num_bytes: 247016773.056 num_examples: 6752 - name: other num_bytes: 774575206.568 num_examples: 32248 - name: invalidated num_bytes: 246579090.149 num_examples: 9533 - name: validated num_bytes: 5125871207.440001 num_examples: 171652 download_size: 6544433914 dataset_size: 6998404558.348999 - config_name: mk features: - name: client_id dtype: string - name: path dtype: string - name: audio dtype: audio: sampling_rate: 48000 - name: sentence dtype: string - name: up_votes dtype: int64 - name: down_votes dtype: int64 - name: age dtype: string - name: gender dtype: string - name: accent dtype: string - name: locale dtype: string - name: segment dtype: string - name: variant dtype: string - name: continuation dtype: string splits: - name: train num_bytes: 47301367.808 num_examples: 1686 - name: validation num_bytes: 34148332.96 num_examples: 1289 - name: test num_bytes: 33004372.576 num_examples: 1097 - name: other num_bytes: 360214120.86600006 num_examples: 12289 - name: invalidated num_bytes: 7369474.0 num_examples: 243 - name: validated num_bytes: 197695517.31999996 num_examples: 6512 download_size: 565282221 dataset_size: 679733185.53 - config_name: ml features: - name: client_id dtype: string - name: path dtype: string - name: audio dtype: audio: sampling_rate: 48000 - name: sentence dtype: string - name: up_votes dtype: int64 - name: down_votes dtype: int64 - name: age dtype: string - name: gender dtype: string - name: accent dtype: string - name: locale dtype: string - name: segment dtype: string - name: variant dtype: string - name: continuation dtype: string splits: - name: train num_bytes: 31264003.679 num_examples: 1259 - name: validation num_bytes: 18739113.0 num_examples: 764 - name: test num_bytes: 18614275.0 num_examples: 710 - name: other num_bytes: 141699368.196 num_examples: 5621 - name: invalidated num_bytes: 3191472.0 num_examples: 106 - name: validated num_bytes: 76056084.6 num_examples: 2984 download_size: 277861858 dataset_size: 289564316.475 - config_name: mn features: - name: client_id dtype: string - name: path dtype: string - name: audio dtype: audio: sampling_rate: 48000 - name: sentence dtype: string - name: up_votes dtype: int64 - name: down_votes dtype: int64 - name: age dtype: string - name: gender dtype: string - name: accent dtype: string - name: locale dtype: string - name: segment dtype: string - name: variant dtype: string - name: continuation dtype: string splits: - name: train num_bytes: 91286618.6 num_examples: 2175 - name: validation num_bytes: 83918248.11 num_examples: 1870 - name: test num_bytes: 87301693.544 num_examples: 1896 - name: other num_bytes: 261783831.25699997 num_examples: 5773 - name: invalidated num_bytes: 37994415.0 num_examples: 809 - name: validated num_bytes: 401045422.717 num_examples: 8757 download_size: 877760445 dataset_size: 963330229.2279999 - config_name: mr features: - name: client_id dtype: string - name: path dtype: string - name: audio dtype: audio: sampling_rate: 48000 - name: sentence dtype: string - name: up_votes dtype: int64 - name: down_votes dtype: int64 - name: age dtype: string - name: gender dtype: string - name: accent dtype: string - name: locale dtype: string - name: segment dtype: string - name: variant dtype: string - name: continuation dtype: string splits: - name: train num_bytes: 82324371.32 num_examples: 2215 - name: validation num_bytes: 72622291.4 num_examples: 1780 - name: test num_bytes: 69184965.291 num_examples: 1751 - name: other num_bytes: 105920245.12000002 num_examples: 2805 - name: invalidated num_bytes: 89957578.6 num_examples: 2265 - name: validated num_bytes: 430654155.517 num_examples: 10901 download_size: 807328544 dataset_size: 850663607.2479999 - config_name: nl features: - name: client_id dtype: string - name: path dtype: string - name: audio dtype: audio: sampling_rate: 48000 - name: sentence dtype: string - name: up_votes dtype: int64 - name: down_votes dtype: int64 - name: age dtype: string - name: gender dtype: string - name: accent dtype: string - name: locale dtype: string - name: segment dtype: string - name: variant dtype: string - name: continuation dtype: string splits: - name: train num_bytes: 1296442281.912 num_examples: 34898 - name: validation num_bytes: 368174915.228 num_examples: 11252 - name: test num_bytes: 408713015.03199995 num_examples: 11266 - name: other num_bytes: 83953868.822 num_examples: 2771 - name: invalidated num_bytes: 191476101.2 num_examples: 5580 - name: validated num_bytes: 2890451379.794 num_examples: 90449 download_size: 4761956599 dataset_size: 5239211561.988001 - config_name: oc features: - name: client_id dtype: string - name: path dtype: string - name: audio dtype: audio: sampling_rate: 48000 - name: sentence dtype: string - name: up_votes dtype: int64 - name: down_votes dtype: int64 - name: age dtype: string - name: gender dtype: string - name: accent dtype: string - name: locale dtype: string - name: segment dtype: string - name: variant dtype: string - name: continuation dtype: string splits: - name: train num_bytes: 8370168.0 num_examples: 271 - name: validation num_bytes: 7369724.0 num_examples: 260 - name: test num_bytes: 7981225.0 num_examples: 254 - name: other num_bytes: 233530880.4 num_examples: 7632 - name: invalidated num_bytes: 5792724.0 num_examples: 182 - name: validated num_bytes: 49584538.944 num_examples: 1668 download_size: 292926902 dataset_size: 312629260.344 - config_name: pl features: - name: client_id dtype: string - name: path dtype: string - name: audio dtype: audio: sampling_rate: 48000 - name: sentence dtype: string - name: up_votes dtype: int64 - name: down_votes dtype: int64 - name: age dtype: string - name: gender dtype: string - name: accent dtype: string - name: locale dtype: string - name: segment dtype: string - name: variant dtype: string - name: continuation dtype: string splits: - name: train num_bytes: 681180803.048 num_examples: 20729 - name: validation num_bytes: 325217628.02 num_examples: 9230 - name: test num_bytes: 368033596.56 num_examples: 9230 - name: other num_bytes: 22160515.0 num_examples: 662 - name: invalidated num_bytes: 279557995.4 num_examples: 6605 - name: validated num_bytes: 4518718954.4609995 num_examples: 132661 download_size: 6000668493 dataset_size: 6194869492.488999 - config_name: pt features: - name: client_id dtype: string - name: path dtype: string - name: audio dtype: audio: sampling_rate: 48000 - name: sentence dtype: string - name: up_votes dtype: int64 - name: down_votes dtype: int64 - name: age dtype: string - name: gender dtype: string - name: accent dtype: string - name: locale dtype: string - name: segment dtype: string - name: variant dtype: string - name: continuation dtype: string splits: - name: validation num_bytes: 290319070.0 num_examples: 9464 - name: test num_bytes: 304560776.0 num_examples: 9467 - name: train num_bytes: 624494986.0 num_examples: 21968 download_size: 1188978689 dataset_size: 1219374832.0 - config_name: ro features: - name: client_id dtype: string - name: path dtype: string - name: audio dtype: audio: sampling_rate: 48000 - name: sentence dtype: string - name: up_votes dtype: int64 - name: down_votes dtype: int64 - name: age dtype: string - name: gender dtype: string - name: accent dtype: string - name: locale dtype: string - name: segment dtype: string - name: variant dtype: string - name: continuation dtype: string splits: - name: train num_bytes: 133078550.984 num_examples: 5141 - name: validation num_bytes: 105068346.48 num_examples: 3881 - name: test num_bytes: 123465190.968 num_examples: 3896 - name: other num_bytes: 543898614.704 num_examples: 23087 - name: invalidated num_bytes: 23898694.0 num_examples: 977 - name: validated num_bytes: 560844530.353 num_examples: 17737 download_size: 1437521485 dataset_size: 1490253927.4889998 - config_name: ru features: - name: client_id dtype: string - name: path dtype: string - name: audio dtype: audio: sampling_rate: 48000 - name: sentence dtype: string - name: up_votes dtype: int64 - name: down_votes dtype: int64 - name: age dtype: string - name: gender dtype: string - name: accent dtype: string - name: locale dtype: string - name: segment dtype: string - name: variant dtype: string - name: continuation dtype: string splits: - name: validation num_bytes: 393037777.0 num_examples: 10203 - name: test num_bytes: 397099376.0 num_examples: 10203 - name: train num_bytes: 977625337.0 num_examples: 26377 download_size: 1734268016 dataset_size: 1767762490.0 - config_name: sk features: - name: client_id dtype: string - name: path dtype: string - name: audio dtype: audio: sampling_rate: 48000 - name: sentence dtype: string - name: up_votes dtype: int64 - name: down_votes dtype: int64 - name: age dtype: string - name: gender dtype: string - name: accent dtype: string - name: locale dtype: string - name: segment dtype: string - name: variant dtype: string - name: continuation dtype: string splits: - name: train num_bytes: 74831491.866 num_examples: 3258 - name: validation num_bytes: 67653499.816 num_examples: 2588 - name: test num_bytes: 70771288.681 num_examples: 2647 - name: other num_bytes: 92158853.128 num_examples: 3392 - name: invalidated num_bytes: 25400576.0 num_examples: 833 - name: validated num_bytes: 524330322.198 num_examples: 19513 download_size: 767611996 dataset_size: 855146031.689 - config_name: sl features: - name: client_id dtype: string - name: path dtype: string - name: audio dtype: audio: sampling_rate: 48000 - name: sentence dtype: string - name: up_votes dtype: int64 - name: down_votes dtype: int64 - name: age dtype: string - name: gender dtype: string - name: accent dtype: string - name: locale dtype: string - name: segment dtype: string - name: variant dtype: string - name: continuation dtype: string splits: - name: train num_bytes: 30021851.608 num_examples: 1388 - name: validation num_bytes: 33182159.072 num_examples: 1232 - name: test num_bytes: 36852679.33 num_examples: 1242 - name: other num_bytes: 71031102.54 num_examples: 3145 - name: invalidated num_bytes: 8357183.0 num_examples: 281 - name: validated num_bytes: 318885513.516 num_examples: 10819 download_size: 481787837 dataset_size: 498330489.066 - config_name: sr features: - name: client_id dtype: string - name: path dtype: string - name: audio dtype: audio: sampling_rate: 48000 - name: sentence dtype: string - name: up_votes dtype: int64 - name: down_votes dtype: int64 - name: age dtype: string - name: gender dtype: string - name: accent dtype: string - name: locale dtype: string - name: segment dtype: string - name: variant dtype: string - name: continuation dtype: string splits: - name: train num_bytes: 33763655.765 num_examples: 1879 - name: validation num_bytes: 25179221.496 num_examples: 1583 - name: test num_bytes: 31283094.164 num_examples: 1539 - name: other num_bytes: 34633621.309 num_examples: 1781 - name: invalidated num_bytes: 5912716.0 num_examples: 290 - name: validated num_bytes: 121128666.78 num_examples: 5970 download_size: 219387774 dataset_size: 251900975.514 - config_name: sv-SE features: - name: client_id dtype: string - name: path dtype: string - name: audio dtype: audio: sampling_rate: 48000 - name: sentence dtype: string - name: up_votes dtype: int64 - name: down_votes dtype: int64 - name: age dtype: string - name: gender dtype: string - name: accent dtype: string - name: locale dtype: string - name: segment dtype: string - name: variant dtype: string - name: continuation dtype: string splits: - name: train num_bytes: 201604157.344 num_examples: 7744 - name: validation num_bytes: 145407584.16 num_examples: 5210 - name: test num_bytes: 168456898.744 num_examples: 5259 - name: other num_bytes: 182626841.121 num_examples: 6759 - name: invalidated num_bytes: 43666692.56 num_examples: 1428 - name: validated num_bytes: 1302439008.81 num_examples: 40770 download_size: 1772780355 dataset_size: 2044201182.7389998 - config_name: sw features: - name: client_id dtype: string - name: path dtype: string - name: audio dtype: audio: sampling_rate: 48000 - name: sentence dtype: string - name: up_votes dtype: int64 - name: down_votes dtype: int64 - name: age dtype: string - name: gender dtype: string - name: accent dtype: string - name: locale dtype: string - name: segment dtype: string - name: variant dtype: string - name: continuation dtype: string splits: - name: train num_bytes: 1625554237.232 num_examples: 46494 - name: validation num_bytes: 393719831.126 num_examples: 12251 - name: test num_bytes: 447161293.396 num_examples: 12253 - name: other num_bytes: 11713924829.874 num_examples: 377365 - name: invalidated num_bytes: 2500259913.3079996 num_examples: 80612 - name: validated num_bytes: 9054232290.616999 num_examples: 267001 download_size: 25679221842 dataset_size: 25734852395.552998 - config_name: ta features: - name: client_id dtype: string - name: path dtype: string - name: audio dtype: audio: sampling_rate: 48000 - name: sentence dtype: string - name: up_votes dtype: int64 - name: down_votes dtype: int64 - name: age dtype: string - name: gender dtype: string - name: accent dtype: string - name: locale dtype: string - name: segment dtype: string - name: variant dtype: string - name: continuation dtype: string splits: - name: train num_bytes: 1787645589.3039997 num_examples: 45587 - name: validation num_bytes: 411960865.99 num_examples: 12095 - name: test num_bytes: 478673592.114 num_examples: 12074 - name: other num_bytes: 3643795189.905 num_examples: 93989 - name: invalidated num_bytes: 230273211.249 num_examples: 5693 - name: validated num_bytes: 5422820571.824 num_examples: 135391 download_size: 11548448217 dataset_size: 11975169020.386002 - config_name: te features: - name: client_id dtype: string - name: path dtype: string - name: audio dtype: audio: sampling_rate: 48000 - name: sentence dtype: string - name: up_votes dtype: int64 - name: down_votes dtype: int64 - name: age dtype: string - name: gender dtype: string - name: accent dtype: string - name: locale dtype: string - name: segment dtype: string - name: variant dtype: string - name: continuation dtype: string splits: - name: train num_bytes: 1696115.0 num_examples: 62 - name: validation num_bytes: 1381471.0 num_examples: 48 - name: test num_bytes: 1293519.0 num_examples: 49 - name: other num_bytes: 43324939.612 num_examples: 1732 - name: invalidated num_bytes: 441556.0 num_examples: 18 - name: validated num_bytes: 6161936.0 num_examples: 224 download_size: 54489346 dataset_size: 54299536.612 - config_name: th features: - name: client_id dtype: string - name: path dtype: string - name: audio dtype: audio: sampling_rate: 48000 - name: sentence dtype: string - name: up_votes dtype: int64 - name: down_votes dtype: int64 - name: age dtype: string - name: gender dtype: string - name: accent dtype: string - name: locale dtype: string - name: segment dtype: string - name: variant dtype: string - name: continuation dtype: string splits: - name: train num_bytes: 865414649.837 num_examples: 32823 - name: validation num_bytes: 328919810.63 num_examples: 11042 - name: test num_bytes: 337683048.872 num_examples: 11042 - name: other num_bytes: 5266135437.405999 num_examples: 206935 - name: invalidated num_bytes: 332435894.647 num_examples: 9267 - name: validated num_bytes: 4151072931.0839996 num_examples: 147160 download_size: 10608529487 dataset_size: 11281661772.476 - config_name: tr features: - name: client_id dtype: string - name: path dtype: string - name: audio dtype: audio: sampling_rate: 48000 - name: sentence dtype: string - name: up_votes dtype: int64 - name: down_votes dtype: int64 - name: age dtype: string - name: gender dtype: string - name: accent dtype: string - name: locale dtype: string - name: segment dtype: string - name: variant dtype: string - name: continuation dtype: string splits: - name: train num_bytes: 854586956.976 num_examples: 35147 - name: validation num_bytes: 265450510.268 num_examples: 11258 - name: test num_bytes: 363424742.28 num_examples: 11290 - name: other num_bytes: 4238883.0 num_examples: 117 - name: invalidated num_bytes: 152949072.07 num_examples: 4530 - name: validated num_bytes: 2694662410.926 num_examples: 114056 download_size: 4038924157 dataset_size: 4335312575.5199995 - config_name: uk features: - name: client_id dtype: string - name: path dtype: string - name: audio dtype: audio: sampling_rate: 48000 - name: sentence dtype: string - name: up_votes dtype: int64 - name: down_votes dtype: int64 - name: age dtype: string - name: gender dtype: string - name: accent dtype: string - name: locale dtype: string - name: segment dtype: string - name: variant dtype: string - name: continuation dtype: string splits: - name: train num_bytes: 824014245.552 num_examples: 25137 - name: validation num_bytes: 338351263.068 num_examples: 10007 - name: test num_bytes: 363575667.839 num_examples: 10011 - name: other num_bytes: 211123163.846 num_examples: 7851 - name: invalidated num_bytes: 141986802.304 num_examples: 3204 - name: validated num_bytes: 2579348540.4549994 num_examples: 75489 download_size: 4037277320 dataset_size: 4458399683.063999 - config_name: ur features: - name: client_id dtype: string - name: path dtype: string - name: audio dtype: audio: sampling_rate: 48000 - name: sentence dtype: string - name: up_votes dtype: int64 - name: down_votes dtype: int64 - name: age dtype: string - name: gender dtype: string - name: accent dtype: string - name: locale dtype: string - name: segment dtype: string - name: variant dtype: string - name: continuation dtype: string splits: - name: train num_bytes: 133627299.408 num_examples: 5368 - name: validation num_bytes: 98509203.154 num_examples: 4057 - name: test num_bytes: 117242341.632 num_examples: 4056 - name: other num_bytes: 3630451215.8669996 num_examples: 135861 - name: invalidated num_bytes: 197321142.268 num_examples: 6818 - name: validated num_bytes: 1353163990.006 num_examples: 53858 download_size: 5354414559 dataset_size: 5530315192.335001 - config_name: vi features: - name: client_id dtype: string - name: path dtype: string - name: audio dtype: audio: sampling_rate: 48000 - name: sentence dtype: string - name: up_votes dtype: int64 - name: down_votes dtype: int64 - name: age dtype: string - name: gender dtype: string - name: accent dtype: string - name: locale dtype: string - name: segment dtype: string - name: variant dtype: string - name: continuation dtype: string splits: - name: train num_bytes: 76589078.04 num_examples: 2298 - name: validation num_bytes: 14388627.0 num_examples: 641 - name: test num_bytes: 34782072.802 num_examples: 1274 - name: other num_bytes: 329412205.64 num_examples: 11533 - name: invalidated num_bytes: 11291189.0 num_examples: 377 - name: validated num_bytes: 139846021.79 num_examples: 5135 download_size: 519996701 dataset_size: 606309194.272 configs: - config_name: ar data_files: - split: validation path: ar/validation-* - split: test path: ar/test-* - split: train path: ar/train-* - config_name: ast data_files: - split: train path: ast/train/** - split: validation path: ast/validation/** - split: test path: ast/test/** - split: other path: ast/other/** - split: invalidated path: ast/invalidated/** - split: validated path: ast/validated/** - config_name: be data_files: - split: train path: be/train/** - split: validation path: be/validation/** - split: test path: be/test/** - config_name: bg data_files: - split: train path: bg/train/** - split: validation path: bg/validation/** - split: test path: bg/test/** - split: other path: bg/other/** - split: invalidated path: bg/invalidated/** - split: validated path: bg/validated/** - config_name: br data_files: - split: train path: br/train/** - split: validation path: br/validation/** - split: test path: br/test/** - split: other path: br/other/** - split: invalidated path: br/invalidated/** - split: validated path: br/validated/** - config_name: cs data_files: - split: train path: cs/train/** - split: validation path: cs/validation/** - split: test path: cs/test/** - split: other path: cs/other/** - split: invalidated path: cs/invalidated/** - split: validated path: cs/validated/** - config_name: cy data_files: - split: train path: cy/train/** - split: validation path: cy/validation/** - split: test path: cy/test/** - split: other path: cy/other/** - split: invalidated path: cy/invalidated/** - split: validated path: cy/validated/** - config_name: da data_files: - split: train path: da/train/** - split: validation path: da/validation/** - split: test path: da/test/** - split: other path: da/other/** - split: invalidated path: da/invalidated/** - split: validated path: da/validated/** - config_name: de data_files: - split: validation path: de/validation-* - split: test path: de/test-* - split: train path: de/train-* - config_name: el data_files: - split: train path: el/train/** - split: validation path: el/validation/** - split: test path: el/test/** - split: other path: el/other/** - split: invalidated path: el/invalidated/** - split: validated path: el/validated/** - config_name: en data_files: - split: test path: en/test-* - split: validation path: en/validation-* - split: train path: en/train-* - split: validated path: en/validated-* - config_name: es data_files: - split: validation path: es/validation-* - split: test path: es/test-* - split: train path: es/train-* - config_name: et data_files: - split: train path: et/train/** - split: validation path: et/validation/** - split: test path: et/test/** - split: other path: et/other/** - split: invalidated path: et/invalidated/** - split: validated path: et/validated/** - config_name: fa data_files: - split: train path: fa/train/** - split: validation path: fa/validation/** - split: test path: fa/test/** - split: other path: fa/other/** - split: invalidated path: fa/invalidated/** - split: validated path: fa/validated/** - config_name: fi data_files: - split: train path: fi/train/** - split: validation path: fi/validation/** - split: test path: fi/test/** - split: other path: fi/other/** - split: invalidated path: fi/invalidated/** - split: validated path: fi/validated/** - config_name: fr data_files: - split: validation path: fr/validation-* - split: train path: frnew/train-* - split: test path: fr/test-* - config_name: frold data_files: - split: train path: fr/train-* - split: test path: fr/test-* - split: validation path: fr/validation-* - config_name: gl data_files: - split: train path: gl/train/** - split: validation path: gl/validation/** - split: test path: gl/test/** - split: other path: gl/other/** - split: invalidated path: gl/invalidated/** - split: validated path: gl/validated/** - config_name: ha data_files: - split: train path: ha/train/** - split: validation path: ha/validation/** - split: test path: ha/test/** - config_name: hi data_files: - split: train path: hi/train/** - split: validation path: hi/validation/** - split: test path: hi/test/** - split: other path: hi/other/** - split: invalidated path: hi/invalidated/** - split: validated path: hi/validated/** - config_name: hu data_files: - split: train path: hu/train/** - split: validation path: hu/validation/** - split: test path: hu/test/** - split: other path: hu/other/** - split: invalidated path: hu/invalidated/** - split: validated path: hu/validated/** - config_name: it data_files: - split: validation path: it/validation-* - split: test path: it/test-* - split: train path: it/train-* - config_name: ja data_files: - split: validation path: ja/validation-* - split: test path: ja/test-* - split: train path: ja/train-* - config_name: ka data_files: - split: train path: ka/train/** - split: validation path: ka/validation/** - split: test path: ka/test/** - split: other path: ka/other/** - split: invalidated path: ka/invalidated/** - split: validated path: ka/validated/** - config_name: ko data_files: - split: train path: ko/train/** - split: validation path: ko/validation/** - split: test path: ko/test/** - split: other path: ko/other/** - split: invalidated path: ko/invalidated/** - split: validated path: ko/validated/** - config_name: lt data_files: - split: train path: lt/train/** - split: validation path: lt/validation/** - split: test path: lt/test/** - split: other path: lt/other/** - split: invalidated path: lt/invalidated/** - split: validated path: lt/validated/** - config_name: lv data_files: - split: train path: lv/train/** - split: validation path: lv/validation/** - split: test path: lv/test/** - split: other path: lv/other/** - split: invalidated path: lv/invalidated/** - split: validated path: lv/validated/** - config_name: mk data_files: - split: train path: mk/train/** - split: validation path: mk/validation/** - split: test path: mk/test/** - split: other path: mk/other/** - split: invalidated path: mk/invalidated/** - split: validated path: mk/validated/** - config_name: ml data_files: - split: train path: ml/train/** - split: validation path: ml/validation/** - split: test path: ml/test/** - split: other path: ml/other/** - split: invalidated path: ml/invalidated/** - split: validated path: ml/validated/** - config_name: mn data_files: - split: train path: mn/train/** - split: validation path: mn/validation/** - split: test path: mn/test/** - split: other path: mn/other/** - split: invalidated path: mn/invalidated/** - split: validated path: mn/validated/** - config_name: mr data_files: - split: train path: mr/train/** - split: validation path: mr/validation/** - split: test path: mr/test/** - split: other path: mr/other/** - split: invalidated path: mr/invalidated/** - split: validated path: mr/validated/** - config_name: nl data_files: - split: train path: nl/train/** - split: validation path: nl/validation/** - split: test path: nl/test/** - split: other path: nl/other/** - split: invalidated path: nl/invalidated/** - split: validated path: nl/validated/** - config_name: oc data_files: - split: train path: oc/train/** - split: validation path: oc/validation/** - split: test path: oc/test/** - split: other path: oc/other/** - split: invalidated path: oc/invalidated/** - split: validated path: oc/validated/** - config_name: pl data_files: - split: train path: pl/train/** - split: validation path: pl/validation/** - split: test path: pl/test/** - split: other path: pl/other/** - split: invalidated path: pl/invalidated/** - split: validated path: pl/validated/** - config_name: pt data_files: - split: validation path: pt/validation-* - split: test path: pt/test-* - split: train path: pt/train-* - config_name: ro data_files: - split: train path: ro/train/** - split: validation path: ro/validation/** - split: test path: ro/test/** - split: other path: ro/other/** - split: invalidated path: ro/invalidated/** - split: validated path: ro/validated/** - config_name: ru data_files: - split: validation path: ru/validation-* - split: test path: ru/test-* - split: train path: ru/train-* - config_name: sk data_files: - split: train path: sk/train/** - split: validation path: sk/validation/** - split: test path: sk/test/** - split: other path: sk/other/** - split: invalidated path: sk/invalidated/** - split: validated path: sk/validated/** - config_name: sl data_files: - split: train path: sl/train/** - split: validation path: sl/validation/** - split: test path: sl/test/** - split: other path: sl/other/** - split: invalidated path: sl/invalidated/** - split: validated path: sl/validated/** - config_name: sr data_files: - split: train path: sr/train/** - split: validation path: sr/validation/** - split: test path: sr/test/** - split: other path: sr/other/** - split: invalidated path: sr/invalidated/** - split: validated path: sr/validated/** - config_name: sv-SE data_files: - split: train path: sv-SE/train/** - split: validation path: sv-SE/validation/** - split: test path: sv-SE/test/** - split: other path: sv-SE/other/** - split: invalidated path: sv-SE/invalidated/** - split: validated path: sv-SE/validated/** - config_name: sw data_files: - split: train path: sw/train/** - split: validation path: sw/validation/** - split: test path: sw/test/** - split: other path: sw/other/** - split: invalidated path: sw/invalidated/** - split: validated path: sw/validated/** - config_name: ta data_files: - split: train path: ta/train/** - split: validation path: ta/validation/** - split: test path: ta/test/** - split: other path: ta/other/** - split: invalidated path: ta/invalidated/** - split: validated path: ta/validated/** - config_name: te data_files: - split: train path: te/train/** - split: validation path: te/validation/** - split: test path: te/test/** - split: other path: te/other/** - split: invalidated path: te/invalidated/** - split: validated path: te/validated/** - config_name: th data_files: - split: train path: th/train/** - split: validation path: th/validation/** - split: test path: th/test/** - split: other path: th/other/** - split: invalidated path: th/invalidated/** - split: validated path: th/validated/** - config_name: tr data_files: - split: train path: tr/train/** - split: validation path: tr/validation/** - split: test path: tr/test/** - split: other path: tr/other/** - split: invalidated path: tr/invalidated/** - split: validated path: tr/validated/** - config_name: uk data_files: - split: train path: uk/train/** - split: validation path: uk/validation/** - split: test path: uk/test/** - split: other path: uk/other/** - split: invalidated path: uk/invalidated/** - split: validated path: uk/validated/** - config_name: ur data_files: - split: train path: ur/train/** - split: validation path: ur/validation/** - split: test path: ur/test/** - split: other path: ur/other/** - split: invalidated path: ur/invalidated/** - split: validated path: ur/validated/** - config_name: vi data_files: - split: train path: vi/train/** - split: validation path: vi/validation/** - split: test path: vi/test/** - split: other path: vi/other/** - split: invalidated path: vi/invalidated/** - split: validated path: vi/validated/** ---

allenai/sciq

allenai

--- annotations_creators: - no-annotation language_creators: - crowdsourced language: - en license: - cc-by-nc-3.0 multilinguality: - monolingual size_categories: - 10K<n<100K source_datasets: - original task_categories: - question-answering task_ids: - closed-domain-qa paperswithcode_id: sciq pretty_name: SciQ dataset_info: features: - name: question dtype: string - name: distractor3 dtype: string - name: distractor1 dtype: string - name: distractor2 dtype: string - name: correct_answer dtype: string - name: support dtype: string splits: - name: train num_bytes: 6546183 num_examples: 11679 - name: validation num_bytes: 554120 num_examples: 1000 - name: test num_bytes: 563927 num_examples: 1000 download_size: 4674410 dataset_size: 7664230 configs: - config_name: default data_files: - split: train path: data/train-* - split: validation path: data/validation-* - split: test path: data/test-* --- # Dataset Card for "sciq" ## Table of Contents - [Dataset Description](#dataset-description) - [Dataset Summary](#dataset-summary) - [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards) - [Languages](#languages) - [Dataset Structure](#dataset-structure) - [Data Instances](#data-instances) - [Data Fields](#data-fields) - [Data Splits](#data-splits) - [Dataset Creation](#dataset-creation) - [Curation Rationale](#curation-rationale) - [Source Data](#source-data) - [Annotations](#annotations) - [Personal and Sensitive Information](#personal-and-sensitive-information) - [Considerations for Using the Data](#considerations-for-using-the-data) - [Social Impact of Dataset](#social-impact-of-dataset) - [Discussion of Biases](#discussion-of-biases) - [Other Known Limitations](#other-known-limitations) - [Additional Information](#additional-information) - [Dataset Curators](#dataset-curators) - [Licensing Information](#licensing-information) - [Citation Information](#citation-information) - [Contributions](#contributions) ## Dataset Description - **Homepage:** [https://allenai.org/data/sciq](https://allenai.org/data/sciq) - **Repository:** [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) - **Paper:** [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) - **Point of Contact:** [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) - **Size of downloaded dataset files:** 2.82 MB - **Size of the generated dataset:** 7.68 MB - **Total amount of disk used:** 10.50 MB ### Dataset Summary The SciQ dataset contains 13,679 crowdsourced science exam questions about Physics, Chemistry and Biology, among others. The questions are in multiple-choice format with 4 answer options each. For the majority of the questions, an additional paragraph with supporting evidence for the correct answer is provided. ### Supported Tasks and Leaderboards [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Languages [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ## Dataset Structure ### Data Instances #### default - **Size of downloaded dataset files:** 2.82 MB - **Size of the generated dataset:** 7.68 MB - **Total amount of disk used:** 10.50 MB An example of 'train' looks as follows. ``` This example was too long and was cropped: { "correct_answer": "coriolis effect", "distractor1": "muon effect", "distractor2": "centrifugal effect", "distractor3": "tropical effect", "question": "What phenomenon makes global winds blow northeast to southwest or the reverse in the northern hemisphere and northwest to southeast or the reverse in the southern hemisphere?", "support": "\"Without Coriolis Effect the global winds would blow north to south or south to north. But Coriolis makes them blow northeast to..." } ``` ### Data Fields The data fields are the same among all splits. #### default - `question`: a `string` feature. - `distractor3`: a `string` feature. - `distractor1`: a `string` feature. - `distractor2`: a `string` feature. - `correct_answer`: a `string` feature. - `support`: a `string` feature. ### Data Splits | name |train|validation|test| |-------|----:|---------:|---:| |default|11679| 1000|1000| ## Dataset Creation ### Curation Rationale [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Source Data #### Initial Data Collection and Normalization [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) #### Who are the source language producers? [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Annotations #### Annotation process [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) #### Who are the annotators? [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Personal and Sensitive Information [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ## Considerations for Using the Data ### Social Impact of Dataset [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Discussion of Biases [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Other Known Limitations [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ## Additional Information ### Dataset Curators [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Licensing Information The dataset is licensed under the [Creative Commons Attribution-NonCommercial 3.0 Unported License](http://creativecommons.org/licenses/by-nc/3.0/). ### Citation Information ``` @inproceedings{SciQ, title={Crowdsourcing Multiple Choice Science Questions}, author={Johannes Welbl, Nelson F. Liu, Matt Gardner}, year={2017}, journal={arXiv:1707.06209v1} } ``` ### Contributions Thanks to [@patrickvonplaten](https://github.com/patrickvonplaten), [@lewtun](https://github.com/lewtun), [@thomwolf](https://github.com/thomwolf) for adding this dataset.

mteb/biosses-sts

mteb

--- language: - en ---

HuggingFaceFW/fineweb-edu-score-2

HuggingFaceFW

--- license: odc-by task_categories: - text-generation language: - en pretty_name: FineWeb-Edu (score >= 2) size_categories: - n>1T configs: - config_name: default features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: date dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 data_files: - split: train path: data/*/* - config_name: CC-MAIN-2024-51 data_files: - split: train path: data/CC-MAIN-2024-51/* - config_name: CC-MAIN-2024-46 data_files: - split: train path: data/CC-MAIN-2024-46/* - config_name: CC-MAIN-2024-42 data_files: - split: train path: data/CC-MAIN-2024-42/* - config_name: CC-MAIN-2024-38 data_files: - split: train path: data/CC-MAIN-2024-38/* - config_name: CC-MAIN-2024-33 data_files: - split: train path: data/CC-MAIN-2024-33/* - config_name: CC-MAIN-2024-30 data_files: - split: train path: data/CC-MAIN-2024-30/* - config_name: CC-MAIN-2024-26 data_files: - split: train path: data/CC-MAIN-2024-26/* - config_name: CC-MAIN-2024-22 data_files: - split: train path: data/CC-MAIN-2024-22/* - config_name: CC-MAIN-2024-18 data_files: - split: train path: data/CC-MAIN-2024-18/* - config_name: CC-MAIN-2024-10 data_files: - split: train path: data/CC-MAIN-2024-10/* - config_name: CC-MAIN-2023-50 data_files: - split: train path: data/CC-MAIN-2023-50/* - config_name: CC-MAIN-2023-40 data_files: - split: train path: data/CC-MAIN-2023-40/* - config_name: CC-MAIN-2023-23 data_files: - split: train path: data/CC-MAIN-2023-23/* - config_name: CC-MAIN-2023-14 data_files: - split: train path: data/CC-MAIN-2023-14/* - config_name: CC-MAIN-2023-06 data_files: - split: train path: data/CC-MAIN-2023-06/* - config_name: CC-MAIN-2022-49 data_files: - split: train path: data/CC-MAIN-2022-49/* - config_name: CC-MAIN-2022-40 data_files: - split: train path: data/CC-MAIN-2022-40/* - config_name: CC-MAIN-2022-33 data_files: - split: train path: data/CC-MAIN-2022-33/* - config_name: CC-MAIN-2022-27 data_files: - split: train path: data/CC-MAIN-2022-27/* - config_name: CC-MAIN-2022-21 data_files: - split: train path: data/CC-MAIN-2022-21/* - config_name: CC-MAIN-2022-05 data_files: - split: train path: data/CC-MAIN-2022-05/* - config_name: CC-MAIN-2021-49 data_files: - split: train path: data/CC-MAIN-2021-49/* - config_name: CC-MAIN-2021-43 data_files: - split: train path: data/CC-MAIN-2021-43/* - config_name: CC-MAIN-2021-39 data_files: - split: train path: data/CC-MAIN-2021-39/* - config_name: CC-MAIN-2021-31 data_files: - split: train path: data/CC-MAIN-2021-31/* - config_name: CC-MAIN-2021-25 data_files: - split: train path: data/CC-MAIN-2021-25/* - config_name: CC-MAIN-2021-21 data_files: - split: train path: data/CC-MAIN-2021-21/* - config_name: CC-MAIN-2021-17 data_files: - split: train path: data/CC-MAIN-2021-17/* - config_name: CC-MAIN-2021-10 data_files: - split: train path: data/CC-MAIN-2021-10/* - config_name: CC-MAIN-2021-04 data_files: - split: train path: data/CC-MAIN-2021-04/* - config_name: CC-MAIN-2020-50 data_files: - split: train path: data/CC-MAIN-2020-50/* - config_name: CC-MAIN-2020-45 data_files: - split: train path: data/CC-MAIN-2020-45/* - config_name: CC-MAIN-2020-40 data_files: - split: train path: data/CC-MAIN-2020-40/* - config_name: CC-MAIN-2020-34 data_files: - split: train path: data/CC-MAIN-2020-34/* - config_name: CC-MAIN-2020-29 data_files: - split: train path: data/CC-MAIN-2020-29/* - config_name: CC-MAIN-2020-24 data_files: - split: train path: data/CC-MAIN-2020-24/* - config_name: CC-MAIN-2020-16 data_files: - split: train path: data/CC-MAIN-2020-16/* - config_name: CC-MAIN-2020-10 data_files: - split: train path: data/CC-MAIN-2020-10/* - config_name: CC-MAIN-2020-05 data_files: - split: train path: data/CC-MAIN-2020-05/* - config_name: CC-MAIN-2019-51 data_files: - split: train path: data/CC-MAIN-2019-51/* - config_name: CC-MAIN-2019-47 data_files: - split: train path: data/CC-MAIN-2019-47/* - config_name: CC-MAIN-2019-43 data_files: - split: train path: data/CC-MAIN-2019-43/* - config_name: CC-MAIN-2019-39 data_files: - split: train path: data/CC-MAIN-2019-39/* - config_name: CC-MAIN-2019-35 data_files: - split: train path: data/CC-MAIN-2019-35/* - config_name: CC-MAIN-2019-30 data_files: - split: train path: data/CC-MAIN-2019-30/* - config_name: CC-MAIN-2019-26 data_files: - split: train path: data/CC-MAIN-2019-26/* - config_name: CC-MAIN-2019-22 data_files: - split: train path: data/CC-MAIN-2019-22/* - config_name: CC-MAIN-2019-18 data_files: - split: train path: data/CC-MAIN-2019-18/* - config_name: CC-MAIN-2019-13 data_files: - split: train path: data/CC-MAIN-2019-13/* - config_name: CC-MAIN-2019-09 data_files: - split: train path: data/CC-MAIN-2019-09/* - config_name: CC-MAIN-2019-04 data_files: - split: train path: data/CC-MAIN-2019-04/* - config_name: CC-MAIN-2018-51 data_files: - split: train path: data/CC-MAIN-2018-51/* - config_name: CC-MAIN-2018-47 data_files: - split: train path: data/CC-MAIN-2018-47/* - config_name: CC-MAIN-2018-43 data_files: - split: train path: data/CC-MAIN-2018-43/* - config_name: CC-MAIN-2018-39 data_files: - split: train path: data/CC-MAIN-2018-39/* - config_name: CC-MAIN-2018-34 data_files: - split: train path: data/CC-MAIN-2018-34/* - config_name: CC-MAIN-2018-30 data_files: - split: train path: data/CC-MAIN-2018-30/* - config_name: CC-MAIN-2018-26 data_files: - split: train path: data/CC-MAIN-2018-26/* - config_name: CC-MAIN-2018-22 data_files: - split: train path: data/CC-MAIN-2018-22/* - config_name: CC-MAIN-2018-17 data_files: - split: train path: data/CC-MAIN-2018-17/* - config_name: CC-MAIN-2018-13 data_files: - split: train path: data/CC-MAIN-2018-13/* - config_name: CC-MAIN-2018-09 data_files: - split: train path: data/CC-MAIN-2018-09/* - config_name: CC-MAIN-2018-05 data_files: - split: train path: data/CC-MAIN-2018-05/* - config_name: CC-MAIN-2017-51 data_files: - split: train path: data/CC-MAIN-2017-51/* - config_name: CC-MAIN-2017-47 data_files: - split: train path: data/CC-MAIN-2017-47/* - config_name: CC-MAIN-2017-43 data_files: - split: train path: data/CC-MAIN-2017-43/* - config_name: CC-MAIN-2017-39 data_files: - split: train path: data/CC-MAIN-2017-39/* - config_name: CC-MAIN-2017-34 data_files: - split: train path: data/CC-MAIN-2017-34/* - config_name: CC-MAIN-2017-30 data_files: - split: train path: data/CC-MAIN-2017-30/* - config_name: CC-MAIN-2017-26 data_files: - split: train path: data/CC-MAIN-2017-26/* - config_name: CC-MAIN-2017-22 data_files: - split: train path: data/CC-MAIN-2017-22/* - config_name: CC-MAIN-2017-17 data_files: - split: train path: data/CC-MAIN-2017-17/* - config_name: CC-MAIN-2017-13 data_files: - split: train path: data/CC-MAIN-2017-13/* - config_name: CC-MAIN-2017-09 data_files: - split: train path: data/CC-MAIN-2017-09/* - config_name: CC-MAIN-2017-04 data_files: - split: train path: data/CC-MAIN-2017-04/* - config_name: CC-MAIN-2016-50 data_files: - split: train path: data/CC-MAIN-2016-50/* - config_name: CC-MAIN-2016-44 data_files: - split: train path: data/CC-MAIN-2016-44/* - config_name: CC-MAIN-2016-40 data_files: - split: train path: data/CC-MAIN-2016-40/* - config_name: CC-MAIN-2016-36 data_files: - split: train path: data/CC-MAIN-2016-36/* - config_name: CC-MAIN-2016-30 data_files: - split: train path: data/CC-MAIN-2016-30/* - config_name: CC-MAIN-2016-26 data_files: - split: train path: data/CC-MAIN-2016-26/* - config_name: CC-MAIN-2016-22 data_files: - split: train path: data/CC-MAIN-2016-22/* - config_name: CC-MAIN-2016-18 data_files: - split: train path: data/CC-MAIN-2016-18/* - config_name: CC-MAIN-2016-07 data_files: - split: train path: data/CC-MAIN-2016-07/* - config_name: CC-MAIN-2015-48 data_files: - split: train path: data/CC-MAIN-2015-48/* - config_name: CC-MAIN-2015-40 data_files: - split: train path: data/CC-MAIN-2015-40/* - config_name: CC-MAIN-2015-35 data_files: - split: train path: data/CC-MAIN-2015-35/* - config_name: CC-MAIN-2015-32 data_files: - split: train path: data/CC-MAIN-2015-32/* - config_name: CC-MAIN-2015-27 data_files: - split: train path: data/CC-MAIN-2015-27/* - config_name: CC-MAIN-2015-22 data_files: - split: train path: data/CC-MAIN-2015-22/* - config_name: CC-MAIN-2015-18 data_files: - split: train path: data/CC-MAIN-2015-18/* - config_name: CC-MAIN-2015-14 data_files: - split: train path: data/CC-MAIN-2015-14/* - config_name: CC-MAIN-2015-11 data_files: - split: train path: data/CC-MAIN-2015-11/* - config_name: CC-MAIN-2015-06 data_files: - split: train path: data/CC-MAIN-2015-06/* - config_name: CC-MAIN-2014-52 data_files: - split: train path: data/CC-MAIN-2014-52/* - config_name: CC-MAIN-2014-49 data_files: - split: train path: data/CC-MAIN-2014-49/* - config_name: CC-MAIN-2014-42 data_files: - split: train path: data/CC-MAIN-2014-42/* - config_name: CC-MAIN-2014-41 data_files: - split: train path: data/CC-MAIN-2014-41/* - config_name: CC-MAIN-2014-35 data_files: - split: train path: data/CC-MAIN-2014-35/* - config_name: CC-MAIN-2014-23 data_files: - split: train path: data/CC-MAIN-2014-23/* - config_name: CC-MAIN-2014-15 data_files: - split: train path: data/CC-MAIN-2014-15/* - config_name: CC-MAIN-2014-10 data_files: - split: train path: data/CC-MAIN-2014-10/* - config_name: CC-MAIN-2013-48 data_files: - split: train path: data/CC-MAIN-2013-48/* - config_name: CC-MAIN-2013-20 data_files: - split: train path: data/CC-MAIN-2013-20/* --- # 📚 FineWeb-Edu-score-2 <center> <img src="https://cdn-uploads.huggingface.co/production/uploads/61c141342aac764ce1654e43/wwRnEQydH9qdRtFofIE-A.png" alt="FineWeb-Edu: The finest collection of educational content the web has to offer"> </center> > 1.3 trillion tokens of the finest educational data the 🌐 web has to offer ## What is it? 📚 FineWeb-Edu dataset consists of **1.3T tokens** ([FineWeb-Edu](https://huggingface.co./datasets/HuggingFaceFW/fineweb-edu)) and **5.4T tokens** of educational web pages filtered from 🍷 FineWeb dataset. This is the 5.4 trillion version. ### Note: this version uses a lower educational score threshold = 2, which results in more documents, but lower quality compared to the 1.3T version. For more details check the FineWeb [blog post](https://huggingface.co./spaces/HuggingFaceFW/blogpost-fineweb-v1). To enhance FineWeb's quality, we developed an [educational quality classifier](https://huggingface.co./HuggingFaceFW/fineweb-edu-classifier) using annotations generated by LLama3-70B-Instruct. We then used this classifier to retain only the most educational web pages. FineWeb-Edu outperforms FineWeb on popular benchmarks and shows the power of classifiers trained on synthetic data. The [Dataset Curation](https://huggingface.co./datasets/HuggingFaceFW/fineweb-edu#dataset-curation) section details the process for creating the dataset.  ## What is being released? Along with the dataset, which includes all filtered CommonCrawl dumps since 2013, we also release the educational classifier used for the filtering as well as the code for training it and running inference at: https://github.com/huggingface/cosmopedia/tree/main/classification. ## Changelog _Previous versions remain available in the branch `version name`._ - **v1.2.0 (03-01-2024):** Added 9 new snapshots: `CC-MAIN-2024-18`, `CC-MAIN-2024-22`, `CC-MAIN-2024-26`, `CC-MAIN-2024-30`, `CC-MAIN-2024-33`, `CC-MAIN-2024-38`, `CC-MAIN-2024-42`, `CC-MAIN-2024-46`, `CC-MAIN-2024-51`, covering April to December 2024. - **v1.0.0 (02-06-2024):** Initial version ## How to load the dataset Similarily to FineWeb, You can load the full dataset or a specific crawl/dump. Dumps have the format `CC-MAIN-(year)-(week number)`. ### Using 🏭 [`datatrove`](https://github.com/huggingface/datatrove/) ```python from datatrove.pipeline.readers import ParquetReader # limit determines how many documents will be streamed (remove for all) data_reader = ParquetReader("hf://datasets/HuggingFaceFW/fineweb-edu-score-2", glob_pattern="data/*/*.parquet", limit=1000) data_reader = ParquetReader("hf://datasets/HuggingFaceFW/fineweb-edu-score-2/CC-MAIN-2024-10", limit=1000) for document in data_reader(): # do something with document print(document) ############################### # OR for a processing pipeline: ############################### from datatrove.executor import LocalPipelineExecutor from datatrove.pipeline.readers import ParquetReader from datatrove.pipeline.filters import LambdaFilter from datatrove.pipeline.writers import JsonlWriter pipeline_exec = LocalPipelineExecutor( pipeline=[ ParquetReader("hf://datasets/HuggingFaceFW/fineweb-edu-score-2/CC-MAIN-2024-10", limit=1000), LambdaFilter(lambda doc: "hugging" in doc.text), JsonlWriter("some-output-path") ], tasks=10 ) pipeline_exec.run() ``` ### Using `datasets` ```python from datasets import load_dataset fw = load_dataset("HuggingFaceFW/fineweb-edu-score-2", name="CC-MAIN-2024-10", split="train", streaming=True) ``` ## Dataset curation A new approach has recently emerged for filtering LLM training datasets: using synthetic data to develop classifiers for identifying educational content. This technique was used in the trainings of [LLama3](https://ai.meta.com/blog/meta-llama-3-meta-ai-responsibility/), [Claude3](https://www-cdn.anthropic.com/de8ba9b01c9ab7cbabf5c33b80b7bbc618857627/Model_Card_Claude_3.pdf) and [Phi3](https://arxiv.org/abs/2404.14219), but its large-scale impact on web data filtering hasn't been fully explored or published. The highly popular Phi3 models were trained on 3.3 and 4.8 trillion tokens, with the paper stating: “Our training data consists of heavily filtered publicly available web data (according to the 'educational level') from various open internet sources, as well as synthetic LLM-generated data". Similarly, the LLama3 blog post notes: “We found that previous generations of Llama are good at identifying high-quality data, so we used Llama 2 to help build the text-quality classifiers that are powering Llama 3.” However these classifiers and filtered datasets are not publicly available. To enhance FineWeb's quality, we developed an educational quality classifier using annotations generated by [LLama3-70B-Instruct](https://huggingface.co./meta-llama/Meta-Llama-3-70B-Instruct) to create FineWeb-Edu. ### Annotation We used [Llama3-70B-Instruct](https://huggingface.co./meta-llama/Meta-Llama-3-70B-Instruct) to score 500k FineWeb samples for their educational quality on a scale from 0 to 5. We explored various prompts and found that the additive scale by [Yuan et al.](https://arxiv.org/pdf/2401.10020) worked best. To avoid the LLM favoring highly technical pages like arXiv abstracts and submissions, we focused on grade-school and middle-school level knowledge. By setting a threshold of 3 (on a scale of 0 to 5) during the filtering process, we were able to also retain some high-level educational pages. The final prompt can be found in this blog post TODO. We also experimented with different LLMs: Llama3-70B-Instruct, Mixtral-8x-7B-Instruct, and Mixtral-8x22B-Instruct. Llama3 and Mixtral-8x22B produced similar scores, while Mixtral-8x7B tended to be more generous, not fully adhering to the score scale. Verga et al. suggest using multiple LLMs as juries. We tried averaging the scores from the three models, but this shifted the distribution to the right due to the higher scores from Mixtral-8x7B. Training on a dataset filtered with a classifier using jury annotations performed worse than using a classifier based on Llama3 annotations. We hypothesize that the jury-based approach retains more low-quality samples. ### Classifier training We fine-tuned a Bert-like regression model using these annotations, based on [Snowflake-arctic-embed](https://huggingface.co./Snowflake/snowflake-arctic-embed-m). When converted to a binary classification using a score of 3 as a threshold for keeping and removing files, the model achieved an F1 score of 82%. The classification of FineWeb 15T tokens took 6k H100 GPU hours. The classifier is available at: [https://huggingface.co./HuggingFaceFW/fineweb-edu-classifier/ ](https://huggingface.co./HuggingFaceFW/fineweb-edu-classifier/) ### Filtering and results **Note**: You can find more details about the ablations and results in the FineWeb blog post (TODO). We investigated the impact of using different thresholds for the filtering and found that threshold 3 gave the best overall results. Although using a threshold higher than 3 improves performance on knowledge and reasoning intensive benchmarks, it significantly degrades performance on HellaSwag and PIQA. We then built 📚 FineWeb-Edu by filtering out samples with scores lower than 3. This removed 92% of the dataset, leaving us with 1.3T educational tokens. Our ablation demonstrated that this refined dataset surpasses 🍷 FineWeb and all other open web datasets, with remarkable improvements on educational benchmarks such as MMLU, ARC, and OpenBookQA. The plot below compares FineWeb-Edu to other web datasets:  To retain more tokens, we also experimented with a less strict threshold of 2 instead of 3. While being less performant than using threshold 3, it still outperformed FineWeb and it preserved 5.4T tokens. We release these two dataset as [FineWeb-Edu](https://huggingface.co./datasets/HuggingFaceFW/fineweb-edu) and [FineWeb-Edu-score-2](https://huggingface.co./datasets/HuggingFaceFW/fineweb-edu-score-2) along with the [classifier](https://huggingface.co./HuggingFaceFW/fineweb-edu-classifier). You will find all the ablation models in [this collection](https://huggingface.co./collections/HuggingFaceFW/ablation-models-662457b0d213e8c14fe47f32). The FineWeb-Edu ablation model (trained on 350B tokens) is available at [https://huggingface.co./HuggingFaceFW/ablation-model-fineweb-edu](https://huggingface.co./HuggingFaceFW/ablation-model-fineweb-edu). ## Considerations for Using the Data This section is copied from the parent dataset: [FineWeb](https://huggingface.co./datasets/HuggingFaceFW/fineweb). ### Social Impact of Dataset With the release of this dataset we aim to make model training more accessible to the machine learning community at large. While multiple open-weights models with strong performance have been publicly released in the past, more often than not these releases are not accompanied by the corresponding training dataset. This is unfortunate as the dataset specificities and characteristics have been demonstrated to have a very large impact and role in the performances of the models. As the creation of a high quality training dataset is a fundamental requirement to training an LLM capable of excelling at downstream tasks, with 🍷 FineWeb we (a) not only make the dataset creation process more transparent, by sharing our entire processing setup including the codebase used, we also (b) help alleviate the costs of dataset curation, both in time and in compute, for model creators by publicly releasing our dataset with the community. ### Discussion of Biases Efforts were made to minimize the amount of NSFW and toxic content present in the dataset by employing filtering on the URL level. However, there are still a significant number of documents present in the final dataset that could be considered toxic or contain harmful content. As 🍷 FineWeb was sourced from the web as a whole, any harmful biases typically present in it may be reproduced on our dataset. We deliberately avoided using machine learning filtering methods that define text quality based on the similarity to a “gold” source such as wikipedia or toxicity classifiers as these methods have been known to [disproportionately remove content in specific dialects](https://aclanthology.org/D16-1120/) and [overclassify as toxic text related to specific social identities](https://arxiv.org/pdf/2109.07445.pdf), respectively. ### Other Known Limitations As a consequence of some of the filtering steps applied, it is likely that code content is not prevalent in our dataset. If you are training a model that should also perform code tasks, we recommend you use 🍷 FineWeb with a code dataset, such as [The Stack v2](https://huggingface.co./datasets/bigcode/the-stack-v2). You should also probably consider complementing 🍷 FineWeb with specialized curated sources (such as Wikipedia, for example) as they will likely have better formatting than the wikipedia content included in 🍷 FineWeb (we did not tailor the processing to individual websites). ## Additional Information ### Licensing Information The dataset is released under the **Open Data Commons Attribution License (ODC-By) v1.0** [license](https://opendatacommons.org/licenses/by/1-0/). The use of this dataset is also subject to [CommonCrawl's Terms of Use](https://commoncrawl.org/terms-of-use). ### Future work We plan to work on better educational classifier to improve the quality of FineWeb-Edu. ### Citation Information ``` @software{lozhkov2024fineweb-edu, author = {Lozhkov, Anton and Ben Allal, Loubna and von Werra, Leandro and Wolf, Thomas}, title = {FineWeb-Edu}, month = May, year = 2024, url = {https://huggingface.co./datasets/HuggingFaceFW/fineweb-edu} } ```

PleIAs/common_corpus

PleIAs

--- language: - en - fr - de - it - pt - nl - es pretty_name: Common Corpus size_categories: - n>1T task_categories: - text-generation tags: - legal - finance - literature - science - code --- # Common Corpus Common Corpus is the largest open and permissible licensed text dataset, comprising over 2 trillion tokens (2,003,039,184,047 tokens). It is a diverse dataset, consisting of books, newspapers, scientific articles, government and legal documents, code, and more. Common Corpus differs from existing open datasets in that it is: * **Truly Open**: contains only data that is permissively licensed * **Multilingual**: mostly representing English and French data, but contains data for XX languages * **Diverse**: consisting of scientific articles, government and legal documents, code, and cultural heritage data, including books and newspapers * **Extensively Curated**: spelling and formatting has been corrected from digitized texts, harmful and toxic content has been removed, and content with low educational content has also been removed. # About Common Corpus Common Corpus is made of five carefully curated collections: * **OpenCulture**: our largest collection at 926,541,096,243 tokens, featuring public domain books, newspapers, and Wikisource content. We've developed innovative tools like OCROnos-Vintage to correct historical digitization errors, while implementing advanced toxicity filtering to ensure content meets modern ethical standards. * **OpenGovernment**: 387,965,738,992 tokens of financial and legal documents, including Finance Commons (from sources like SEC and WTO) and Legal Commons (including Europarl and Caselaw Access Project), providing enterprise-grade training data from regulatory bodies and administrative sources. * **OpenSource**: 334,658,896,533 tokens of high-quality code in open source from GitHub, filtered using ArmoRM to ensure only the top 80% of submissions by quality rating are included. * **OpenScience**: 221,798,136,564 tokens of academic content from Open Alex and other open science reposiories, processed using vision-language models to preserve crucial document structure and formatting. * **OpenWeb**: 132,075,315,715 tokens from Wikipedia (official releases from the [Wikimedia Foundation](https://huggingface.co./datasets/wikimedia/wikipedia) on Huggingface), YouTube Commons and other websites available under permissible licenses like Stack-Exchange. | Collection | Domain | Sources | |----------------|--------------------------|-------------------------------------------------------------------------------------------| | OpenGovernment | legal and administrative | [Finance Commons](https://huggingface.co./collections/PleIAs/finance-commons-66925e1095c7fa6e6828e26c) (e.g. SEC, WTO) and Legal Commons (e.g. Europarl, Caselaw Access Project) | | OpenCulture | cultural heritage | public domain books and newspapers, Wikisource | | OpenScience | academic | OpenAlex, French theses | | OpenWeb | web text | [YouTube Commons](https://huggingface.co./datasets/PleIAs/YouTube-Commons), Stack Exchange | | OpenSource | code | GitHub | We will accompany the dataset release with a comprehensive technical report detailing our methodologies and data sources will accompany the release, ensuring full transparency and reproducibility. We will release the individual sub-corpora in coming weeks for more fine-grained auditability for to expand uses ## Dataset Structure <details > <summary>Data Fields</summary> * identifier: unique text identifier * text: post-processed text * char_count: number of UTF-8 characters in text * file_name: original file path, organized by collection * set_id: set id (1-10) * subset_id: subset id (1-100) </details > <br /> # How to Use ## Considerations for Using the Data All data in Common Corpus are permissibly licensed and may be used for both commercial and non-commercial purposes. The dataset is multilingual. The language text is included in the metadata, so data can be filtered by language. Additionally, some of the text data are historical. The year each text is written is included in the metadata, therefore it is possible to construct a dataset with a custom date cutoff if desired. ### Discussion of Bias Some of the dataset sources contain biased and toxic content, such as stereotypes about certain minoritized groups. We have removed texts which had high toxicity scores according to our toxicity classifier, [Celadon](https://huggingface.co./PleIAs/celadon), or which contain offensive terms and slurs. See our [preprint](https://arxiv.org/pdf/2410.22587) for more details. ### Personal and Sensitive Information We have attempted to remove personally identifiable information (PII). We primarily use [Microsoft Presidio](https://microsoft.github.io/presidio/), but make additional modifications to account for language- and country-specific considerations, such as European phone number formats. ## Use Common Corpus ``` from datasets import load_dataset data = load_dataset('PleIAs/common_corpus') ``` # Acknowledgements The corpus was stored and processed with the generous support of the AI Alliance, Jean Zay (Eviden, Idris), Nvidia Inception program, Nebius AI, Tracto AI, Mozilla. It was built up with the support and concerted efforts of the state start-up LANGU:IA (start-up d’Etat), supported by the French Ministry of Culture and DINUM, as part of the prefiguration of the service offering of the Alliance for Language technologies EDIC (ALT-EDIC). This dataset was also made in partnership with Wikimedia Enterprise for the Wikipedia part. The collection of the corpus has been largely facilitated thanks to the open science LLM community insights, cooperation and support (Eleuther AI, Allen AI, HuggingFace…). <div style="text-align: center;"> <img src="https://huggingface.co./datasets/PleIAs/common_corpus/resolve/main/logo/ai_alliance.png" style="width: 33%; margin: 0 auto; display: inline-block;"/> <img src="https://huggingface.co./datasets/PleIAs/common_corpus/resolve/main/logo/logo-genci-header.svg" style="width: 33%; margin: 0 auto; display: inline-block;"/> <img src="https://huggingface.co./datasets/PleIAs/common_corpus/resolve/main/logo/Nvidia_(logo).svg.png" style="width: 33%; margin: 0 auto; display: inline-block;"/> <img src="https://huggingface.co./datasets/PleIAs/common_corpus/resolve/main/logo/tractoAI.png" style="width: 33%; margin: 0 auto; display: inline-block;"/> <img src="https://huggingface.co./datasets/PleIAs/common_corpus/resolve/main/logo/mozilla.png" style="width: 33%; margin: 0 auto; display: inline-block;"/> <img src="https://raw.githubusercontent.com/Pleias/logos/f117dee70b317bc664eac14ee70d7c0563101ed1/ministere_logo.png?token=GHSAT0AAAAAACZUTJMICO3MSWUJ43EQWG5QZZL3RFQ" style="width: 33%; margin: 0 auto; display: inline-block;"/> <img src="https://raw.githubusercontent.com/Pleias/logos/f117dee70b317bc664eac14ee70d7c0563101ed1/wikimedia_logo.png?token=GHSAT0AAAAAACZUTJMIIPAP4J7MKP6RSSWCZZL3TFA" style="width: 33%; margin: 0 auto; display: inline-block;"/> </div>

HuggingFaceM4/Docmatix

HuggingFaceM4

--- language: - en license: mit size_categories: - 1M<n<10M task_categories: - visual-question-answering pretty_name: Docmatix tags: - docvqa configs: - config_name: images data_files: - split: train path: data/train-* - config_name: pdf data_files: - split: train path: pdf/train-* - config_name: zero-shot-exp data_files: - split: train path: zero-shot-exp/train-* - split: test path: zero-shot-exp/test-* dataset_info: - config_name: images features: - name: images sequence: image - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string splits: - name: train num_bytes: 552957537722.77 num_examples: 1273215 download_size: 159404414330 dataset_size: 552957537722.77 - config_name: pdf features: - name: pdf dtype: binary - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string splits: - name: train num_bytes: 458612867150 num_examples: 1273245 download_size: 431829972210 dataset_size: 458612867150 - config_name: zero-shot-exp features: - name: images sequence: image - name: texts list: - name: user dtype: string - name: assistant dtype: string - name: source dtype: string splits: - name: test num_bytes: 68900253.0 num_examples: 200 - name: train num_bytes: 578335690.5 num_examples: 1700 download_size: 642963847 dataset_size: 647235943.5 --- # Dataset Card for Docmatix  ## Dataset description Docmatix is part of the Idefics3 release (stay tuned). It is a massive dataset for Document Visual Question Answering that was used for the fine-tuning of the vision-language model Idefics3. ## Load the dataset To load the dataset, install the library `datasets` with `pip install datasets`. Then, ``` from datasets import load_dataset ds = load_dataset("HuggingFaceM4/Docmatix") ``` If you want the dataset to link to the pdf files as binaries instead of the images, do: ``` from datasets import load_dataset ds = load_dataset("HuggingFaceM4/Docmatix", "pdf") ``` ## Data fields An example of a sample looks as follows: ``` { "images" = [PIL.Image] "texts" = [ { "user": "What is the purpose of the Confirmation Statement mentioned in the document?", "assistant": "The purpose of the Confirmation Statement is to confirm that all information required to be delivered by the company to the registrar in relation to the confirmation period concerned has been delivered or is being delivered at the same time as the confirmation statement.", "source": "PDFA key: 244" }, { "user": "When was the filing received as per the document?", "assistant": "The filing was received for filing in Electronic Format on the 23/03/2021.", "source": "PDFA key: 244" }, ] } ``` In `images`, there is a list of up to 4 images, to be placed before the text. In `texts`, there is a conversation between a user and an assistant about the images that is represented by a list of turns. ## Comparison to other DocVQA datasets | Dataset | # images | # Q/A pairs | # tokens | |----------------------|----------|-------------|------------| | *Document visual question answering* | | **Docmatix** | **2,444,750**| **9,500,000** | **390,000,000**| | DocVQA | 10,189 | 39,463 | 337,829 | | TextCaps | 21,953 | 21,953 | 389,658 | | TextVQA | 21,953 | 34,602 | 181,918 | | ST-VQA | 17,247 | 23,121 | 127,846 | | OCR-VQA | 165,746 | 801,579 | 6,073,824 | | VisualMRC | 3,027 | 11,988 | 168,828 | | IAM | 5,663 | 5,663 | 144,216 | | InfoVQA | 2,118 | 10,074 | 61,048 | | Diagram image-to-text| 300 | 300 | 22,196 | # Citation **BibTeX:** ```bibtex @misc{laurençon2024building, title={Building and better understanding vision-language models: insights and future directions.}, author={Hugo Laurençon and Andrés Marafioti and Victor Sanh and Léo Tronchon}, year={2024}, eprint={2408.12637}, archivePrefix={arXiv}, primaryClass={cs.CV} } ```

common-canvas/commoncatalog-cc-by-nc-nd

common-canvas

--- license: cc-by-nc-nd-4.0 dataset_info: features: - name: jpg dtype: image - name: blip2_caption dtype: string - name: caption dtype: string - name: licensename dtype: string - name: licenseurl dtype: string - name: width dtype: int32 - name: height dtype: int32 - name: original_width dtype: int32 - name: original_height dtype: int32 - name: photoid dtype: int64 - name: uid dtype: string - name: unickname dtype: string - name: datetaken dtype: timestamp[us] - name: dateuploaded dtype: int64 - name: capturedevice dtype: string - name: title dtype: string - name: usertags dtype: string - name: machinetags dtype: string - name: longitude dtype: float64 - name: latitude dtype: float64 - name: accuracy dtype: int64 - name: pageurl dtype: string - name: downloadurl dtype: string - name: serverid dtype: int64 - name: farmid dtype: int64 - name: secret dtype: string - name: secretoriginal dtype: string - name: ext dtype: string - name: url dtype: string - name: key dtype: string - name: status dtype: string - name: error_message dtype: string - name: exif dtype: string - name: sha256 dtype: string - name: description dtype: string task_categories: - text-to-image language: - en --- # Dataset Card for CommonCatalog CC-BY-NC-ND This dataset is a large collection of high-resolution Creative Common images (composed of different licenses, see paper Table 1 in the Appendix) collected in 2014 from users of Yahoo Flickr. The dataset contains images of up to 4k resolution, making this one of the highest resolution captioned image datasets. ## Dataset Details ### Dataset Description We provide captions synthetic captions to approximately 100 million high resolution images collected from Yahoo Flickr Creative Commons (YFCC). - **Curated by:** Aaron Gokaslan - **Language(s) (NLP):** en - **License:** See relevant yaml tag / dataset name. ### Dataset Sources <!-- Provide the basic links for the dataset. --> - **Repository:** https://github.com/mosaicml/diffusion - **Paper:** https://arxiv.org/abs/2310.16825 - **Demo:** See CommonCanvas Gradios ## Uses We use CommonCatalog to train a family latent diffusion models called CommonCanvas. The goal is to produce a model that is competitive with Stable Diffusion 2, but to do so using an easily accessible dataset of known provenance. Doing so makes replicating the model significantly easier, and provides a clearer mechanism for applying training-data attribution techniques. ### Direct Use Training text-to-image models Training image-to-text models ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the dataset will not work well for. --> * Commercial use * Crafting content that is offensive or injurious towards individuals, including negative portrayals of their living conditions, cultural backgrounds, religious beliefs, etc. * Deliberately creating or spreading content that is discriminatory or reinforces harmful stereotypes. * Falsely representing individuals without their permission. * Generating sexual content that may be seen by individuals without their consent. * Producing or disseminating false or misleading information. * Creating content that depicts extreme violence or bloodshed. * Distributing content that modifies copyrighted or licensed material in a way that breaches its usage terms. ## Dataset Structure The dataset is divided into 10 subsets each containing parquets about 4GB each. Each subfolder within contains a resolution range of the images and their respective aspect ratios. The dataset is also divided along images licensed for commercial use (C) and those that are not (NC). ## Dataset Creation ### Curation Rationale Creating a standardized, accessible dataset with synthetic caption and releasing it so other people can train on a common dataset for open source image generation. ### Source Data Yahoo Flickr Creative Commons 100M Dataset and Synthetically Generated Caption Data. #### Data Collection and Processing All synthetic captions were generated with BLIP2. See paper for more details. #### Who are the source data producers? <!-- This section describes the people or systems who originally created the data. It should also include self-reported demographic or identity information for the source data creators if this information is available. --> Users of Flickr ## Bias, Risks, and Limitations See Yahoo Flickr Creative Commons 100M dataset for more information. The information was collected circa 2014 and known to have a bias towards internet connected Western countries. Some areas such as the global south lack representation. ## Citation **BibTeX:** ``` @article{gokaslan2023commoncanvas, title={CommonCanvas: An Open Diffusion Model Trained with Creative-Commons Images}, author={Gokaslan, Aaron and Cooper, A Feder and Collins, Jasmine and Seguin, Landan and Jacobson, Austin and Patel, Mihir and Frankle, Jonathan and Stephenson, Cory and Kuleshov, Volodymyr}, journal={arXiv preprint arXiv:2310.16825}, year={2023} } ``` ## Dataset Card Authors [Aaron Gokaslan](https://huggingface.co./Skylion007) ## Dataset Card Contact [Aaron Gokaslan](https://huggingface.co./Skylion007)

ChongyanChen/VQAonline

ChongyanChen

--- license: cc-by-sa-4.0 task_categories: - visual-question-answering pretty_name: VQAonline --- # VQAonline <img src="https://cdn-uploads.huggingface.co/production/uploads/6337e9b676421c05430a0287/6vt42q8w7EWx9vVuZqc3U.png" width="50%"> [**🌐 Homepage**](https://vqaonline.github.io/) | [**🤗 Dataset**](https://huggingface.co./datasets/ChongyanChen/VQAonline/) | [**📖 arXiv**](https://arxiv.org/abs/2311.15562) ## Dataset Description We introduce VQAonline, the first VQA dataset in which all contents originate from an authentic use case. VQAonline includes 64K visual questions sourced from an online question answering community (i.e., StackExchange). It differs from prior datasets; examples include that it contains: - (1) authentic context that clarifies the question - (2) an answer the individual asking the question validated as acceptable from all community provided answers, - (3) answers that are considerably longer (e.g., a mean of 173 words versus typically 11 words or fewer in prior work) - (4) user-chosen topics for each visual question from 105 diverse topics revealing the dataset’s inherent diversity. ## Download To download, you can use the following code: ``` git clone https://huggingface.co./datasets/ChongyanChen/VQAonline ``` ## Dataset Structure In total, the VQAonline dataset contains 64,696 visual questions. We designed VQAonline to support few-shot settings given the recent exciting developments around in-context few-shot learning with foundation models. Thus, we split the dataset as follows: - Training set: 665 visual questions - Validation set: 285 visual questions - Test set: 63,746 visual questions The questions, contexts, and answers are provided in the json files. Due to the constraint of huggingface, we separate the image files into 7 folders (named from images1 to images7), each of which contains 10,000 image files, except for folder "images 7". ## Contact - Chongyan Chen: [email protected] ## Citation **BibTeX:** ```bibtex @article{chen2023vqaonline, title={Fully Authentic Visual Question Answering Dataset from Online Communities}, author={Chen, Chongyan and Liu, Mengchen and Codella, Noel and Li, Yunsheng and Yuan, Lu and Gurari, Danna}, journal={arXiv preprint arXiv:2311.15562}, year={2023} } ```

mteb/banking77

mteb

--- language: - en ---

asahi417/seamless-align-enA-zhA.speaker-embedding.xlsr-2b

asahi417

--- dataset_info: - config_name: subset_1 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14209259131 num_examples: 1962 download_size: 14256120203 dataset_size: 14209259131 - config_name: subset_10 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13574781625 num_examples: 2031 download_size: 13621966757 dataset_size: 13574781625 - config_name: subset_100 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13223964877 num_examples: 1891 download_size: 13269307182 dataset_size: 13223964877 - config_name: subset_101 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13038203739 num_examples: 1885 download_size: 13083404216 dataset_size: 13038203739 - config_name: subset_102 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12731679458 num_examples: 1863 download_size: 12775688644 dataset_size: 12731679458 - config_name: subset_103 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12967209285 num_examples: 1861 download_size: 13011071076 dataset_size: 12967209285 - config_name: subset_104 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12798692606 num_examples: 1875 download_size: 12842795816 dataset_size: 12798692606 - config_name: subset_105 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13127114114 num_examples: 1871 download_size: 13172271401 dataset_size: 13127114114 - config_name: subset_106 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12426801586 num_examples: 1865 download_size: 12469421998 dataset_size: 12426801586 - config_name: subset_107 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12484775174 num_examples: 1838 download_size: 12527398592 dataset_size: 12484775174 - config_name: subset_108 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13018346253 num_examples: 1860 download_size: 13063301347 dataset_size: 13018346253 - config_name: subset_109 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12986696298 num_examples: 1866 download_size: 13030608940 dataset_size: 12986696298 - config_name: subset_11 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13038519979 num_examples: 1994 download_size: 13084550040 dataset_size: 13038519979 - config_name: subset_110 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12537003686 num_examples: 1843 download_size: 12580875152 dataset_size: 12537003686 - config_name: subset_111 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12920543044 num_examples: 1845 download_size: 12964231904 dataset_size: 12920543044 - config_name: subset_112 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12666264009 num_examples: 1844 download_size: 12709732284 dataset_size: 12666264009 - config_name: subset_113 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12572103874 num_examples: 1839 download_size: 12615926245 dataset_size: 12572103874 - config_name: subset_114 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12918422777 num_examples: 1851 download_size: 12960836861 dataset_size: 12918422777 - config_name: subset_115 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12832082885 num_examples: 1821 download_size: 12875679807 dataset_size: 12832082885 - config_name: subset_116 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12805128711 num_examples: 1837 download_size: 12848847004 dataset_size: 12805128711 - config_name: subset_117 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12914312061 num_examples: 1854 download_size: 12957416120 dataset_size: 12914312061 - config_name: subset_118 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12536340519 num_examples: 1814 download_size: 12579845649 dataset_size: 12536340519 - config_name: subset_119 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12663849536 num_examples: 1823 download_size: 12706307005 dataset_size: 12663849536 - config_name: subset_12 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13345506634 num_examples: 2034 download_size: 13391815198 dataset_size: 13345506634 - config_name: subset_120 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12540967981 num_examples: 1835 download_size: 12584734529 dataset_size: 12540967981 - config_name: subset_121 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12881361209 num_examples: 1832 download_size: 12925049223 dataset_size: 12881361209 - config_name: subset_122 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12693240892 num_examples: 1824 download_size: 12736912334 dataset_size: 12693240892 - config_name: subset_123 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12762978970 num_examples: 1800 download_size: 12804981254 dataset_size: 12762978970 - config_name: subset_124 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13001669496 num_examples: 1830 download_size: 13045674231 dataset_size: 13001669496 - config_name: subset_125 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12993926322 num_examples: 1858 download_size: 13037516573 dataset_size: 12993926322 - config_name: subset_126 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13297930843 num_examples: 1888 download_size: 13343186712 dataset_size: 13297930843 - config_name: subset_127 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12751048394 num_examples: 1833 download_size: 12794759892 dataset_size: 12751048394 - config_name: subset_128 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13141818374 num_examples: 1835 download_size: 13185797931 dataset_size: 13141818374 - config_name: subset_129 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13304123905 num_examples: 1885 download_size: 13349335826 dataset_size: 13304123905 - config_name: subset_13 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13296351131 num_examples: 2021 download_size: 13342470698 dataset_size: 13296351131 - config_name: subset_130 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12913357124 num_examples: 1828 download_size: 12956967608 dataset_size: 12913357124 - config_name: subset_131 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12861389006 num_examples: 1813 download_size: 12904807434 dataset_size: 12861389006 - config_name: subset_132 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13234681867 num_examples: 1864 download_size: 13279044682 dataset_size: 13234681867 - config_name: subset_133 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12962105674 num_examples: 1844 download_size: 13005284694 dataset_size: 12962105674 - config_name: subset_134 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12743586667 num_examples: 1826 download_size: 12787256702 dataset_size: 12743586667 - config_name: subset_135 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13166439361 num_examples: 1853 download_size: 13211052569 dataset_size: 13166439361 - config_name: subset_136 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13099690718 num_examples: 1881 download_size: 13144846389 dataset_size: 13099690718 - config_name: subset_137 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12741551269 num_examples: 1837 download_size: 12785267794 dataset_size: 12741551269 - config_name: subset_138 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13205037463 num_examples: 1869 download_size: 13250209887 dataset_size: 13205037463 - config_name: subset_139 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12997304962 num_examples: 1830 download_size: 13040947110 dataset_size: 12997304962 - config_name: subset_14 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13147826343 num_examples: 2012 download_size: 13193978395 dataset_size: 13147826343 - config_name: subset_140 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12925120270 num_examples: 1815 download_size: 12968597687 dataset_size: 12925120270 - config_name: subset_141 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12720671970 num_examples: 1814 download_size: 12764228297 dataset_size: 12720671970 - config_name: subset_142 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13068068628 num_examples: 1851 download_size: 13111428243 dataset_size: 13068068628 - config_name: subset_143 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12707538206 num_examples: 1792 download_size: 12750667442 dataset_size: 12707538206 - config_name: subset_144 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13032830257 num_examples: 1856 download_size: 13077677610 dataset_size: 13032830257 - config_name: subset_145 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13125760032 num_examples: 1850 download_size: 13169372344 dataset_size: 13125760032 - config_name: subset_146 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13267575660 num_examples: 1847 download_size: 13312015745 dataset_size: 13267575660 - config_name: subset_147 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13027789155 num_examples: 1851 download_size: 13072382865 dataset_size: 13027789155 - config_name: subset_148 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13035403722 num_examples: 1848 download_size: 13079919602 dataset_size: 13035403722 - config_name: subset_149 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12973733702 num_examples: 1869 download_size: 13017673308 dataset_size: 12973733702 - config_name: subset_15 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13088705529 num_examples: 2010 download_size: 13134907161 dataset_size: 13088705529 - config_name: subset_150 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13483674365 num_examples: 1866 download_size: 13528056417 dataset_size: 13483674365 - config_name: subset_151 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13181178047 num_examples: 1862 download_size: 13225576965 dataset_size: 13181178047 - config_name: subset_152 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12941487991 num_examples: 1825 download_size: 12985061862 dataset_size: 12941487991 - config_name: subset_153 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13368213999 num_examples: 1859 download_size: 13412797003 dataset_size: 13368213999 - config_name: subset_154 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13297990214 num_examples: 1862 download_size: 13342836529 dataset_size: 13297990214 - config_name: subset_155 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13054204743 num_examples: 1827 download_size: 13097552879 dataset_size: 13054204743 - config_name: subset_156 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13062749902 num_examples: 1834 download_size: 13106716484 dataset_size: 13062749902 - config_name: subset_157 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13387093767 num_examples: 1861 download_size: 13431728772 dataset_size: 13387093767 - config_name: subset_158 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12880058650 num_examples: 1783 download_size: 12922917433 dataset_size: 12880058650 - config_name: subset_159 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 11881220327 num_examples: 1654 download_size: 11920259054 dataset_size: 11881220327 - config_name: subset_16 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12462625538 num_examples: 1974 download_size: 12506159941 dataset_size: 12462625538 - config_name: subset_160 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13238783195 num_examples: 1841 download_size: 13282707085 dataset_size: 13238783195 - config_name: subset_161 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13020419071 num_examples: 1838 download_size: 13064546764 dataset_size: 13020419071 - config_name: subset_162 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12977261277 num_examples: 1783 download_size: 13020115761 dataset_size: 12977261277 - config_name: subset_163 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13154440690 num_examples: 1805 download_size: 13196753466 dataset_size: 13154440690 - config_name: subset_164 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13221774010 num_examples: 1785 download_size: 13265348083 dataset_size: 13221774010 - config_name: subset_165 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12890453538 num_examples: 1764 download_size: 12932702421 dataset_size: 12890453538 - config_name: subset_166 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13238731446 num_examples: 1865 download_size: 13283761551 dataset_size: 13238731446 - config_name: subset_167 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13116757486 num_examples: 1794 download_size: 13160391058 dataset_size: 13116757486 - config_name: subset_168 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13507948525 num_examples: 1871 download_size: 13553344138 dataset_size: 13507948525 - config_name: subset_169 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13281798625 num_examples: 1845 download_size: 13326150167 dataset_size: 13281798625 - config_name: subset_17 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12530147436 num_examples: 2005 download_size: 12574908317 dataset_size: 12530147436 - config_name: subset_170 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13529725455 num_examples: 1877 download_size: 13575090508 dataset_size: 13529725455 - config_name: subset_171 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13437938918 num_examples: 1863 download_size: 13482733557 dataset_size: 13437938918 - config_name: subset_172 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13501430052 num_examples: 1841 download_size: 13546564951 dataset_size: 13501430052 - config_name: subset_173 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13150686556 num_examples: 1846 download_size: 13195014459 dataset_size: 13150686556 - config_name: subset_174 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13175889059 num_examples: 1833 download_size: 13218163076 dataset_size: 13175889059 - config_name: subset_175 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13102902135 num_examples: 1781 download_size: 13146424916 dataset_size: 13102902135 - config_name: subset_176 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13113639029 num_examples: 1809 download_size: 13156636320 dataset_size: 13113639029 - config_name: subset_177 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12925639837 num_examples: 1779 download_size: 12968379518 dataset_size: 12925639837 - config_name: subset_178 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13408612490 num_examples: 1810 download_size: 13450580598 dataset_size: 13408612490 - config_name: subset_179 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13385760100 num_examples: 1808 download_size: 13429460828 dataset_size: 13385760100 - config_name: subset_18 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12199898588 num_examples: 1933 download_size: 12243282500 dataset_size: 12199898588 - config_name: subset_180 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13530721722 num_examples: 1844 download_size: 13575900699 dataset_size: 13530721722 - config_name: subset_181 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13329843658 num_examples: 1808 download_size: 13373550290 dataset_size: 13329843658 - config_name: subset_182 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13421206325 num_examples: 1807 download_size: 13463752732 dataset_size: 13421206325 - config_name: subset_183 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13293489170 num_examples: 1790 download_size: 13336547592 dataset_size: 13293489170 - config_name: subset_184 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13170304190 num_examples: 1756 download_size: 13212477470 dataset_size: 13170304190 - config_name: subset_185 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13090231354 num_examples: 1782 download_size: 13133751213 dataset_size: 13090231354 - config_name: subset_186 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13202410818 num_examples: 1791 download_size: 13246025198 dataset_size: 13202410818 - config_name: subset_187 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13117901283 num_examples: 1780 download_size: 13161452953 dataset_size: 13117901283 - config_name: subset_188 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13040538960 num_examples: 1783 download_size: 13083376359 dataset_size: 13040538960 - config_name: subset_189 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13439617718 num_examples: 1814 download_size: 13483108790 dataset_size: 13439617718 - config_name: subset_19 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12564662092 num_examples: 1983 download_size: 12608495037 dataset_size: 12564662092 - config_name: subset_190 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13250790159 num_examples: 1802 download_size: 13294475053 dataset_size: 13250790159 - config_name: subset_191 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13576629500 num_examples: 1794 download_size: 13621403290 dataset_size: 13576629500 - config_name: subset_192 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13534614314 num_examples: 1805 download_size: 13579424803 dataset_size: 13534614314 - config_name: subset_193 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13205308518 num_examples: 1801 download_size: 13249015229 dataset_size: 13205308518 - config_name: subset_194 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13173748624 num_examples: 1781 download_size: 13217312510 dataset_size: 13173748624 - config_name: subset_195 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13262230923 num_examples: 1793 download_size: 13305822959 dataset_size: 13262230923 - config_name: subset_196 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13442030054 num_examples: 1808 download_size: 13485707566 dataset_size: 13442030054 - config_name: subset_197 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13279014406 num_examples: 1813 download_size: 13322778547 dataset_size: 13279014406 - config_name: subset_198 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13372535801 num_examples: 1806 download_size: 13416177685 dataset_size: 13372535801 - config_name: subset_199 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13260187374 num_examples: 1798 download_size: 13303786873 dataset_size: 13260187374 - config_name: subset_2 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14824893136 num_examples: 2052 download_size: 14872062544 dataset_size: 14824893136 - config_name: subset_20 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12469186480 num_examples: 1959 download_size: 12512664696 dataset_size: 12469186480 - config_name: subset_200 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13405377823 num_examples: 1814 download_size: 13449064998 dataset_size: 13405377823 - config_name: subset_201 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12857648840 num_examples: 1743 download_size: 12899723972 dataset_size: 12857648840 - config_name: subset_202 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13875371606 num_examples: 1837 download_size: 13920369985 dataset_size: 13875371606 - config_name: subset_203 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13399467921 num_examples: 1802 download_size: 13443037100 dataset_size: 13399467921 - config_name: subset_204 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13199244957 num_examples: 1790 download_size: 13242850615 dataset_size: 13199244957 - config_name: subset_205 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13522066316 num_examples: 1805 download_size: 13566902309 dataset_size: 13522066316 - config_name: subset_206 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13358642027 num_examples: 1793 download_size: 13402228636 dataset_size: 13358642027 - config_name: subset_207 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13117565020 num_examples: 1803 download_size: 13160834483 dataset_size: 13117565020 - config_name: subset_208 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13382606765 num_examples: 1772 download_size: 13425953489 dataset_size: 13382606765 - config_name: subset_209 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12974477742 num_examples: 1760 download_size: 13016667136 dataset_size: 12974477742 - config_name: subset_21 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12085360980 num_examples: 1934 download_size: 12128838861 dataset_size: 12085360980 - config_name: subset_210 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13476138379 num_examples: 1796 download_size: 13519239424 dataset_size: 13476138379 - config_name: subset_211 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13419976632 num_examples: 1804 download_size: 13463566063 dataset_size: 13419976632 - config_name: subset_212 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13480363370 num_examples: 1782 download_size: 13523820554 dataset_size: 13480363370 - config_name: subset_213 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13318991720 num_examples: 1782 download_size: 13362474010 dataset_size: 13318991720 - config_name: subset_214 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13172359156 num_examples: 1797 download_size: 13214875172 dataset_size: 13172359156 - config_name: subset_215 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13280189404 num_examples: 1805 download_size: 13323825654 dataset_size: 13280189404 - config_name: subset_216 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13228612682 num_examples: 1784 download_size: 13272174030 dataset_size: 13228612682 - config_name: subset_217 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13301788292 num_examples: 1795 download_size: 13344755106 dataset_size: 13301788292 - config_name: subset_218 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13444033873 num_examples: 1787 download_size: 13486618579 dataset_size: 13444033873 - config_name: subset_219 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13385006271 num_examples: 1798 download_size: 13428624694 dataset_size: 13385006271 - config_name: subset_22 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12068647069 num_examples: 1919 download_size: 12112052242 dataset_size: 12068647069 - config_name: subset_220 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13387979539 num_examples: 1793 download_size: 13431556808 dataset_size: 13387979539 - config_name: subset_221 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13184366878 num_examples: 1768 download_size: 13227780561 dataset_size: 13184366878 - config_name: subset_222 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13019967994 num_examples: 1771 download_size: 13063453259 dataset_size: 13019967994 - config_name: subset_223 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13009363028 num_examples: 1758 download_size: 13052746979 dataset_size: 13009363028 - config_name: subset_224 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13653747955 num_examples: 1816 download_size: 13698603852 dataset_size: 13653747955 - config_name: subset_225 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13118240446 num_examples: 1793 download_size: 13161929983 dataset_size: 13118240446 - config_name: subset_226 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13687749995 num_examples: 1820 download_size: 13732610680 dataset_size: 13687749995 - config_name: subset_227 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13607917615 num_examples: 1780 download_size: 13652544829 dataset_size: 13607917615 - config_name: subset_228 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13342866303 num_examples: 1787 download_size: 13386381015 dataset_size: 13342866303 - config_name: subset_229 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13310021752 num_examples: 1749 download_size: 13353269100 dataset_size: 13310021752 - config_name: subset_23 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12351336675 num_examples: 1955 download_size: 12394781249 dataset_size: 12351336675 - config_name: subset_230 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13841783584 num_examples: 1822 download_size: 13886657543 dataset_size: 13841783584 - config_name: subset_231 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13716496527 num_examples: 1829 download_size: 13761486198 dataset_size: 13716496527 - config_name: subset_232 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13468291883 num_examples: 1783 download_size: 13510236937 dataset_size: 13468291883 - config_name: subset_233 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13380265372 num_examples: 1800 download_size: 13423849283 dataset_size: 13380265372 - config_name: subset_234 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13713921272 num_examples: 1815 download_size: 13758828731 dataset_size: 13713921272 - config_name: subset_235 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13514220908 num_examples: 1804 download_size: 13559019032 dataset_size: 13514220908 - config_name: subset_236 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13494111624 num_examples: 1801 download_size: 13537700105 dataset_size: 13494111624 - config_name: subset_237 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13544863571 num_examples: 1790 download_size: 13589626744 dataset_size: 13544863571 - config_name: subset_238 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13554393425 num_examples: 1811 download_size: 13597849508 dataset_size: 13554393425 - config_name: subset_239 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13546762388 num_examples: 1801 download_size: 13591616587 dataset_size: 13546762388 - config_name: subset_24 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12065934022 num_examples: 1912 download_size: 12109149622 dataset_size: 12065934022 - config_name: subset_240 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13196715201 num_examples: 1770 download_size: 13240155032 dataset_size: 13196715201 - config_name: subset_241 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13659450783 num_examples: 1832 download_size: 13704113396 dataset_size: 13659450783 - config_name: subset_242 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13246292263 num_examples: 1769 download_size: 13289711363 dataset_size: 13246292263 - config_name: subset_243 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13566094535 num_examples: 1791 download_size: 13610689089 dataset_size: 13566094535 - config_name: subset_244 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13087093994 num_examples: 1754 download_size: 13130462985 dataset_size: 13087093994 - config_name: subset_245 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13606181830 num_examples: 1790 download_size: 13650688469 dataset_size: 13606181830 - config_name: subset_246 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13477021726 num_examples: 1793 download_size: 13520536644 dataset_size: 13477021726 - config_name: subset_247 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13530919547 num_examples: 1820 download_size: 13575873477 dataset_size: 13530919547 - config_name: subset_248 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13076084830 num_examples: 1779 download_size: 13118512234 dataset_size: 13076084830 - config_name: subset_249 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13529657489 num_examples: 1797 download_size: 13574453907 dataset_size: 13529657489 - config_name: subset_25 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12305898739 num_examples: 1925 download_size: 12349158665 dataset_size: 12305898739 - config_name: subset_250 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13381525728 num_examples: 1802 download_size: 13425146039 dataset_size: 13381525728 - config_name: subset_251 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13822740954 num_examples: 1801 download_size: 13866366309 dataset_size: 13822740954 - config_name: subset_252 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13673963248 num_examples: 1800 download_size: 13718685655 dataset_size: 13673963248 - config_name: subset_253 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13835058700 num_examples: 1805 download_size: 13879166806 dataset_size: 13835058700 - config_name: subset_254 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13383712853 num_examples: 1767 download_size: 13426540477 dataset_size: 13383712853 - config_name: subset_255 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13560805607 num_examples: 1763 download_size: 13604948210 dataset_size: 13560805607 - config_name: subset_256 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13237669958 num_examples: 1758 download_size: 13281016253 dataset_size: 13237669958 - config_name: subset_257 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13923624660 num_examples: 1807 download_size: 13968391517 dataset_size: 13923624660 - config_name: subset_258 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 11361216368 num_examples: 1503 download_size: 11398068945 dataset_size: 11361216368 - config_name: subset_26 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 11342909197 num_examples: 1832 download_size: 11383158933 dataset_size: 11342909197 - config_name: subset_27 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 11602861316 num_examples: 1862 download_size: 11643598489 dataset_size: 11602861316 - config_name: subset_28 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 11423759992 num_examples: 1829 download_size: 11464108953 dataset_size: 11423759992 - config_name: subset_29 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 11317928199 num_examples: 1828 download_size: 11358232335 dataset_size: 11317928199 - config_name: subset_3 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 15009073368 num_examples: 2081 download_size: 15059069139 dataset_size: 15009073368 - config_name: subset_30 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 11340440138 num_examples: 1801 download_size: 11380580568 dataset_size: 11340440138 - config_name: subset_31 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 11585306838 num_examples: 1904 download_size: 11626002198 dataset_size: 11585306838 - config_name: subset_32 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 11839140118 num_examples: 1904 download_size: 11881221624 dataset_size: 11839140118 - config_name: subset_33 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 11667822890 num_examples: 1874 download_size: 11709572131 dataset_size: 11667822890 - config_name: subset_34 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12102711256 num_examples: 1932 download_size: 12146166646 dataset_size: 12102711256 - config_name: subset_35 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12121565378 num_examples: 1902 download_size: 12164750724 dataset_size: 12121565378 - config_name: subset_36 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 11813142889 num_examples: 1877 download_size: 11853807475 dataset_size: 11813142889 - config_name: subset_37 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12105640911 num_examples: 1862 download_size: 12148512935 dataset_size: 12105640911 - config_name: subset_38 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12055811433 num_examples: 1878 download_size: 12098864002 dataset_size: 12055811433 - config_name: subset_39 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12027703389 num_examples: 1879 download_size: 12070810328 dataset_size: 12027703389 - config_name: subset_4 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14871815890 num_examples: 2102 download_size: 14921781959 dataset_size: 14871815890 - config_name: subset_40 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12297307550 num_examples: 1919 download_size: 12340628479 dataset_size: 12297307550 - config_name: subset_41 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 11673113363 num_examples: 1828 download_size: 11714539382 dataset_size: 11673113363 - config_name: subset_42 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12114525371 num_examples: 1884 download_size: 12157548017 dataset_size: 12114525371 - config_name: subset_43 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12072393153 num_examples: 1874 download_size: 12115455581 dataset_size: 12072393153 - config_name: subset_44 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12231430525 num_examples: 1894 download_size: 12274252942 dataset_size: 12231430525 - config_name: subset_45 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12138951543 num_examples: 1869 download_size: 12181833715 dataset_size: 12138951543 - config_name: subset_46 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12338384571 num_examples: 1899 download_size: 12381559009 dataset_size: 12338384571 - config_name: subset_47 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12595976439 num_examples: 1913 download_size: 12639701571 dataset_size: 12595976439 - config_name: subset_48 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12291667679 num_examples: 1922 download_size: 12335068918 dataset_size: 12291667679 - config_name: subset_49 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12076363347 num_examples: 1844 download_size: 12118856817 dataset_size: 12076363347 - config_name: subset_5 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14463875379 num_examples: 2045 download_size: 14511930615 dataset_size: 14463875379 - config_name: subset_50 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12201692647 num_examples: 1884 download_size: 12244065455 dataset_size: 12201692647 - config_name: subset_51 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12205237779 num_examples: 1918 download_size: 12247882809 dataset_size: 12205237779 - config_name: subset_52 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12189874310 num_examples: 1880 download_size: 12232943844 dataset_size: 12189874310 - config_name: subset_53 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12566145830 num_examples: 1897 download_size: 12609016174 dataset_size: 12566145830 - config_name: subset_54 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12446537009 num_examples: 1901 download_size: 12489664423 dataset_size: 12446537009 - config_name: subset_55 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12447865477 num_examples: 1890 download_size: 12490882006 dataset_size: 12447865477 - config_name: subset_56 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 11886184932 num_examples: 1851 download_size: 11927798488 dataset_size: 11886184932 - config_name: subset_57 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12488545723 num_examples: 1904 download_size: 12531536020 dataset_size: 12488545723 - config_name: subset_58 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12062402025 num_examples: 1850 download_size: 12105197651 dataset_size: 12062402025 - config_name: subset_59 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12373068180 num_examples: 1875 download_size: 12415995259 dataset_size: 12373068180 - config_name: subset_6 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14501738118 num_examples: 2090 download_size: 14551152342 dataset_size: 14501738118 - config_name: subset_60 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12180776572 num_examples: 1881 download_size: 12223818393 dataset_size: 12180776572 - config_name: subset_61 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12048086660 num_examples: 1849 download_size: 12090892833 dataset_size: 12048086660 - config_name: subset_62 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12657808103 num_examples: 1895 download_size: 12701743869 dataset_size: 12657808103 - config_name: subset_63 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12392654565 num_examples: 1874 download_size: 12434138173 dataset_size: 12392654565 - config_name: subset_64 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12350385561 num_examples: 1882 download_size: 12393397192 dataset_size: 12350385561 - config_name: subset_65 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12373129329 num_examples: 1871 download_size: 12410450046 dataset_size: 12373129329 - config_name: subset_66 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12278015011 num_examples: 1850 download_size: 12320703540 dataset_size: 12278015011 - config_name: subset_67 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12371002905 num_examples: 1896 download_size: 12414173841 dataset_size: 12371002905 - config_name: subset_68 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12305454575 num_examples: 1850 download_size: 12348208355 dataset_size: 12305454575 - config_name: subset_69 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12411747691 num_examples: 1854 download_size: 12454448363 dataset_size: 12411747691 - config_name: subset_7 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14508087261 num_examples: 2116 download_size: 14558140635 dataset_size: 14508087261 - config_name: subset_70 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12350275460 num_examples: 1851 download_size: 12393029167 dataset_size: 12350275460 - config_name: subset_71 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12537513558 num_examples: 1876 download_size: 12581645796 dataset_size: 12537513558 - config_name: subset_72 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12490553756 num_examples: 1841 download_size: 12533178091 dataset_size: 12490553756 - config_name: subset_73 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12518388540 num_examples: 1882 download_size: 12561275853 dataset_size: 12518388540 - config_name: subset_74 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12497263818 num_examples: 1865 download_size: 12540088306 dataset_size: 12497263818 - config_name: subset_75 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12305999986 num_examples: 1848 download_size: 12348789656 dataset_size: 12305999986 - config_name: subset_76 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12750830510 num_examples: 1894 download_size: 12795055702 dataset_size: 12750830510 - config_name: subset_77 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12671852813 num_examples: 1875 download_size: 12715112660 dataset_size: 12671852813 - config_name: subset_78 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12871126714 num_examples: 1933 download_size: 12914706808 dataset_size: 12871126714 - config_name: subset_79 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12749824472 num_examples: 1900 download_size: 12793397015 dataset_size: 12749824472 - config_name: subset_8 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 14210430391 num_examples: 2095 download_size: 14259459141 dataset_size: 14210430391 - config_name: subset_80 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12490567475 num_examples: 1821 download_size: 12533032118 dataset_size: 12490567475 - config_name: subset_81 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12666304824 num_examples: 1873 download_size: 12710378751 dataset_size: 12666304824 - config_name: subset_82 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12789616733 num_examples: 1862 download_size: 12833584641 dataset_size: 12789616733 - config_name: subset_83 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12338377273 num_examples: 1809 download_size: 12380811191 dataset_size: 12338377273 - config_name: subset_84 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12554741918 num_examples: 1792 download_size: 12597991658 dataset_size: 12554741918 - config_name: subset_85 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12701297528 num_examples: 1870 download_size: 12745293256 dataset_size: 12701297528 - config_name: subset_86 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12337303789 num_examples: 1838 download_size: 12378681021 dataset_size: 12337303789 - config_name: subset_87 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12515934904 num_examples: 1852 download_size: 12559866703 dataset_size: 12515934904 - config_name: subset_88 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12486460328 num_examples: 1867 download_size: 12529352258 dataset_size: 12486460328 - config_name: subset_89 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13005033357 num_examples: 1903 download_size: 13050512457 dataset_size: 13005033357 - config_name: subset_9 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13964425360 num_examples: 2073 download_size: 14011911721 dataset_size: 13964425360 - config_name: subset_90 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12508609901 num_examples: 1826 download_size: 12552399045 dataset_size: 12508609901 - config_name: subset_91 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12766878985 num_examples: 1852 download_size: 12810779213 dataset_size: 12766878985 - config_name: subset_92 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12484630250 num_examples: 1852 download_size: 12527348681 dataset_size: 12484630250 - config_name: subset_93 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12560208384 num_examples: 1830 download_size: 12602554131 dataset_size: 12560208384 - config_name: subset_94 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12563291097 num_examples: 1848 download_size: 12607156154 dataset_size: 12563291097 - config_name: subset_95 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12839362555 num_examples: 1857 download_size: 12882825153 dataset_size: 12839362555 - config_name: subset_96 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12907967612 num_examples: 1885 download_size: 12952072820 dataset_size: 12907967612 - config_name: subset_97 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12893205307 num_examples: 1869 download_size: 12935785916 dataset_size: 12893205307 - config_name: subset_98 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 12554140420 num_examples: 1860 download_size: 12598098176 dataset_size: 12554140420 - config_name: subset_99 features: - name: line_no dtype: int64 - name: enA.id dtype: string - name: enA.laser_score dtype: float64 - name: zhA.id dtype: string - name: zhA.laser_score dtype: float64 - name: zhA.audio.speaker_embedding sequence: float32 - name: zhA.audio.speaker_embedding.full sequence: sequence: float32 - name: enA.audio.speaker_embedding sequence: float32 - name: enA.audio.speaker_embedding.full sequence: sequence: float32 splits: - name: train num_bytes: 13502104593 num_examples: 1915 download_size: 13548188642 dataset_size: 13502104593 configs: - config_name: subset_1 data_files: - split: train path: subset_1/train-* - config_name: subset_10 data_files: - split: train path: subset_10/train-* - config_name: subset_100 data_files: - split: train path: subset_100/train-* - config_name: subset_101 data_files: - split: train path: subset_101/train-* - config_name: subset_102 data_files: - split: train path: subset_102/train-* - config_name: subset_103 data_files: - split: train path: subset_103/train-* - config_name: subset_104 data_files: - split: train path: subset_104/train-* - config_name: subset_105 data_files: - split: train path: subset_105/train-* - config_name: subset_106 data_files: - split: train path: subset_106/train-* - config_name: subset_107 data_files: - split: train path: subset_107/train-* - config_name: subset_108 data_files: - split: train path: subset_108/train-* - config_name: subset_109 data_files: - split: train path: subset_109/train-* - config_name: subset_11 data_files: - split: train path: subset_11/train-* - config_name: subset_110 data_files: - split: train path: subset_110/train-* - config_name: subset_111 data_files: - split: train path: subset_111/train-* - config_name: subset_112 data_files: - split: train path: subset_112/train-* - config_name: subset_113 data_files: - split: train path: subset_113/train-* - config_name: subset_114 data_files: - split: train path: subset_114/train-* - config_name: subset_115 data_files: - split: train path: subset_115/train-* - config_name: subset_116 data_files: - split: train path: subset_116/train-* - config_name: subset_117 data_files: - split: train path: subset_117/train-* - config_name: subset_118 data_files: - split: train path: subset_118/train-* - config_name: subset_119 data_files: - split: train path: subset_119/train-* - config_name: subset_12 data_files: - split: train path: subset_12/train-* - config_name: subset_120 data_files: - split: train path: subset_120/train-* - config_name: subset_121 data_files: - split: train path: subset_121/train-* - config_name: subset_122 data_files: - split: train path: subset_122/train-* - config_name: subset_123 data_files: - split: train path: subset_123/train-* - config_name: subset_124 data_files: - split: train path: subset_124/train-* - config_name: subset_125 data_files: - split: train path: subset_125/train-* - config_name: subset_126 data_files: - split: train path: subset_126/train-* - config_name: subset_127 data_files: - split: train path: subset_127/train-* - config_name: subset_128 data_files: - split: train path: subset_128/train-* - config_name: subset_129 data_files: - split: train path: subset_129/train-* - config_name: subset_13 data_files: - split: train path: subset_13/train-* - config_name: subset_130 data_files: - split: train path: subset_130/train-* - config_name: subset_131 data_files: - split: train path: subset_131/train-* - config_name: subset_132 data_files: - split: train path: subset_132/train-* - config_name: subset_133 data_files: - split: train path: subset_133/train-* - config_name: subset_134 data_files: - split: train path: subset_134/train-* - config_name: subset_135 data_files: - split: train path: subset_135/train-* - config_name: subset_136 data_files: - split: train path: subset_136/train-* - config_name: subset_137 data_files: - split: train path: subset_137/train-* - config_name: subset_138 data_files: - split: train path: subset_138/train-* - config_name: subset_139 data_files: - split: train path: subset_139/train-* - config_name: subset_14 data_files: - split: train path: subset_14/train-* - config_name: subset_140 data_files: - split: train path: subset_140/train-* - config_name: subset_141 data_files: - split: train path: subset_141/train-* - config_name: subset_142 data_files: - split: train path: subset_142/train-* - config_name: subset_143 data_files: - split: train path: subset_143/train-* - config_name: subset_144 data_files: - split: train path: subset_144/train-* - config_name: subset_145 data_files: - split: train path: subset_145/train-* - config_name: subset_146 data_files: - split: train path: subset_146/train-* - config_name: subset_147 data_files: - split: train path: subset_147/train-* - config_name: subset_148 data_files: - split: train path: subset_148/train-* - config_name: subset_149 data_files: - split: train path: subset_149/train-* - config_name: subset_15 data_files: - split: train path: subset_15/train-* - config_name: subset_150 data_files: - split: train path: subset_150/train-* - config_name: subset_151 data_files: - split: train path: subset_151/train-* - config_name: subset_152 data_files: - split: train path: subset_152/train-* - config_name: subset_153 data_files: - split: train path: subset_153/train-* - config_name: subset_154 data_files: - split: train path: subset_154/train-* - config_name: subset_155 data_files: - split: train path: subset_155/train-* - config_name: subset_156 data_files: - split: train path: subset_156/train-* - config_name: subset_157 data_files: - split: train path: subset_157/train-* - config_name: subset_158 data_files: - split: train path: subset_158/train-* - config_name: subset_159 data_files: - split: train path: subset_159/train-* - config_name: subset_16 data_files: - split: train path: subset_16/train-* - config_name: subset_160 data_files: - split: train path: subset_160/train-* - config_name: subset_161 data_files: - split: train path: subset_161/train-* - config_name: subset_162 data_files: - split: train path: subset_162/train-* - config_name: subset_163 data_files: - split: train path: subset_163/train-* - config_name: subset_164 data_files: - split: train path: subset_164/train-* - config_name: subset_165 data_files: - split: train path: subset_165/train-* - config_name: subset_166 data_files: - split: train path: subset_166/train-* - config_name: subset_167 data_files: - split: train path: subset_167/train-* - config_name: subset_168 data_files: - split: train path: subset_168/train-* - config_name: subset_169 data_files: - split: train path: subset_169/train-* - config_name: subset_17 data_files: - split: train path: subset_17/train-* - config_name: subset_170 data_files: - split: train path: subset_170/train-* - config_name: subset_171 data_files: - split: train path: subset_171/train-* - config_name: subset_172 data_files: - split: train path: subset_172/train-* - config_name: subset_173 data_files: - split: train path: subset_173/train-* - config_name: subset_174 data_files: - split: train path: subset_174/train-* - config_name: subset_175 data_files: - split: train path: subset_175/train-* - config_name: subset_176 data_files: - split: train path: subset_176/train-* - config_name: subset_177 data_files: - split: train path: subset_177/train-* - config_name: subset_178 data_files: - split: train path: subset_178/train-* - config_name: subset_179 data_files: - split: train path: subset_179/train-* - config_name: subset_18 data_files: - split: train path: subset_18/train-* - config_name: subset_180 data_files: - split: train path: subset_180/train-* - config_name: subset_181 data_files: - split: train path: subset_181/train-* - config_name: subset_182 data_files: - split: train path: subset_182/train-* - config_name: subset_183 data_files: - split: train path: subset_183/train-* - config_name: subset_184 data_files: - split: train path: subset_184/train-* - config_name: subset_185 data_files: - split: train path: subset_185/train-* - config_name: subset_186 data_files: - split: train path: subset_186/train-* - config_name: subset_187 data_files: - split: train path: subset_187/train-* - config_name: subset_188 data_files: - split: train path: subset_188/train-* - config_name: subset_189 data_files: - split: train path: subset_189/train-* - config_name: subset_19 data_files: - split: train path: subset_19/train-* - config_name: subset_190 data_files: - split: train path: subset_190/train-* - config_name: subset_191 data_files: - split: train path: subset_191/train-* - config_name: subset_192 data_files: - split: train path: subset_192/train-* - config_name: subset_193 data_files: - split: train path: subset_193/train-* - config_name: subset_194 data_files: - split: train path: subset_194/train-* - config_name: subset_195 data_files: - split: train path: subset_195/train-* - config_name: subset_196 data_files: - split: train path: subset_196/train-* - config_name: subset_197 data_files: - split: train path: subset_197/train-* - config_name: subset_198 data_files: - split: train path: subset_198/train-* - config_name: subset_199 data_files: - split: train path: subset_199/train-* - config_name: subset_2 data_files: - split: train path: subset_2/train-* - config_name: subset_20 data_files: - split: train path: subset_20/train-* - config_name: subset_200 data_files: - split: train path: subset_200/train-* - config_name: subset_201 data_files: - split: train path: subset_201/train-* - config_name: subset_202 data_files: - split: train path: subset_202/train-* - config_name: subset_203 data_files: - split: train path: subset_203/train-* - config_name: subset_204 data_files: - split: train path: subset_204/train-* - config_name: subset_205 data_files: - split: train path: subset_205/train-* - config_name: subset_206 data_files: - split: train path: subset_206/train-* - config_name: subset_207 data_files: - split: train path: subset_207/train-* - config_name: subset_208 data_files: - split: train path: subset_208/train-* - config_name: subset_209 data_files: - split: train path: subset_209/train-* - config_name: subset_21 data_files: - split: train path: subset_21/train-* - config_name: subset_210 data_files: - split: train path: subset_210/train-* - config_name: subset_211 data_files: - split: train path: subset_211/train-* - config_name: subset_212 data_files: - split: train path: subset_212/train-* - config_name: subset_213 data_files: - split: train path: subset_213/train-* - config_name: subset_214 data_files: - split: train path: subset_214/train-* - config_name: subset_215 data_files: - split: train path: subset_215/train-* - config_name: subset_216 data_files: - split: train path: subset_216/train-* - config_name: subset_217 data_files: - split: train path: subset_217/train-* - config_name: subset_218 data_files: - split: train path: subset_218/train-* - config_name: subset_219 data_files: - split: train path: subset_219/train-* - config_name: subset_22 data_files: - split: train path: subset_22/train-* - config_name: subset_220 data_files: - split: train path: subset_220/train-* - config_name: subset_221 data_files: - split: train path: subset_221/train-* - config_name: subset_222 data_files: - split: train path: subset_222/train-* - config_name: subset_223 data_files: - split: train path: subset_223/train-* - config_name: subset_224 data_files: - split: train path: subset_224/train-* - config_name: subset_225 data_files: - split: train path: subset_225/train-* - config_name: subset_226 data_files: - split: train path: subset_226/train-* - config_name: subset_227 data_files: - split: train path: subset_227/train-* - config_name: subset_228 data_files: - split: train path: subset_228/train-* - config_name: subset_229 data_files: - split: train path: subset_229/train-* - config_name: subset_23 data_files: - split: train path: subset_23/train-* - config_name: subset_230 data_files: - split: train path: subset_230/train-* - config_name: subset_231 data_files: - split: train path: subset_231/train-* - config_name: subset_232 data_files: - split: train path: subset_232/train-* - config_name: subset_233 data_files: - split: train path: subset_233/train-* - config_name: subset_234 data_files: - split: train path: subset_234/train-* - config_name: subset_235 data_files: - split: train path: subset_235/train-* - config_name: subset_236 data_files: - split: train path: subset_236/train-* - config_name: subset_237 data_files: - split: train path: subset_237/train-* - config_name: subset_238 data_files: - split: train path: subset_238/train-* - config_name: subset_239 data_files: - split: train path: subset_239/train-* - config_name: subset_24 data_files: - split: train path: subset_24/train-* - config_name: subset_240 data_files: - split: train path: subset_240/train-* - config_name: subset_241 data_files: - split: train path: subset_241/train-* - config_name: subset_242 data_files: - split: train path: subset_242/train-* - config_name: subset_243 data_files: - split: train path: subset_243/train-* - config_name: subset_244 data_files: - split: train path: subset_244/train-* - config_name: subset_245 data_files: - split: train path: subset_245/train-* - config_name: subset_246 data_files: - split: train path: subset_246/train-* - config_name: subset_247 data_files: - split: train path: subset_247/train-* - config_name: subset_248 data_files: - split: train path: subset_248/train-* - config_name: subset_249 data_files: - split: train path: subset_249/train-* - config_name: subset_25 data_files: - split: train path: subset_25/train-* - config_name: subset_250 data_files: - split: train path: subset_250/train-* - config_name: subset_251 data_files: - split: train path: subset_251/train-* - config_name: subset_252 data_files: - split: train path: subset_252/train-* - config_name: subset_253 data_files: - split: train path: subset_253/train-* - config_name: subset_254 data_files: - split: train path: subset_254/train-* - config_name: subset_255 data_files: - split: train path: subset_255/train-* - config_name: subset_256 data_files: - split: train path: subset_256/train-* - config_name: subset_257 data_files: - split: train path: subset_257/train-* - config_name: subset_258 data_files: - split: train path: subset_258/train-* - config_name: subset_26 data_files: - split: train path: subset_26/train-* - config_name: subset_27 data_files: - split: train path: subset_27/train-* - config_name: subset_28 data_files: - split: train path: subset_28/train-* - config_name: subset_29 data_files: - split: train path: subset_29/train-* - config_name: subset_3 data_files: - split: train path: subset_3/train-* - config_name: subset_30 data_files: - split: train path: subset_30/train-* - config_name: subset_31 data_files: - split: train path: subset_31/train-* - config_name: subset_32 data_files: - split: train path: subset_32/train-* - config_name: subset_33 data_files: - split: train path: subset_33/train-* - config_name: subset_34 data_files: - split: train path: subset_34/train-* - config_name: subset_35 data_files: - split: train path: subset_35/train-* - config_name: subset_36 data_files: - split: train path: subset_36/train-* - config_name: subset_37 data_files: - split: train path: subset_37/train-* - config_name: subset_38 data_files: - split: train path: subset_38/train-* - config_name: subset_39 data_files: - split: train path: subset_39/train-* - config_name: subset_4 data_files: - split: train path: subset_4/train-* - config_name: subset_40 data_files: - split: train path: subset_40/train-* - config_name: subset_41 data_files: - split: train path: subset_41/train-* - config_name: subset_42 data_files: - split: train path: subset_42/train-* - config_name: subset_43 data_files: - split: train path: subset_43/train-* - config_name: subset_44 data_files: - split: train path: subset_44/train-* - config_name: subset_45 data_files: - split: train path: subset_45/train-* - config_name: subset_46 data_files: - split: train path: subset_46/train-* - config_name: subset_47 data_files: - split: train path: subset_47/train-* - config_name: subset_48 data_files: - split: train path: subset_48/train-* - config_name: subset_49 data_files: - split: train path: subset_49/train-* - config_name: subset_5 data_files: - split: train path: subset_5/train-* - config_name: subset_50 data_files: - split: train path: subset_50/train-* - config_name: subset_51 data_files: - split: train path: subset_51/train-* - config_name: subset_52 data_files: - split: train path: subset_52/train-* - config_name: subset_53 data_files: - split: train path: subset_53/train-* - config_name: subset_54 data_files: - split: train path: subset_54/train-* - config_name: subset_55 data_files: - split: train path: subset_55/train-* - config_name: subset_56 data_files: - split: train path: subset_56/train-* - config_name: subset_57 data_files: - split: train path: subset_57/train-* - config_name: subset_58 data_files: - split: train path: subset_58/train-* - config_name: subset_59 data_files: - split: train path: subset_59/train-* - config_name: subset_6 data_files: - split: train path: subset_6/train-* - config_name: subset_60 data_files: - split: train path: subset_60/train-* - config_name: subset_61 data_files: - split: train path: subset_61/train-* - config_name: subset_62 data_files: - split: train path: subset_62/train-* - config_name: subset_63 data_files: - split: train path: subset_63/train-* - config_name: subset_64 data_files: - split: train path: subset_64/train-* - config_name: subset_65 data_files: - split: train path: subset_65/train-* - config_name: subset_66 data_files: - split: train path: subset_66/train-* - config_name: subset_67 data_files: - split: train path: subset_67/train-* - config_name: subset_68 data_files: - split: train path: subset_68/train-* - config_name: subset_69 data_files: - split: train path: subset_69/train-* - config_name: subset_7 data_files: - split: train path: subset_7/train-* - config_name: subset_70 data_files: - split: train path: subset_70/train-* - config_name: subset_71 data_files: - split: train path: subset_71/train-* - config_name: subset_72 data_files: - split: train path: subset_72/train-* - config_name: subset_73 data_files: - split: train path: subset_73/train-* - config_name: subset_74 data_files: - split: train path: subset_74/train-* - config_name: subset_75 data_files: - split: train path: subset_75/train-* - config_name: subset_76 data_files: - split: train path: subset_76/train-* - config_name: subset_77 data_files: - split: train path: subset_77/train-* - config_name: subset_78 data_files: - split: train path: subset_78/train-* - config_name: subset_79 data_files: - split: train path: subset_79/train-* - config_name: subset_8 data_files: - split: train path: subset_8/train-* - config_name: subset_80 data_files: - split: train path: subset_80/train-* - config_name: subset_81 data_files: - split: train path: subset_81/train-* - config_name: subset_82 data_files: - split: train path: subset_82/train-* - config_name: subset_83 data_files: - split: train path: subset_83/train-* - config_name: subset_84 data_files: - split: train path: subset_84/train-* - config_name: subset_85 data_files: - split: train path: subset_85/train-* - config_name: subset_86 data_files: - split: train path: subset_86/train-* - config_name: subset_87 data_files: - split: train path: subset_87/train-* - config_name: subset_88 data_files: - split: train path: subset_88/train-* - config_name: subset_89 data_files: - split: train path: subset_89/train-* - config_name: subset_9 data_files: - split: train path: subset_9/train-* - config_name: subset_90 data_files: - split: train path: subset_90/train-* - config_name: subset_91 data_files: - split: train path: subset_91/train-* - config_name: subset_92 data_files: - split: train path: subset_92/train-* - config_name: subset_93 data_files: - split: train path: subset_93/train-* - config_name: subset_94 data_files: - split: train path: subset_94/train-* - config_name: subset_95 data_files: - split: train path: subset_95/train-* - config_name: subset_96 data_files: - split: train path: subset_96/train-* - config_name: subset_97 data_files: - split: train path: subset_97/train-* - config_name: subset_98 data_files: - split: train path: subset_98/train-* - config_name: subset_99 data_files: - split: train path: subset_99/train-* ---

HuggingFaceTB/smollm-corpus

HuggingFaceTB

--- license: odc-by dataset_info: - config_name: cosmopedia-v2 features: - name: prompt dtype: string - name: text dtype: string - name: token_length dtype: int64 - name: audience dtype: string - name: format dtype: string - name: seed_data dtype: string splits: - name: train num_bytes: 212503640747 num_examples: 39134000 download_size: 122361137711 dataset_size: 212503640747 - config_name: fineweb-edu-dedup features: - name: text dtype: string - name: id dtype: string - name: metadata struct: - name: dump dtype: string - name: url dtype: string - name: date dtype: timestamp[s] - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 splits: - name: train num_bytes: 957570164451 num_examples: 190168005 download_size: 550069279849 dataset_size: 957570164451 - config_name: python-edu features: - name: blob_id dtype: string - name: repo_name dtype: string - name: path dtype: string - name: length_bytes dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 splits: - name: train num_bytes: 989334135 num_examples: 7678448 download_size: 643903049 dataset_size: 989334135 configs: - config_name: cosmopedia-v2 data_files: - split: train path: cosmopedia-v2/train-* - config_name: fineweb-edu-dedup data_files: - split: train path: fineweb-edu-dedup/train-* - config_name: python-edu data_files: - split: train path: python-edu/train-* language: - en --- # SmolLM-Corpus This dataset is a curated collection of high-quality educational and synthetic data designed for training small language models. You can find more details about the models trained on this dataset in our [SmolLM blog post](https://huggingface.co./blog/smollm). # Dataset subsets ## Cosmopedia v2 Cosmopedia v2 is an enhanced version of Cosmopedia, the largest synthetic dataset for pre-training, consisting of over 39 million textbooks, blog posts, and stories generated by [Mixtral-8x7B-Instruct-v0.1](https://huggingface.co./mistralai/Mixtral-8x7B-Instruct-v0.1). Most of the samples are generated by prompting the model to generate content on specific topics using a web page referred to as a "seed sample," as shown in Figure 1. We use web samples to increase diversity and expand the range of prompts. You can find more details in this [blog post](https://huggingface.co./blog/smollm). ### Dataset Features * `prompt (string)`: The input prompt used to generate the text. * `text (string)`: The generated text content. * `token_length (int64)`: The length of the text in tokens (Mistral-7B tokenizer). * `audience (string)`: The intended audience for the content. * `format (string)`: The format of the content (e.g., textbook, story). * `seed_data (string)`: The seed sample used to generate the text. ### Loading the dataset ```python from datasets import load_dataset ds = load_dataset("HuggingFaceTB/smollm-corpus", "cosmopedia-v2", split="train", num_proc=16) print(ds[0]) ``` ## Python-Edu The `python-edu` subset consists of Python files that were scored 4 or more by the [educational code model](https://huggingface.co./HuggingFaceTB/python-edu-scorer). The files were extracted from the [`stack-v2-train`](https://huggingface.co./datasets/bigcode/the-stack-v2-train-full-ids) dataset. ### Dataset Features * `blob_id (string)`: Software Heritage (SWH) ID of the file on AWS S3. * `repo_name (string)`: Repository name on GitHub. * `path (string)`: The file path within the repository. * `length_bytes (int64)`: Length of the file content in UTF-8 bytes. * `score (float32)`: The output of the educational scoring model. * `int_score (uint8)`: The rounded educational score. ### Downloading the data The file contents are downloaded from Software Heritage's S3 bucket to ensure data compliance. Please refer to [the-stack-v2](https://huggingface.co./datasets/bigcode/the-stack-v2-train-full-ids) for the data license. When running on a 16-core AWS `us-east-1` instance, this script takes ~6 hours to download the files: ```python import boto3 import gzip from datasets import load_dataset from botocore.exceptions import ClientError num_proc = 16 s3 = boto3.client('s3') bucket_name = "softwareheritage" def download_contents(blob_id): key = f"content/{blob_id}" try: obj = s3.get_object(Bucket=bucket_name, Key=key) with gzip.GzipFile(fileobj=obj['Body']) as fin: content = fin.read().decode("utf-8", errors="ignore") return {"text": content, "download_success": True} except ClientError as e: if e.response['Error']['Code'] == 'NoSuchKey': print(f"File not found: {key}") return {"text": "", "download_success": False} else: raise ds = load_dataset("HuggingFaceTB/smollm-corpus", "python-edu", split="train", num_proc=num_proc) ds = ds.map(download_contents, input_columns="blob_id", num_proc=num_proc) # Filter out failed downloads ds = ds.filter(lambda x: x['download_success']) # Optionally, print the first example to verify the data print(ds[0]) ``` ## FineWeb-Edu (deduplicated) FineWeb-Edu-Dedup is a deduplicated subset of the [FineWeb-Edu](https://huggingface.co./datasets/HuggingFaceFW/fineweb-edu) dataset, containing 220 billion tokens of educational web pages. The source dataset was filtered using an educational quality classifier to retain only the highest quality educational content. For more information refer to the [FineWeb-v1 blog post](https://huggingface.co./spaces/HuggingFaceFW/blogpost-fineweb-v1) ### Dataset Features * `text (string)`: The web page's text content. * `id (string)`: Unique ID of the web page. * `metadata (struct)`: Metadata about the web page, including: * `dump (string)`: The source CommonCrawl dump. * `url (string)`: The URL of the web page. * `date (timestamp[s])`: The date the web page was captured. * `file_path (string)`: The file path of the commoncrawl snapshot. * `language (string)`: The language of the web page. * `language_score (float64)`: The language probability. * `token_count (int64)`: The token count of the web page (gpt2 tokenizer). * `score (float64)`: The educational quality score. * `int_score (int64)`: The rounded educational quality score. ### Loading the dataset ```python from datasets import load_dataset ds = load_dataset("HuggingFaceTB/smollm-corpus", "fineweb-edu-dedup", split="train", num_proc=16) print(ds[0]) ``` ## Citation ``` @software{benallal2024smollmcorpus, author = {Ben Allal, Loubna and Lozhkov, Anton and Penedo, Guilherme and Wolf, Thomas and von Werra, Leandro}, title = {SmolLM-Corpus}, month = July, year = 2024, url = {https://huggingface.co./datasets/HuggingFaceTB/smollm-corpus} } ```

Jackmin108/xtreme

Jackmin108

--- license: apache-2.0 configs: - config_name: mnli data_files: - split: train path: - "mnli/train-0000.parquet" - "mnli/train-0001.parquet" - "mnli/train-0002.parquet" - "mnli/train-0003.parquet" features: sentence1: dtype: string _type: Value sentence2: dtype: string _type: Value label: names: - entailment - neutral - contradiction _type: ClassLabel idx: dtype: int32 _type: Value - config_name: tydiqa data_files: - split: train path: - "tydiqa/ko/train.parquet" - "tydiqa/sw/train.parquet" - "tydiqa/ru/train.parquet" - "tydiqa/te/train.parquet" - "tydiqa/ar/train.parquet" - "tydiqa/fi/train.parquet" - "tydiqa/bn/train.parquet" - "tydiqa/en/train.parquet" - "tydiqa/id/train.parquet" - split: validation path: - "tydiqa/ko/validation.parquet" - "tydiqa/sw/validation.parquet" - "tydiqa/ru/validation.parquet" - "tydiqa/te/validation.parquet" - "tydiqa/ar/validation.parquet" - "tydiqa/fi/validation.parquet" - "tydiqa/bn/validation.parquet" - "tydiqa/en/validation.parquet" - "tydiqa/id/validation.parquet" - config_name: tydiqa.ko data_files: - split: train path: "tydiqa/ko/train.parquet" - split: validation path: "tydiqa/ko/validation.parquet" - config_name: tydiqa.sw data_files: - split: train path: "tydiqa/sw/train.parquet" - split: validation path: "tydiqa/sw/validation.parquet" - config_name: tydiqa.ru data_files: - split: train path: "tydiqa/ru/train.parquet" - split: validation path: "tydiqa/ru/validation.parquet" - config_name: tydiqa.te data_files: - split: train path: "tydiqa/te/train.parquet" - split: validation path: "tydiqa/te/validation.parquet" - config_name: tydiqa.ar data_files: - split: train path: "tydiqa/ar/train.parquet" - split: validation path: "tydiqa/ar/validation.parquet" - config_name: tydiqa.fi data_files: - split: train path: "tydiqa/fi/train.parquet" - split: validation path: "tydiqa/fi/validation.parquet" - config_name: tydiqa.bn data_files: - split: train path: "tydiqa/bn/train.parquet" - split: validation path: "tydiqa/bn/validation.parquet" - config_name: tydiqa.en data_files: - split: train path: "tydiqa/en/train.parquet" - split: validation path: "tydiqa/en/validation.parquet" - config_name: tydiqa.id data_files: - split: train path: "tydiqa/id/train.parquet" - split: validation path: "tydiqa/id/validation.parquet" - config_name: xnli data_files: - split: validation path: - xnli/hi/validation.parquet - xnli/zh/validation.parquet - xnli/sw/validation.parquet - xnli/tr/validation.parquet - xnli/en/validation.parquet - xnli/th/validation.parquet - xnli/ru/validation.parquet - xnli/ar/validation.parquet - xnli/vi/validation.parquet - xnli/bg/validation.parquet - xnli/es/validation.parquet - xnli/el/validation.parquet - xnli/fr/validation.parquet - xnli/ur/validation.parquet - xnli/de/validation.parquet - split: test path: - xnli/hi/test.parquet - xnli/zh/test.parquet - xnli/sw/test.parquet - xnli/tr/test.parquet - xnli/en/test.parquet - xnli/th/test.parquet - xnli/ru/test.parquet - xnli/ar/test.parquet - xnli/vi/test.parquet - xnli/bg/test.parquet - xnli/es/test.parquet - xnli/el/test.parquet - xnli/fr/test.parquet - xnli/ur/test.parquet - xnli/de/test.parquet features: sentence1: dtype: string _type: Value sentence2: dtype: string _type: Value label: names: - entailment - neutral - contradiction _type: ClassLabel idx: dtype: int32 _type: Value - config_name: xnli.hi data_files: - split: validation path: xnli/hi/validation.parquet - split: test path: xnli/hi/test.parquet features: sentence1: dtype: string _type: Value sentence2: dtype: string _type: Value label: names: - entailment - neutral - contradiction _type: ClassLabel idx: dtype: int32 _type: Value - config_name: xnli.zh data_files: - split: validation path: xnli/zh/validation.parquet - split: test path: xnli/zh/test.parquet features: sentence1: dtype: string _type: Value sentence2: dtype: string _type: Value label: names: - entailment - neutral - contradiction _type: ClassLabel idx: dtype: int32 _type: Value - config_name: xnli.sw data_files: - split: validation path: xnli/sw/validation.parquet - split: test path: xnli/sw/test.parquet features: sentence1: dtype: string _type: Value sentence2: dtype: string _type: Value label: names: - entailment - neutral - contradiction _type: ClassLabel idx: dtype: int32 _type: Value - config_name: xnli.tr data_files: - split: validation path: xnli/tr/validation.parquet - split: test path: xnli/tr/test.parquet features: sentence1: dtype: string _type: Value sentence2: dtype: string _type: Value label: names: - entailment - neutral - contradiction _type: ClassLabel idx: dtype: int32 _type: Value - config_name: xnli.en data_files: - split: validation path: xnli/en/validation.parquet - split: test path: xnli/en/test.parquet features: sentence1: dtype: string _type: Value sentence2: dtype: string _type: Value label: names: - entailment - neutral - contradiction _type: ClassLabel idx: dtype: int32 _type: Value - config_name: xnli.th data_files: - split: validation path: xnli/th/validation.parquet - split: test path: xnli/th/test.parquet features: sentence1: dtype: string _type: Value sentence2: dtype: string _type: Value label: names: - entailment - neutral - contradiction _type: ClassLabel idx: dtype: int32 _type: Value - config_name: xnli.ru data_files: - split: validation path: xnli/ru/validation.parquet - split: test path: xnli/ru/test.parquet features: sentence1: dtype: string _type: Value sentence2: dtype: string _type: Value label: names: - entailment - neutral - contradiction _type: ClassLabel idx: dtype: int32 _type: Value - config_name: xnli.ar data_files: - split: validation path: xnli/ar/validation.parquet - split: test path: xnli/ar/test.parquet features: sentence1: dtype: string _type: Value sentence2: dtype: string _type: Value label: names: - entailment - neutral - contradiction _type: ClassLabel idx: dtype: int32 _type: Value - config_name: xnli.vi data_files: - split: validation path: xnli/vi/validation.parquet - split: test path: xnli/vi/test.parquet features: sentence1: dtype: string _type: Value sentence2: dtype: string _type: Value label: names: - entailment - neutral - contradiction _type: ClassLabel idx: dtype: int32 _type: Value - config_name: xnli.bg data_files: - split: validation path: xnli/bg/validation.parquet - split: test path: xnli/bg/test.parquet features: sentence1: dtype: string _type: Value sentence2: dtype: string _type: Value label: names: - entailment - neutral - contradiction _type: ClassLabel idx: dtype: int32 _type: Value - config_name: xnli.es data_files: - split: validation path: xnli/es/validation.parquet - split: test path: xnli/es/test.parquet features: sentence1: dtype: string _type: Value sentence2: dtype: string _type: Value label: names: - entailment - neutral - contradiction _type: ClassLabel idx: dtype: int32 _type: Value - config_name: xnli.el data_files: - split: validation path: xnli/el/validation.parquet - split: test path: xnli/el/test.parquet features: sentence1: dtype: string _type: Value sentence2: dtype: string _type: Value label: names: - entailment - neutral - contradiction _type: ClassLabel idx: dtype: int32 _type: Value - config_name: xnli.fr data_files: - split: validation path: xnli/fr/validation.parquet - split: test path: xnli/fr/test.parquet features: sentence1: dtype: string _type: Value sentence2: dtype: string _type: Value label: names: - entailment - neutral - contradiction _type: ClassLabel idx: dtype: int32 _type: Value - config_name: xnli.ur data_files: - split: validation path: xnli/ur/validation.parquet - split: test path: xnli/ur/test.parquet features: sentence1: dtype: string _type: Value sentence2: dtype: string _type: Value label: names: - entailment - neutral - contradiction _type: ClassLabel idx: dtype: int32 _type: Value - config_name: xnli.de data_files: - split: validation path: xnli/de/validation.parquet - split: test path: xnli/de/test.parquet features: sentence1: dtype: string _type: Value sentence2: dtype: string _type: Value label: names: - entailment - neutral - contradiction _type: ClassLabel idx: dtype: int32 _type: Value - config_name: paws-x.de data_files: - split: train path: paws-x/de/train.parquet - split: validation path: paws-x/de/validation.parquet - split: test path: paws-x/de/test.parquet features: sentence1: dtype: string _type: Value sentence2: dtype: string _type: Value label: names: - not_paraphrase - paraphrase _type: ClassLabel - config_name: paws-x.en data_files: - split: train path: paws-x/en/train.parquet - split: validation path: paws-x/en/validation.parquet - split: test path: paws-x/en/test.parquet features: sentence1: dtype: string _type: Value sentence2: dtype: string _type: Value label: names: - not_paraphrase - paraphrase _type: ClassLabel - config_name: paws-x.es data_files: - split: train path: paws-x/es/train.parquet - split: validation path: paws-x/es/validation.parquet - split: test path: paws-x/es/test.parquet features: sentence1: dtype: string _type: Value sentence2: dtype: string _type: Value label: names: - not_paraphrase - paraphrase _type: ClassLabel - config_name: paws-x.fr data_files: - split: train path: paws-x/fr/train.parquet - split: validation path: paws-x/fr/validation.parquet - split: test path: paws-x/fr/test.parquet features: sentence1: dtype: string _type: Value sentence2: dtype: string _type: Value label: names: - not_paraphrase - paraphrase _type: ClassLabel - config_name: paws-x.ja data_files: - split: train path: paws-x/ja/train.parquet - split: validation path: paws-x/ja/validation.parquet - split: test path: paws-x/ja/test.parquet features: sentence1: dtype: string _type: Value sentence2: dtype: string _type: Value label: names: - not_paraphrase - paraphrase _type: ClassLabel - config_name: paws-x.ko data_files: - split: train path: paws-x/ko/train.parquet - split: validation path: paws-x/ko/validation.parquet - split: test path: paws-x/ko/test.parquet features: sentence1: dtype: string _type: Value sentence2: dtype: string _type: Value label: names: - not_paraphrase - paraphrase _type: ClassLabel - config_name: paws-x.zh data_files: - split: train path: paws-x/zh/train.parquet - split: validation path: paws-x/zh/validation.parquet - split: test path: paws-x/zh/test.parquet features: sentence1: dtype: string _type: Value sentence2: dtype: string _type: Value label: names: - not_paraphrase - paraphrase _type: ClassLabel ---

lmms-lab/Video-MME

lmms-lab

--- dataset_info: config_name: videomme features: - name: video_id dtype: string - name: duration dtype: string - name: domain dtype: string - name: sub_category dtype: string - name: url dtype: string - name: videoID dtype: string - name: question_id dtype: string - name: task_type dtype: string - name: question dtype: string - name: options sequence: string - name: answer dtype: string splits: - name: test num_bytes: 1003241.0 num_examples: 2700 download_size: 405167 dataset_size: 1003241.0 configs: - config_name: videomme data_files: - split: test path: videomme/test-* ---

bigcode/self-oss-instruct-sc2-instructions

bigcode

--- dataset_info: features: - name: prompt dtype: string - name: fingerprint dtype: 'null' - name: seed dtype: string - name: sha1 dtype: string - name: id dtype: int64 - name: concepts sequence: string - name: instruction dtype: string splits: - name: train num_bytes: 1708698948 num_examples: 237517 download_size: 341570013 dataset_size: 1708698948 configs: - config_name: default data_files: - split: train path: data/train-* ---

Real-IAD/Real-IAD

Real-IAD

--- license: cc-by-nc-sa-4.0 pretty_name: Real-IAD size_categories: - 100B<n<1T --- Website: [https://realiad4ad.github.io/Real-IAD/](https://realiad4ad.github.io/Real-IAD/) Real-IAD is released for research purpose only. If your Hugging face is registrated by your college email address, we will approve your access request directly, otherwise please send an email to [email protected] from your affiliation email address. Thank your understanding and cooperation. A recommended application email format is: ---------------------------------------------------------------------- I am writing to request access to the Real-IAD for research purposes. Name: [Your Full Name] Affilication: [Name of your Institution/Organization] Title：[Your Title] Supervisor: [Name of your supervisor](This information is only necessary if you are a student) ---------------------------------------------------------------------- Evaluation Tool: [ADEval](https://pypi.org/project/ADEval/) - Install ADEval ```shell python3 -m pip install ADEval ``` - Execute Evaluation ```shell python3 -m adeval --sample_key_pat "([a-zA-Z][a-zA-Z0-9_]*_[0-9]{4}_[A-Z][A-Z_]*[A-Z])_C[0-9]_" some_object.pkl ``` where the result file `some_object.pkl` can be generated following the guidance of ADEval [ReadMe](https://github.com/winggan/adeval?tab=readme-ov-file#commandline-usage). For Real-IAD, we should generate 30 result files, one file per object given an experiment setting, i.e. `audiojack.pkl`, `bottle_cap.pkl`, ... > Note: the argument `--sample_key_pat` is identical for all experiment settings of Real-IAD

trl-internal-testing/zen

trl-internal-testing

--- dataset_info: - config_name: conversational_implicit_prompt_preference features: - name: chosen list: - name: content dtype: string - name: role dtype: string - name: rejected list: - name: content dtype: string - name: role dtype: string splits: - name: train num_bytes: 2755 num_examples: 17 - name: test num_bytes: 386 num_examples: 2 download_size: 6623 dataset_size: 3141 - config_name: conversational_language_modeling features: - name: messages list: - name: content dtype: string - name: role dtype: string splits: - name: train num_bytes: 1399 num_examples: 17 - name: test num_bytes: 210 num_examples: 2 download_size: 3723 dataset_size: 1609 - config_name: conversational_preference features: - name: prompt list: - name: content dtype: string - name: role dtype: string - name: chosen list: - name: content dtype: string - name: role dtype: string - name: rejected list: - name: content dtype: string - name: role dtype: string splits: - name: train num_bytes: 2070 num_examples: 17 - name: test num_bytes: 295 num_examples: 2 download_size: 8123 dataset_size: 2365 - config_name: conversational_prompt_completion features: - name: prompt list: - name: content dtype: string - name: role dtype: string - name: completion list: - name: content dtype: string - name: role dtype: string splits: - name: train num_bytes: 1467 num_examples: 17 - name: test num_bytes: 218 num_examples: 2 download_size: 5796 dataset_size: 1685 - config_name: conversational_prompt_only features: - name: prompt list: - name: content dtype: string - name: role dtype: string splits: - name: train num_bytes: 821 num_examples: 17 - name: test num_bytes: 107 num_examples: 2 download_size: 3326 dataset_size: 928 - config_name: conversational_unpaired_preference features: - name: prompt list: - name: content dtype: string - name: role dtype: string - name: completion list: - name: content dtype: string - name: role dtype: string - name: label dtype: bool splits: - name: train num_bytes: 1441 num_examples: 17 - name: test num_bytes: 219 num_examples: 2 download_size: 6421 dataset_size: 1660 - config_name: standard_implicit_prompt_preference features: - name: chosen dtype: string - name: rejected dtype: string splits: - name: train num_bytes: 1537 num_examples: 17 - name: test num_bytes: 258 num_examples: 2 download_size: 4330 dataset_size: 1795 - config_name: standard_language_modeling features: - name: text dtype: string splits: - name: train num_bytes: 744 num_examples: 17 - name: test num_bytes: 136 num_examples: 2 download_size: 2457 dataset_size: 880 - config_name: standard_preference features: - name: prompt dtype: string - name: chosen dtype: string - name: rejected dtype: string splits: - name: train num_bytes: 1213 num_examples: 17 - name: test num_bytes: 205 num_examples: 2 download_size: 4466 dataset_size: 1418 - config_name: standard_prompt_completion features: - name: prompt dtype: string - name: completion dtype: string splits: - name: train num_bytes: 812 num_examples: 17 - name: test num_bytes: 144 num_examples: 2 download_size: 3231 dataset_size: 956 - config_name: standard_prompt_only features: - name: prompt dtype: string splits: - name: train num_bytes: 460 num_examples: 17 - name: test num_bytes: 69 num_examples: 2 download_size: 2044 dataset_size: 529 - config_name: standard_stepwise features: - name: prompt dtype: string - name: completions sequence: string - name: label sequence: bool splits: - name: train num_bytes: 1402.9473684210527 num_examples: 17 - name: test num_bytes: 165.05263157894737 num_examples: 2 download_size: 5033 dataset_size: 1568.0 - config_name: standard_stepwise_supervision features: - name: prompt dtype: string - name: completions sequence: string - name: labels sequence: bool splits: - name: train num_bytes: 1382 num_examples: 17 - name: test num_bytes: 187 num_examples: 2 download_size: 5039 dataset_size: 1569 - config_name: standard_unpaired_preference features: - name: prompt dtype: string - name: completion dtype: string - name: label dtype: bool splits: - name: train num_bytes: 840 num_examples: 17 - name: test num_bytes: 131 num_examples: 2 download_size: 3861 dataset_size: 971 configs: - config_name: conversational_implicit_prompt_preference data_files: - split: train path: conversational_implicit_prompt_preference/train-* - split: test path: conversational_implicit_prompt_preference/test-* - config_name: conversational_language_modeling data_files: - split: train path: conversational_language_modeling/train-* - split: test path: conversational_language_modeling/test-* - config_name: conversational_preference data_files: - split: train path: conversational_preference/train-* - split: test path: conversational_preference/test-* - config_name: conversational_prompt_completion data_files: - split: train path: conversational_prompt_completion/train-* - split: test path: conversational_prompt_completion/test-* - config_name: conversational_prompt_only data_files: - split: train path: conversational_prompt_only/train-* - split: test path: conversational_prompt_only/test-* - config_name: conversational_unpaired_preference data_files: - split: train path: conversational_unpaired_preference/train-* - split: test path: conversational_unpaired_preference/test-* - config_name: standard_implicit_prompt_preference data_files: - split: train path: standard_implicit_prompt_preference/train-* - split: test path: standard_implicit_prompt_preference/test-* - config_name: standard_language_modeling data_files: - split: train path: standard_language_modeling/train-* - split: test path: standard_language_modeling/test-* - config_name: standard_preference data_files: - split: train path: standard_preference/train-* - split: test path: standard_preference/test-* - config_name: standard_prompt_completion data_files: - split: train path: standard_prompt_completion/train-* - split: test path: standard_prompt_completion/test-* - config_name: standard_prompt_only data_files: - split: train path: standard_prompt_only/train-* - split: test path: standard_prompt_only/test-* - config_name: standard_stepwise data_files: - split: train path: standard_stepwise/train-* - split: test path: standard_stepwise/test-* - config_name: standard_stepwise_supervision data_files: - split: train path: standard_stepwise_supervision/train-* - split: test path: standard_stepwise_supervision/test-* - config_name: standard_unpaired_preference data_files: - split: train path: standard_unpaired_preference/train-* - split: test path: standard_unpaired_preference/test-* ---

EleutherAI/race

EleutherAI

--- annotations_creators: - expert-generated language: - en language_creators: - found license: - other multilinguality: - monolingual pretty_name: RACE size_categories: - 10K<n<100K source_datasets: - original task_categories: - multiple-choice task_ids: - multiple-choice-qa paperswithcode_id: race dataset_info: --- # "race" Grouped by Article This is a modified version of https://huggingface.co./datasets/race that returns documents grouped by article context instead of by question. **Note:** This dataset currently only contains that test set of the ```high``` subset of the data. The original readme is contained below. # Dataset Card for "race" ## Table of Contents - [Dataset Description](#dataset-description) - [Dataset Summary](#dataset-summary) - [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards) - [Languages](#languages) - [Dataset Structure](#dataset-structure) - [Data Instances](#data-instances) - [Data Fields](#data-fields) - [Data Splits](#data-splits) - [Dataset Creation](#dataset-creation) - [Curation Rationale](#curation-rationale) - [Source Data](#source-data) - [Annotations](#annotations) - [Personal and Sensitive Information](#personal-and-sensitive-information) - [Considerations for Using the Data](#considerations-for-using-the-data) - [Social Impact of Dataset](#social-impact-of-dataset) - [Discussion of Biases](#discussion-of-biases) - [Other Known Limitations](#other-known-limitations) - [Additional Information](#additional-information) - [Dataset Curators](#dataset-curators) - [Licensing Information](#licensing-information) - [Citation Information](#citation-information) - [Contributions](#contributions) ## Dataset Description - **Homepage:** [http://www.cs.cmu.edu/~glai1/data/race/](http://www.cs.cmu.edu/~glai1/data/race/) - **Repository:** https://github.com/qizhex/RACE_AR_baselines - **Paper:** [RACE: Large-scale ReAding Comprehension Dataset From Examinations](https://arxiv.org/abs/1704.04683) - **Point of Contact:** [Guokun Lai](mailto:[email protected]), [Qizhe Xie](mailto:[email protected]) - **Size of downloaded dataset files:** 76.33 MB - **Size of the generated dataset:** 349.46 MB - **Total amount of disk used:** 425.80 MB ### Dataset Summary RACE is a large-scale reading comprehension dataset with more than 28,000 passages and nearly 100,000 questions. The dataset is collected from English examinations in China, which are designed for middle school and high school students. The dataset can be served as the training and test sets for machine comprehension. ### Supported Tasks and Leaderboards [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Languages [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ## Dataset Structure ### Data Instances #### all - **Size of downloaded dataset files:** 25.44 MB - **Size of the generated dataset:** 174.73 MB - **Total amount of disk used:** 200.17 MB An example of 'train' looks as follows. ``` This example was too long and was cropped: { "answer": "A", "article": "\"Schoolgirls have been wearing such short skirts at Paget High School in Branston that they've been ordered to wear trousers ins...", "example_id": "high132.txt", "options": ["short skirts give people the impression of sexualisation", "short skirts are too expensive for parents to afford", "the headmaster doesn't like girls wearing short skirts", "the girls wearing short skirts will be at the risk of being laughed at"], "question": "The girls at Paget High School are not allowed to wear skirts in that _ ." } ``` #### high - **Size of downloaded dataset files:** 25.44 MB - **Size of the generated dataset:** 140.12 MB - **Total amount of disk used:** 165.56 MB An example of 'train' looks as follows. ``` This example was too long and was cropped: { "answer": "A", "article": "\"Schoolgirls have been wearing such short skirts at Paget High School in Branston that they've been ordered to wear trousers ins...", "example_id": "high132.txt", "options": ["short skirts give people the impression of sexualisation", "short skirts are too expensive for parents to afford", "the headmaster doesn't like girls wearing short skirts", "the girls wearing short skirts will be at the risk of being laughed at"], "question": "The girls at Paget High School are not allowed to wear skirts in that _ ." } ``` #### middle - **Size of downloaded dataset files:** 25.44 MB - **Size of the generated dataset:** 34.61 MB - **Total amount of disk used:** 60.05 MB An example of 'train' looks as follows. ``` This example was too long and was cropped: { "answer": "B", "article": "\"There is not enough oil in the world now. As time goes by, it becomes less and less, so what are we going to do when it runs ou...", "example_id": "middle3.txt", "options": ["There is more petroleum than we can use now.", "Trees are needed for some other things besides making gas.", "We got electricity from ocean tides in the old days.", "Gas wasn't used to run cars in the Second World War."], "question": "According to the passage, which of the following statements is TRUE?" } ``` ### Data Fields The data fields are the same among all splits. #### all - `example_id`: a `string` feature. - `article`: a `string` feature. - `answer`: a `string` feature. - `question`: a `string` feature. - `options`: a `list` of `string` features. #### high - `example_id`: a `string` feature. - `article`: a `string` feature. - `answer`: a `string` feature. - `question`: a `string` feature. - `options`: a `list` of `string` features. #### middle - `example_id`: a `string` feature. - `article`: a `string` feature. - `answer`: a `string` feature. - `question`: a `string` feature. - `options`: a `list` of `string` features. ### Data Splits | name |train|validation|test| |------|----:|---------:|---:| |all |87866| 4887|4934| |high |62445| 3451|3498| |middle|25421| 1436|1436| ## Dataset Creation ### Curation Rationale [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Source Data #### Initial Data Collection and Normalization [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) #### Who are the source language producers? [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Annotations #### Annotation process [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) #### Who are the annotators? [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Personal and Sensitive Information [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ## Considerations for Using the Data ### Social Impact of Dataset [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Discussion of Biases [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Other Known Limitations [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ## Additional Information ### Dataset Curators [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Licensing Information http://www.cs.cmu.edu/~glai1/data/race/ 1. RACE dataset is available for non-commercial research purpose only. 2. All passages are obtained from the Internet which is not property of Carnegie Mellon University. We are not responsible for the content nor the meaning of these passages. 3. You agree not to reproduce, duplicate, copy, sell, trade, resell or exploit for any commercial purpose, any portion of the contexts and any portion of derived data. 4. We reserve the right to terminate your access to the RACE dataset at any time. ### Citation Information ``` @inproceedings{lai-etal-2017-race, title = "{RACE}: Large-scale {R}e{A}ding Comprehension Dataset From Examinations", author = "Lai, Guokun and Xie, Qizhe and Liu, Hanxiao and Yang, Yiming and Hovy, Eduard", booktitle = "Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing", month = sep, year = "2017", address = "Copenhagen, Denmark", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/D17-1082", doi = "10.18653/v1/D17-1082", pages = "785--794", } ``` ### Contributions Thanks to [@abarbosa94](https://github.com/abarbosa94), [@patrickvonplaten](https://github.com/patrickvonplaten), [@lewtun](https://github.com/lewtun), [@thomwolf](https://github.com/thomwolf), [@mariamabarham](https://github.com/mariamabarham) for adding this dataset.

stanfordnlp/sst2

stanfordnlp

--- annotations_creators: - crowdsourced language_creators: - found language: - en license: - unknown multilinguality: - monolingual size_categories: - 10K<n<100K source_datasets: - original task_categories: - text-classification task_ids: - sentiment-classification paperswithcode_id: sst pretty_name: Stanford Sentiment Treebank v2 dataset_info: features: - name: idx dtype: int32 - name: sentence dtype: string - name: label dtype: class_label: names: '0': negative '1': positive splits: - name: train num_bytes: 4681603 num_examples: 67349 - name: validation num_bytes: 106252 num_examples: 872 - name: test num_bytes: 216640 num_examples: 1821 download_size: 3331058 dataset_size: 5004495 configs: - config_name: default data_files: - split: train path: data/train-* - split: validation path: data/validation-* - split: test path: data/test-* --- # Dataset Card for [Dataset Name] ## Table of Contents - [Table of Contents](#table-of-contents) - [Dataset Description](#dataset-description) - [Dataset Summary](#dataset-summary) - [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards) - [Languages](#languages) - [Dataset Structure](#dataset-structure) - [Data Instances](#data-instances) - [Data Fields](#data-fields) - [Data Splits](#data-splits) - [Dataset Creation](#dataset-creation) - [Curation Rationale](#curation-rationale) - [Source Data](#source-data) - [Annotations](#annotations) - [Personal and Sensitive Information](#personal-and-sensitive-information) - [Considerations for Using the Data](#considerations-for-using-the-data) - [Social Impact of Dataset](#social-impact-of-dataset) - [Discussion of Biases](#discussion-of-biases) - [Other Known Limitations](#other-known-limitations) - [Additional Information](#additional-information) - [Dataset Curators](#dataset-curators) - [Licensing Information](#licensing-information) - [Citation Information](#citation-information) - [Contributions](#contributions) ## Dataset Description - **Homepage:** https://nlp.stanford.edu/sentiment/ - **Repository:** - **Paper:** [Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank](https://www.aclweb.org/anthology/D13-1170/) - **Leaderboard:** - **Point of Contact:** ### Dataset Summary The Stanford Sentiment Treebank is a corpus with fully labeled parse trees that allows for a complete analysis of the compositional effects of sentiment in language. The corpus is based on the dataset introduced by Pang and Lee (2005) and consists of 11,855 single sentences extracted from movie reviews. It was parsed with the Stanford parser and includes a total of 215,154 unique phrases from those parse trees, each annotated by 3 human judges. Binary classification experiments on full sentences (negative or somewhat negative vs somewhat positive or positive with neutral sentences discarded) refer to the dataset as SST-2 or SST binary. ### Supported Tasks and Leaderboards - `sentiment-classification` ### Languages The text in the dataset is in English (`en`). ## Dataset Structure ### Data Instances ``` {'idx': 0, 'sentence': 'hide new secretions from the parental units ', 'label': 0} ``` ### Data Fields - `idx`: Monotonically increasing index ID. - `sentence`: Complete sentence expressing an opinion about a film. - `label`: Sentiment of the opinion, either "negative" (0) or positive (1). The test set labels are hidden (-1). ### Data Splits | | train | validation | test | |--------------------|---------:|-----------:|-----:| | Number of examples | 67349 | 872 | 1821 | ## Dataset Creation ### Curation Rationale [More Information Needed] ### Source Data #### Initial Data Collection and Normalization [More Information Needed] #### Who are the source language producers? Rotten Tomatoes reviewers. ### Annotations #### Annotation process [More Information Needed] #### Who are the annotators? [More Information Needed] ### Personal and Sensitive Information [More Information Needed] ## Considerations for Using the Data ### Social Impact of Dataset [More Information Needed] ### Discussion of Biases [More Information Needed] ### Other Known Limitations [More Information Needed] ## Additional Information ### Dataset Curators [More Information Needed] ### Licensing Information Unknown. ### Citation Information ```bibtex @inproceedings{socher-etal-2013-recursive, title = "Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank", author = "Socher, Richard and Perelygin, Alex and Wu, Jean and Chuang, Jason and Manning, Christopher D. and Ng, Andrew and Potts, Christopher", booktitle = "Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing", month = oct, year = "2013", address = "Seattle, Washington, USA", publisher = "Association for Computational Linguistics", url = "https://www.aclweb.org/anthology/D13-1170", pages = "1631--1642", } ``` ### Contributions Thanks to [@albertvillanova](https://github.com/albertvillanova) for adding this dataset.

omegalabsinc/omega-voice

omegalabsinc

--- license: mit ---

IGNF/PASTIS-HD

IGNF

--- license: etalab-2.0 task_categories: - image-classification - image-segmentation tags: - remote sensing - Agricultural size_categories: - 1K<n<10K --- # 🌱 PASTIS-HD 🌿 Panoptic Agricultural Satellite TIme Series : optical time series, radar time series and very high resolution image [PASTIS](https://github.com/VSainteuf/pastis-benchmark) is a benchmark dataset for panoptic and semantic segmentation of agricultural parcels from satellite time series. It contains 2,433 patches within the French metropolitan territory with panoptic annotations (instance index + semantic label for each pixel). Each patch is a Sentinel-2 multispectral image time series of variable lentgh. This dataset have been extended in 2021 with aligned radar Sentinel-1 observations for all 2433 patches. For each patch, it constains approximately 70 observations of Sentinel-1 in ascending orbit, and 70 observations in descending orbit. Each each Sentinel1 observation is assembled into a 3-channel image: vertical polarization (VV), horizontal polarisation (VH), and the ratio vertical over horizontal polarization (VV/VH). This extension is named PASTIS-R. We extend PASTIS with aligned very high resolution satellite images from SPOT 6-7 constellation for all 2433 patches in addition to the Sentinel-1 and 2 time series. The image are resampled to a 1m resolution and converted to 8 bits. This enhancement significantly improves the dataset's spatial content, providing more granular information for agricultural parcel segmentation. **PASTIS-HD** can be used to evaluate multi-modal fusion methods (with optical time series, radar time series and VHR images) for parcel-based classification, semantic segmentation, and panoptic segmentation. ## Dataset in numbers 🛰️ Sentinel 2 | 🛰️ Sentinel 1 | 🛰️ **SPOT 6-7 VHR** | 🗻 Annotations :-------------------------------------------- | :-------------------------------------------------- | :------------------------------| :------------------------------ ➡️ 2,433 time series | ➡️ 2 time 2,433 time series | ➡️ **2,433 images** | 124,422 individual parcels ➡️ 10m / pixel | ➡️ 10m / pixel | ➡️ **1.5m / pixel** | covers ~4,000 km² ➡️ 128x128 pixels / images | ➡️ 128x128 pixels / images | ➡️ **1280x1280 pixels / images** | over 2B pixels ➡️ 38-61 acquisitions / series | ➡️ ~ 70 acquisitions / series | ➡️ **One observation** | 18 crop types ➡️ 10 spectral bands |➡️ 2 spectral bands | ➡️ **3 spectral bands** | ⚠️ The **SPOT data are natively 1.5m resolution**, but we over-sampled them at 1m to align them pixel-perfect with Sentinel data.  ## Data loading The Github repository associated to this dataset contains a PyTorch dataset class of [the OmniSat repository](https://github.com/gastruc/OmniSat/blob/main/src/data/Pastis.py) that can be readily used to load data for training models on PASTIS-HD. The time series contained in PASTIS have variable lengths. The Sentinel 1 and 2 time series are stored in numpy array. The SPOT images are in TIFF format. The annotations are in numpy array too. ⚠️ The S2 and S1 folders contains more than 2433 files on the contrary to the labels folder. Some patches are not labelled and not used for training. The relevant information can be find in the metadata.geojson file (with 2433 entries), which is used as an index by the dataloader. ### Remark about the folder names ⚠️ The **DATA_S1A** folder contains the Sentinel-1 **ascendent** images whereas the **DATA_S1D** folder contains the Sentinel-1 **descendant** images. ## Ground Truth Annotations The agricultural parcels are grouped into 18 different crop classes as shown in the table below. The backgroud class corresponds to non-agricultural land, and the void label for parcels that are mostly outside their patch.  Additional information about the dataset can be found in the documentation/pastis-documentation.pdf document. ## Credits - The Sentinel imagery used in PASTIS was retrieved from [THEIA](www.theia.land.fr): "Value-added data processed by the CNES for the Theia www.theia.land.fr data cluster using Copernicus data. The treatments use algorithms developed by Theia’s Scientific Expertise Centres. " - The annotations used in PASTIS stem from the French [land parcel identification system](https://www.data.gouv.fr/en/datasets/registre-parcellaire-graphique-rpg-contours-des-parcelles-et-ilots-culturaux-et-leur-groupe-de-cultures-majoritaire/) produced by IGN. - The SPOT images are opendata thanks to the Dataterra Dinamis initiative in the case of the ["Couverture France DINAMIS"](https://dinamis.data-terra.org/opendata/) program. ## References If you use PASTIS please cite the [related paper](https://arxiv.org/abs/2107.07933): ``` @article{garnot2021panoptic, title={Panoptic Segmentation of Satellite Image Time Series with Convolutional Temporal Attention Networks}, author={Sainte Fare Garnot, Vivien and Landrieu, Loic}, journal={ICCV}, year={2021} } ``` For the PASTIS-R optical-radar fusion dataset, please also cite [this paper](https://arxiv.org/abs/2112.07558v1): ``` @article{garnot2021mmfusion, title = {Multi-modal temporal attention models for crop mapping from satellite time series}, journal = {ISPRS Journal of Photogrammetry and Remote Sensing}, year = {2022}, doi = {https://doi.org/10.1016/j.isprsjprs.2022.03.012}, author = {Vivien {Sainte Fare Garnot} and Loic Landrieu and Nesrine Chehata}, } ``` For the PASTIS-HD with the 3 modalities optical-radar time series plus VHR images dataset, please also cite [this paper](https://arxiv.org/abs/2404.08351): ``` @article{astruc2024omnisat, title={Omni{S}at: {S}elf-Supervised Modality Fusion for {E}arth Observation}, author={Astruc, Guillaume and Gonthier, Nicolas and Mallet, Clement and Landrieu, Loic}, journal={ECCV}, year={2024} } ```

pico-lm/pretokenized-dolma

pico-lm

--- license: apache-2.0 language: - en pretty_name: 'Pico Dataset: Pre-tokenized, Pre-shuffled Dolma' size_categories: - 100B<n<1T --- ## The Pico Dataset A pre-tokenized, pre-shuffled version of [Dolma](https://huggingface.co./datasets/allenai/dolma), the high-quality text corpus from AI2. ### Overview The Pico dataset simplifies training by providing: - Pre-tokenized text in chunks of 2048 tokens, using the [OLMo Tokenizer](https://huggingface.co./allenai/OLMo-7B-0724-hf/blob/main/tokenizer_config.json) - Pre-shuffled data for consistent training - Streaming-friendly format - 420B tokens total (perfect for 200K steps at batch size 1024) ### Benefits - **Storage Efficient**: No need to download the full 10TB Dolma dataset - **Memory Efficient**: Stream data directly with `load_dataset(..., streaming=True)` - **Reproducible**: All models see identical data in identical order - **Fast**: Skip tokenization during training - **Simple**: Minimal boilerplate code needed ### Usage 1. Set up HuggingFace credentials in `.env`: ``` HF_USERNAME=your_username HF_TOKEN=your_token # Get from https://huggingface.co./settings/tokens ``` 2. Set up in python: ``` from datasets import load_dataset dataset = load_dataset("pico-lm/pretokenized-dolma", streaming=True) ```

mlfoundations/MINT-1T-PDF-CC-2023-23

mlfoundations

--- license: cc-by-4.0 task_categories: - image-to-text - text-generation language: - en tags: - multimodal pretty_name: MINT-1T size_categories: - 100B<n<1T --- <h1 align="center"> 🍃 MINT-1T:<br>Scaling Open-Source Multimodal Data by 10x:<br> A Multimodal Dataset with One Trillion Tokens </h1> 🍃 MINT-1T is an open-source **M**ultimodal **INT**erleaved dataset with 1 trillion text tokens and 3.4 billion images, a 10x scale-up from existing open-source datasets. Additionally, we include previously untapped sources such as PDFs and ArXiv papers. 🍃 MINT-1T is designed to facilitate research in multimodal pretraining. 🍃 MINT-1T is created by a team from the University of Washington in collaboration with Salesforce Research, other academic institutions including Stanford University, University of Texas at Austin, and University of California Berkeley. You are currently viewing a subset of the PDF portion of 🍃 MINT-1T associated with CommonCrawl dump `CC-2023-23`. For other PDF, HTML, and ArXiv subsets, refer to the [🍃 MINT-1T collection](https://huggingface.co./collections/mlfoundations/mint-1t-6690216ca4d0df7e518dde1c).  ## Updates ### 9/19/24 We have removed roughly 10% of the PDF samples as there was a mismatch between the frames in the TIFF images and the document metadata. ### 8/8/24 We have become aware that the image hashes in the PDF subset of MINT-1T do not match the images in the documents. We want to emphasize that the images for each document are correct, and only the image hashes in the documents' metadata are mislabeled. ## Dataset Details ### Dataset Sources - **Repository**: https://github.com/mlfoundations/MINT-1T - **Paper:** https://arxiv.org/abs/2406.11271 - **Blog:** https://blog.salesforceairesearch.com/mint-1t/ ## Uses ### Direct Use <!-- This section describes suitable use cases for the dataset. --> 🍃 MINT-1T is designed to facilitate research in multimodal pretraining. The dataset can be used for training multimodal models that can reson about interleaved text and images sequences such as [Idefics2](https://huggingface.co./HuggingFaceM4/idefics2-8b), [XGen-MM](https://huggingface.co./Salesforce/xgen-mm-phi3-mini-instruct-r-v1), and [Chameleon](https://huggingface.co./facebook/chameleon-30b). ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the dataset will not work well for. --> 🍃 MINT-1T was built to make research into large multimodal models more accessible. Using the dataset to train models that ingest or generate personally identifying information (such as images of people’s faces and other sensitive content) as well as military applications are all inappropriate use cases of 🍃 MINT-1T. ## Dataset Creation ### Curation Rationale 🍃 MINT-1T was created to address a significant gap in the open-source domain by providing a large-scale multimodal interleaved dataset for pre-training large multimodal models. This dataset aims to be a valuable resource for the research community, facilitating open science in multimodal pretraining. ### Source Data The dataset is a comprehensive collection of multimodal documents from various sources: - HTML documents: Filtered from CommonCrawl WARC dumps spanning from 2017 to 2024 - PDF documents: Extracted from CommonCrawl WAT dumps covering 2023 to 2024 - ArXiv documents: A subset of papers from the ArXiv repository In total, 🍃 MINT-1T contains 1056.8 million documents, broken down as follows: - 1029.4 million HTML documents - 24.0 million PDF documents - 0.6 million ArXiv documents #### Data Collection and Processing The data collection and processing involved several steps: 1. Document Extraction: - HTML documents were parsed from CommonCrawl WARC files - PDF documents were extracted from CommonCrawl WAT files - ArXiv papers were directly sourced from ArXiv S3 buckets 2. Filtering Process: - Applied text quality filters to ensure content relevance and readability - Removed duplicate content at both paragraph and document levels - Filtered out undesirable content based on predefined criteria - Verified image availability and quality for HTML documents - Limited PDF size to 50MB and 50 pages to manage dataset size and quality 3. Image Processing: - Used NSFW image detection to remove pornographic or otherwise undesirable images - Removed images smaller than 150 pixels or larger than 20,000 pixels - Adjusted aspect ratio thresholds for HTML (2:1) and PDF (3:1) to preserve scientific figures 4. Text Processing: - Used fasttext for language identification, focusing on English content - Masked personally identifiable information such as email addresses and IP addresses - Applied paragraph and document-level deduplication using Bloom filters 5. PDF Specific Processing: - Used PyMuPDF for parsing PDFs and extracting reading order - Clustered text blocks based on columns and ordered from top left to bottom right 6. ArXiv Specific Processing: - Used TexSoup to parse LaTeX source code and interleave images with text - Cleaned up LaTeX code by removing imports, bibliography, tables, and citation tags Various open-source tools were utilized in this process, including fasttext, [PyMuPDF](https://github.com/pymupdf/PyMuPDF), and [DCLM](https://www.datacomp.ai/dclm/) and [bff](https://github.com/revbucket/bff) for deduplication and content filtering. #### Personal and Sensitive Information Despite sourcing from public web data, significant efforts were made to minimize the inclusion of personal and sensitive information: - Email addresses and IP addresses were masked to protect privacy - An NSFW image classifierto remove inappropriate visual content - URLs containing substrings associated with undesirable or sensitive content were filtered out However, users should be aware that as the data originates from the public web, it may still contain some sensitive or personal information. The dataset creators acknowledge this limitation and advise users to exercise caution and potentially apply additional filtering based on their specific use cases. ## Bias, Risks, and Limitations Several potential biases, risks, and limitations have been identified: 1. Data Bias: As the dataset is sourced from web crawls, it may inherit biases present in online content. 2. Content Risks: Despite extensive filtering, there's a possibility that some offensive, insensitive, or inappropriate content may remain in the dataset. 3. Image Availability: The dataset relies on external image URLs, which may become unavailable over time due to link rot, potentially affecting the dataset's long-term usability. 4. PDF Parsing Limitations: The current method for extracting reading order from PDFs may not always accurately capture the intended flow, especially for documents with complex layouts. 5. Potential Legal and Ethical Concerns: While efforts were made to respect robots.txt files and remove sensitive information, there may still be content that individuals did not explicitly consent to include. ### Recommendations Given these considerations, the following recommendations are provided: 1. Additional Filtering: Users are strongly encouraged to apply additional filtering based on their specific use case and ethical considerations. 2. Inappropriate Use Cases: The dataset is not recommended for applications involving the processing or generation of personally identifying information, nor for military applications. 3. Legal Compliance: Users should independently verify compliance with applicable laws before employing MINT-1T for commercial purposes. 4. Bias Awareness: Researchers and developers should be cognizant of potential biases in the dataset and consider their impact on model training and outputs. ## License We release 🍃 MINT-1T under a CC-BY-4.0 license, designating it primarily as a research artifact. While the dataset is freely available, users are responsible for ensuring its legal use in commercial settings. Users must independently verify compliance with applicable laws before employing MINT-1T for commercial purposes. ## Citation ``` @article{awadalla2024mint1t, title={MINT-1T: Scaling Open-Source Multimodal Data by 10x: A Multimodal Dataset with One Trillion Tokens}, author={Anas Awadalla and Le Xue and Oscar Lo and Manli Shu and Hannah Lee and Etash Kumar Guha and Matt Jordan and Sheng Shen and Mohamed Awadalla and Silvio Savarese and Caiming Xiong and Ran Xu and Yejin Choi and Ludwig Schmidt}, year={2024} } ```

ruslanmv/ai-medical-chatbot

ruslanmv

--- configs: - config_name: default data_files: - path: dialogues.* split: train dataset_info: dataset_size: 141665910 download_size: 141665910 features: - dtype: string name: Description - dtype: string name: Patient - dtype: string name: Doctor splits: - name: train num_bytes: 141665910 num_examples: 256916 --- # AI Medical Chatbot Dataset This is an experimental Dataset designed to run a Medical Chatbot It contains at least 250k dialogues between a Patient and a Doctor. [](https://huggingface.co./spaces/ruslanmv/AI-Medical-Chatbot) ## Playground ChatBot [ruslanmv/AI-Medical-Chatbot](https://huggingface.co./spaces/ruslanmv/AI-Medical-Chatbot) For furter information visit the project here: [https://github.com/ruslanmv/ai-medical-chatbot](https://github.com/ruslanmv/ai-medical-chatbot)

cornell-movie-review-data/rotten_tomatoes

cornell-movie-review-data

--- annotations_creators: - crowdsourced language_creators: - crowdsourced language: - en license: - unknown multilinguality: - monolingual size_categories: - 1K<n<10K source_datasets: - original task_categories: - text-classification task_ids: - sentiment-classification paperswithcode_id: mr pretty_name: RottenTomatoes - MR Movie Review Data dataset_info: features: - name: text dtype: string - name: label dtype: class_label: names: '0': neg '1': pos splits: - name: train num_bytes: 1074810 num_examples: 8530 - name: validation num_bytes: 134679 num_examples: 1066 - name: test num_bytes: 135972 num_examples: 1066 download_size: 487770 dataset_size: 1345461 train-eval-index: - config: default task: text-classification task_id: binary_classification splits: train_split: train eval_split: test col_mapping: text: text label: target metrics: - type: accuracy name: Accuracy - type: f1 name: F1 args: average: binary - type: f1 name: F1 micro args: average: micro - type: f1 name: F1 weighted args: average: weighted - type: precision name: Precision macro args: average: macro - type: precision name: Precision micro args: average: micro - type: precision name: Precision weighted args: average: weighted - type: recall name: Recall macro args: average: macro - type: recall name: Recall micro args: average: micro - type: recall name: Recall weighted args: average: weighted --- # Dataset Card for "rotten_tomatoes" ## Table of Contents - [Dataset Description](#dataset-description) - [Dataset Summary](#dataset-summary) - [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards) - [Languages](#languages) - [Dataset Structure](#dataset-structure) - [Data Instances](#data-instances) - [Data Fields](#data-fields) - [Data Splits](#data-splits) - [Dataset Creation](#dataset-creation) - [Curation Rationale](#curation-rationale) - [Source Data](#source-data) - [Annotations](#annotations) - [Personal and Sensitive Information](#personal-and-sensitive-information) - [Considerations for Using the Data](#considerations-for-using-the-data) - [Social Impact of Dataset](#social-impact-of-dataset) - [Discussion of Biases](#discussion-of-biases) - [Other Known Limitations](#other-known-limitations) - [Additional Information](#additional-information) - [Dataset Curators](#dataset-curators) - [Licensing Information](#licensing-information) - [Citation Information](#citation-information) - [Contributions](#contributions) ## Dataset Description - **Homepage:** [http://www.cs.cornell.edu/people/pabo/movie-review-data/](http://www.cs.cornell.edu/people/pabo/movie-review-data/) - **Repository:** [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) - **Paper:** [https://arxiv.org/abs/cs/0506075](https://arxiv.org/abs/cs/0506075) - **Point of Contact:** [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) - **Size of downloaded dataset files:** 0.49 MB - **Size of the generated dataset:** 1.34 MB - **Total amount of disk used:** 1.84 MB ### Dataset Summary Movie Review Dataset. This is a dataset of containing 5,331 positive and 5,331 negative processed sentences from Rotten Tomatoes movie reviews. This data was first used in Bo Pang and Lillian Lee, ``Seeing stars: Exploiting class relationships for sentiment categorization with respect to rating scales.'', Proceedings of the ACL, 2005. ### Supported Tasks and Leaderboards [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Languages [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ## Dataset Structure ### Data Instances #### default - **Size of downloaded dataset files:** 0.49 MB - **Size of the generated dataset:** 1.34 MB - **Total amount of disk used:** 1.84 MB An example of 'validation' looks as follows. ``` { "label": 1, "text": "Sometimes the days and nights just drag on -- it 's the morning that make me feel alive . And I have one thing to thank for that : pancakes . " } ``` ### Data Fields The data fields are the same among all splits. #### default - `text`: a `string` feature. - `label`: a classification label, with possible values including `neg` (0), `pos` (1). ### Data Splits Reads Rotten Tomatoes sentences and splits into 80% train, 10% validation, and 10% test, as is the practice set out in Jinfeng Li, ``TEXTBUGGER: Generating Adversarial Text Against Real-world Applications.'' | name |train|validation|test| |-------|----:|---------:|---:| |default| 8530| 1066|1066| ## Dataset Creation ### Curation Rationale [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Source Data #### Initial Data Collection and Normalization [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) #### Who are the source language producers? [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Annotations #### Annotation process [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) #### Who are the annotators? [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Personal and Sensitive Information [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ## Considerations for Using the Data ### Social Impact of Dataset [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Discussion of Biases [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Other Known Limitations [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ## Additional Information ### Dataset Curators [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Licensing Information [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Citation Information ``` @InProceedings{Pang+Lee:05a, author = {Bo Pang and Lillian Lee}, title = {Seeing stars: Exploiting class relationships for sentiment categorization with respect to rating scales}, booktitle = {Proceedings of the ACL}, year = 2005 } ``` ### Contributions Thanks to [@thomwolf](https://github.com/thomwolf), [@jxmorris12](https://github.com/jxmorris12) for adding this dataset.

ptb-text-only/ptb_text_only

ptb-text-only

--- annotations_creators: - expert-generated language_creators: - found language: - en license: - other license_details: LDC User Agreement for Non-Members multilinguality: - monolingual size_categories: - 10K<n<100K source_datasets: - original task_categories: - text-generation - fill-mask task_ids: - language-modeling - masked-language-modeling paperswithcode_id: null pretty_name: Penn Treebank dataset_info: features: - name: sentence dtype: string config_name: penn_treebank splits: - name: train num_bytes: 5143706 num_examples: 42068 - name: test num_bytes: 453710 num_examples: 3761 - name: validation num_bytes: 403156 num_examples: 3370 download_size: 5951345 dataset_size: 6000572 --- # Dataset Card for Penn Treebank ## Table of Contents - [Dataset Description](#dataset-description) - [Dataset Summary](#dataset-summary) - [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards) - [Languages](#languages) - [Dataset Structure](#dataset-structure) - [Data Instances](#data-instances) - [Data Fields](#data-fields) - [Data Splits](#data-splits) - [Dataset Creation](#dataset-creation) - [Curation Rationale](#curation-rationale) - [Source Data](#source-data) - [Annotations](#annotations) - [Personal and Sensitive Information](#personal-and-sensitive-information) - [Considerations for Using the Data](#considerations-for-using-the-data) - [Social Impact of Dataset](#social-impact-of-dataset) - [Discussion of Biases](#discussion-of-biases) - [Other Known Limitations](#other-known-limitations) - [Additional Information](#additional-information) - [Dataset Curators](#dataset-curators) - [Licensing Information](#licensing-information) - [Citation Information](#citation-information) - [Contributions](#contributions) ## Dataset Description - **Homepage:** https://catalog.ldc.upenn.edu/LDC99T42 - **Repository:** 'https://raw.githubusercontent.com/wojzaremba/lstm/master/data/ptb.train.txt', 'https://raw.githubusercontent.com/wojzaremba/lstm/master/data/ptb.valid.txt', 'https://raw.githubusercontent.com/wojzaremba/lstm/master/data/ptb.test.txt' - **Paper:** https://www.aclweb.org/anthology/J93-2004.pdf - **Leaderboard:** [Needs More Information] - **Point of Contact:** [Needs More Information] ### Dataset Summary This is the Penn Treebank Project: Release 2 CDROM, featuring a million words of 1989 Wall Street Journal material. The rare words in this version are already replaced with <unk> token. The numbers are replaced with <N> token. ### Supported Tasks and Leaderboards Language Modelling ### Languages The text in the dataset is in American English ## Dataset Structure ### Data Instances [Needs More Information] ### Data Fields [Needs More Information] ### Data Splits [Needs More Information] ## Dataset Creation ### Curation Rationale [Needs More Information] ### Source Data #### Initial Data Collection and Normalization [Needs More Information] #### Who are the source language producers? [Needs More Information] ### Annotations #### Annotation process [Needs More Information] #### Who are the annotators? [Needs More Information] ### Personal and Sensitive Information [Needs More Information] ## Considerations for Using the Data ### Social Impact of Dataset [Needs More Information] ### Discussion of Biases [Needs More Information] ### Other Known Limitations [Needs More Information] ## Additional Information ### Dataset Curators [Needs More Information] ### Licensing Information Dataset provided for research purposes only. Please check dataset license for additional information. ### Citation Information @article{marcus-etal-1993-building, title = "Building a Large Annotated Corpus of {E}nglish: The {P}enn {T}reebank", author = "Marcus, Mitchell P. and Santorini, Beatrice and Marcinkiewicz, Mary Ann", journal = "Computational Linguistics", volume = "19", number = "2", year = "1993", url = "https://www.aclweb.org/anthology/J93-2004", pages = "313--330", } ### Contributions Thanks to [@harshalmittal4](https://github.com/harshalmittal4) for adding this dataset.

mteb/arguana

mteb

--- language: - en multilinguality: - monolingual task_categories: - text-retrieval source_datasets: - arguana task_ids: - document-retrieval config_names: - corpus tags: - text-retrieval dataset_info: - config_name: default features: - name: query-id dtype: string - name: corpus-id dtype: string - name: score dtype: float64 splits: - name: test num_bytes: 111736 num_examples: 1406 - config_name: corpus features: - name: _id dtype: string - name: title dtype: string - name: text dtype: string splits: - name: corpus num_bytes: 9388094 num_examples: 8674 - config_name: queries features: - name: _id dtype: string - name: text dtype: string splits: - name: queries num_bytes: 1743698 num_examples: 1406 configs: - config_name: default data_files: - split: test path: qrels/test.jsonl - config_name: corpus data_files: - split: corpus path: corpus.jsonl - config_name: queries data_files: - split: queries path: queries.jsonl ---

DL3DV/DL3DV-ALL-480P

DL3DV

--- tags: - 3D Vision - NeRF - 3D Gaussian - Dataset - Novel View Synthesis - Text to 3D - Image to 3D pretty_name: Dl3DV-Dataset size_categories: - 100B<n<1T --- # DL3DV-Dataset This repo has all the 480P frames with camera poses of DL3DV-10K Dataset. We are working hard to review all the dataset to avoid sensitive information. Thank you for your patience. # Download If you have enough space, you can use git to download a dataset from huggingface. See this [link](https://huggingface.co./docs/hub/en/datasets-downloading). [480P](https://huggingface.co./datasets/DL3DV/DL3DV-ALL-480P)/[960P](https://huggingface.co./datasets/DL3DV/DL3DV-ALL-960P) versions should satisfies most needs. If you do not have enough space, we further provide a [download script](https://github.com/DL3DV-10K/Dataset/blob/main/scripts/download.py) here to download a subset. The usage: ```Bash usage: download.py [-h] --odir ODIR --subset {1K,2K,3K,4K,5K,6K,7K,8K,9K,10K} --resolution {4K,2K,960P,480P} --file_type {images+poses,video,colmap_cache} [--hash HASH] [--clean_cache] optional arguments: -h, --help show this help message and exit --odir ODIR output directory --subset {1K,2K,3K,4K,5K,6K,7K,8K,9K,10K} The subset of the benchmark to download --resolution {4K,2K,960P,480P} The resolution to donwnload --file_type {images+poses,video,colmap_cache} The file type to download --hash HASH If set subset=hash, this is the hash code of the scene to download --clean_cache If set, will clean the huggingface cache to save space ``` Here are some examples: ```Bash # Make sure you have applied for the access. # Use this to download the download.py script wget https://raw.githubusercontent.com/DL3DV-10K/Dataset/main/scripts/download.py # Download 480P resolution images and poses, 0~1K subset, output to DL3DV-10K directory python download.py --odir DL3DV-10K --subset 1K --resolution 480P --file_type images+poses --clean_cache # Download 480P resolution images and poses, 1K~2K subset, output to DL3DV-10K directory python download.py --odir DL3DV-10K --subset 2K --resolution 480P --file_type images+poses --clean_cache ``` You can also download a specific scene with its hash. The scene-hash pair visualization can be found [here](https://htmlpreview.github.io/?https://github.com/DL3DV-10K/Dataset/blob/main/visualize/index.html). ```Bash # Download 480P resolution images and poses, 1K~2K subset, output to DL3DV-10K directory python download.py --odir DL3DV-10K --subset 2K --resolution 480P --file_type images+poses --hash e2cedefea8a0ed2d0ffbd5bdc08acbe7e1f85c96f72f7b790e9dfe1c98963047 --clean_cache ``` # News - [x] DL3DV-1K, 2K, 3K, 4K - [ ] DL3DV-5K ~ 10K

databricks/databricks-dolly-15k

databricks

--- license: cc-by-sa-3.0 task_categories: - question-answering - summarization language: - en size_categories: - 10K<n<100K --- # Summary `databricks-dolly-15k` is an open source dataset of instruction-following records generated by thousands of Databricks employees in several of the behavioral categories outlined in the [InstructGPT](https://arxiv.org/abs/2203.02155) paper, including brainstorming, classification, closed QA, generation, information extraction, open QA, and summarization. This dataset can be used for any purpose, whether academic or commercial, under the terms of the [Creative Commons Attribution-ShareAlike 3.0 Unported License](https://creativecommons.org/licenses/by-sa/3.0/legalcode). Supported Tasks: - Training LLMs - Synthetic Data Generation - Data Augmentation Languages: English Version: 1.0 **Owner: Databricks, Inc.** # Dataset Overview `databricks-dolly-15k` is a corpus of more than 15,000 records generated by thousands of Databricks employees to enable large language models to exhibit the magical interactivity of ChatGPT. Databricks employees were invited to create prompt / response pairs in each of eight different instruction categories, including the seven outlined in the InstructGPT paper, as well as an open-ended free-form category. The contributors were instructed to avoid using information from any source on the web with the exception of Wikipedia (for particular subsets of instruction categories), and explicitly instructed to avoid using generative AI in formulating instructions or responses. Examples of each behavior were provided to motivate the types of questions and instructions appropriate to each category. Halfway through the data generation process, contributors were given the option of answering questions posed by other contributors. They were asked to rephrase the original question and only select questions they could be reasonably expected to answer correctly. For certain categories contributors were asked to provide reference texts copied from Wikipedia. Reference text (indicated by the `context` field in the actual dataset) may contain bracketed Wikipedia citation numbers (e.g. `[42]`) which we recommend users remove for downstream applications. # Intended Uses While immediately valuable for instruction fine tuning large language models, as a corpus of human-generated instruction prompts, this dataset also presents a valuable opportunity for synthetic data generation in the methods outlined in the Self-Instruct paper. For example, contributor--generated prompts could be submitted as few-shot examples to a large open language model to generate a corpus of millions of examples of instructions in each of the respective InstructGPT categories. Likewise, both the instructions and responses present fertile ground for data augmentation. A paraphrasing model might be used to restate each prompt or short responses, with the resulting text associated to the respective ground-truth sample. Such an approach might provide a form of regularization on the dataset that could allow for more robust instruction-following behavior in models derived from these synthetic datasets. # Dataset ## Purpose of Collection As part of our continuing commitment to open source, Databricks developed what is, to the best of our knowledge, the first open source, human-generated instruction corpus specifically designed to enable large language models to exhibit the magical interactivity of ChatGPT. Unlike other datasets that are limited to non-commercial use, this dataset can be used, modified, and extended for any purpose, including academic or commercial applications. ## Sources - **Human-generated data**: Databricks employees were invited to create prompt / response pairs in each of eight different instruction categories. - **Wikipedia**: For instruction categories that require an annotator to consult a reference text (information extraction, closed QA, summarization) contributors selected passages from Wikipedia for particular subsets of instruction categories. No guidance was given to annotators as to how to select the target passages. ## Annotator Guidelines To create a record, employees were given a brief description of the annotation task as well as examples of the types of prompts typical of each annotation task. Guidelines were succinct by design so as to encourage a high task completion rate, possibly at the cost of rigorous compliance to an annotation rubric that concretely and reliably operationalizes the specific task. Caveat emptor. The annotation guidelines for each of the categories are as follows: - **Creative Writing**: Write a question or instruction that requires a creative, open-ended written response. The instruction should be reasonable to ask of a person with general world knowledge and should not require searching. In this task, your prompt should give very specific instructions to follow. Constraints, instructions, guidelines, or requirements all work, and the more of them the better. - **Closed QA**: Write a question or instruction that requires factually correct response based on a passage of text from Wikipedia. The question can be complex and can involve human-level reasoning capabilities, but should not require special knowledge. To create a question for this task include both the text of the question as well as the reference text in the form. - **Open QA**: Write a question that can be answered using general world knowledge or at most a single search. This task asks for opinions and facts about the world at large and does not provide any reference text for consultation. - **Summarization**: Give a summary of a paragraph from Wikipedia. Please don't ask questions that will require more than 3-5 minutes to answer. To create a question for this task include both the text of the question as well as the reference text in the form. - **Information Extraction**: These questions involve reading a paragraph from Wikipedia and extracting information from the passage. Everything required to produce an answer (e.g. a list, keywords etc) should be included in the passages. To create a question for this task include both the text of the question as well as the reference text in the form. - **Classification**: These prompts contain lists or examples of entities to be classified, e.g. movie reviews, products, etc. In this task the text or list of entities under consideration is contained in the prompt (e.g. there is no reference text.). You can choose any categories for classification you like, the more diverse the better. - **Brainstorming**: Think up lots of examples in response to a question asking to brainstorm ideas. ## Personal or Sensitive Data This dataset contains public information (e.g., some information from Wikipedia). To our knowledge, there are no private person’s personal identifiers or sensitive information. ## Language American English # Known Limitations - Wikipedia is a crowdsourced corpus and the contents of this dataset may reflect the bias, factual errors and topical focus found in Wikipedia - Some annotators may not be native English speakers - Annotator demographics and subject matter may reflect the makeup of Databricks employees # Citation ``` @online{DatabricksBlog2023DollyV2, author = {Mike Conover and Matt Hayes and Ankit Mathur and Jianwei Xie and Jun Wan and Sam Shah and Ali Ghodsi and Patrick Wendell and Matei Zaharia and Reynold Xin}, title = {Free Dolly: Introducing the World's First Truly Open Instruction-Tuned LLM}, year = {2023}, url = {https://www.databricks.com/blog/2023/04/12/dolly-first-open-commercially-viable-instruction-tuned-llm}, urldate = {2023-06-30} } ``` # License/Attribution **Copyright (2023) Databricks, Inc.** This dataset was developed at Databricks (https://www.databricks.com) and its use is subject to the CC BY-SA 3.0 license. Certain categories of material in the dataset include materials from the following sources, licensed under the CC BY-SA 3.0 license: Wikipedia (various pages) - https://www.wikipedia.org/ Copyright © Wikipedia editors and contributors.

google/xtreme

google

--- annotations_creators: - found language_creators: - found language: - af - ar - bg - bn - de - el - en - es - et - eu - fa - fi - fr - he - hi - hu - id - it - ja - jv - ka - kk - ko - ml - mr - ms - my - nl - pt - ru - sw - ta - te - th - tl - tr - ur - vi - yo - zh license: - apache-2.0 - cc-by-4.0 - cc-by-2.0 - cc-by-sa-4.0 - other - cc-by-nc-4.0 multilinguality: - multilingual - translation size_categories: - n<1K - 1K<n<10K - 10K<n<100K - 100K<n<1M source_datasets: - extended|xnli - extended|paws-x - extended|wikiann - extended|xquad - extended|mlqa - extended|tydiqa - extended|tatoeba - extended|squad task_categories: - multiple-choice - question-answering - token-classification - text-classification - text-retrieval - token-classification task_ids: - multiple-choice-qa - extractive-qa - open-domain-qa - natural-language-inference - named-entity-recognition - part-of-speech paperswithcode_id: xtreme pretty_name: XTREME config_names: - MLQA.ar.ar - MLQA.ar.de - MLQA.ar.en - MLQA.ar.es - MLQA.ar.hi - MLQA.ar.vi - MLQA.ar.zh - MLQA.de.ar - MLQA.de.de - MLQA.de.en - MLQA.de.es - MLQA.de.hi - MLQA.de.vi - MLQA.de.zh - MLQA.en.ar - MLQA.en.de - MLQA.en.en - MLQA.en.es - MLQA.en.hi - MLQA.en.vi - MLQA.en.zh - MLQA.es.ar - MLQA.es.de - MLQA.es.en - MLQA.es.es - MLQA.es.hi - MLQA.es.vi - MLQA.es.zh - MLQA.hi.ar - MLQA.hi.de - MLQA.hi.en - MLQA.hi.es - MLQA.hi.hi - MLQA.hi.vi - MLQA.hi.zh - MLQA.vi.ar - MLQA.vi.de - MLQA.vi.en - MLQA.vi.es - MLQA.vi.hi - MLQA.vi.vi - MLQA.vi.zh - MLQA.zh.ar - MLQA.zh.de - MLQA.zh.en - MLQA.zh.es - MLQA.zh.hi - MLQA.zh.vi - MLQA.zh.zh - PAN-X.af - PAN-X.ar - PAN-X.bg - PAN-X.bn - PAN-X.de - PAN-X.el - PAN-X.en - PAN-X.es - PAN-X.et - PAN-X.eu - PAN-X.fa - PAN-X.fi - PAN-X.fr - PAN-X.he - PAN-X.hi - PAN-X.hu - PAN-X.id - PAN-X.it - PAN-X.ja - PAN-X.jv - PAN-X.ka - PAN-X.kk - PAN-X.ko - PAN-X.ml - PAN-X.mr - PAN-X.ms - PAN-X.my - PAN-X.nl - PAN-X.pt - PAN-X.ru - PAN-X.sw - PAN-X.ta - PAN-X.te - PAN-X.th - PAN-X.tl - PAN-X.tr - PAN-X.ur - PAN-X.vi - PAN-X.yo - PAN-X.zh - PAWS-X.de - PAWS-X.en - PAWS-X.es - PAWS-X.fr - PAWS-X.ja - PAWS-X.ko - PAWS-X.zh - SQuAD - XNLI - XQuAD - bucc18.de - bucc18.fr - bucc18.ru - bucc18.zh - tatoeba.afr - tatoeba.ara - tatoeba.ben - tatoeba.bul - tatoeba.cmn - tatoeba.deu - tatoeba.ell - tatoeba.est - tatoeba.eus - tatoeba.fin - tatoeba.fra - tatoeba.heb - tatoeba.hin - tatoeba.hun - tatoeba.ind - tatoeba.ita - tatoeba.jav - tatoeba.jpn - tatoeba.kat - tatoeba.kaz - tatoeba.kor - tatoeba.mal - tatoeba.mar - tatoeba.nld - tatoeba.pes - tatoeba.por - tatoeba.rus - tatoeba.spa - tatoeba.swh - tatoeba.tam - tatoeba.tel - tatoeba.tgl - tatoeba.tha - tatoeba.tur - tatoeba.urd - tatoeba.vie - tydiqa - udpos.Afrikans - udpos.Arabic - udpos.Basque - udpos.Bulgarian - udpos.Chinese - udpos.Dutch - udpos.English - udpos.Estonian - udpos.Finnish - udpos.French - udpos.German - udpos.Greek - udpos.Hebrew - udpos.Hindi - udpos.Hungarian - udpos.Indonesian - udpos.Italian - udpos.Japanese - udpos.Kazakh - udpos.Korean - udpos.Marathi - udpos.Persian - udpos.Portuguese - udpos.Russian - udpos.Spanish - udpos.Tagalog - udpos.Tamil - udpos.Telugu - udpos.Thai - udpos.Turkish - udpos.Urdu - udpos.Vietnamese - udpos.Yoruba language_bcp47: - fa-IR license_details: Licence Universal Dependencies v2.5 tags: - parallel-sentence-retrieval - paraphrase-identification dataset_info: - config_name: MLQA.ar.ar features: - name: id dtype: string - name: title dtype: string - name: context dtype: string - name: question dtype: string - name: answers sequence: - name: answer_start dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 8368086 num_examples: 5335 - name: validation num_bytes: 824080 num_examples: 517 download_size: 4048180 dataset_size: 9192166 - config_name: MLQA.ar.de features: - name: id dtype: string - name: title dtype: string - name: context dtype: string - name: question dtype: string - name: answers sequence: - name: answer_start dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 2183914 num_examples: 1649 - name: validation num_bytes: 364809 num_examples: 207 download_size: 1192825 dataset_size: 2548723 - config_name: MLQA.ar.en features: - name: id dtype: string - name: title dtype: string - name: context dtype: string - name: question dtype: string - name: answers sequence: - name: answer_start dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 8225634 num_examples: 5335 - name: validation num_bytes: 810061 num_examples: 517 download_size: 3998008 dataset_size: 9035695 - config_name: MLQA.ar.es features: - name: id dtype: string - name: title dtype: string - name: context dtype: string - name: question dtype: string - name: answers sequence: - name: answer_start dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 3041350 num_examples: 1978 - name: validation num_bytes: 228152 num_examples: 161 download_size: 1531661 dataset_size: 3269502 - config_name: MLQA.ar.hi features: - name: id dtype: string - name: title dtype: string - name: context dtype: string - name: question dtype: string - name: answers sequence: - name: answer_start dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 3039368 num_examples: 1831 - name: validation num_bytes: 281742 num_examples: 186 download_size: 1369756 dataset_size: 3321110 - config_name: MLQA.ar.vi features: - name: id dtype: string - name: title dtype: string - name: context dtype: string - name: question dtype: string - name: answers sequence: - name: answer_start dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 3290601 num_examples: 2047 - name: validation num_bytes: 288418 num_examples: 163 download_size: 1667238 dataset_size: 3579019 - config_name: MLQA.ar.zh features: - name: id dtype: string - name: title dtype: string - name: context dtype: string - name: question dtype: string - name: answers sequence: - name: answer_start dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 3229844 num_examples: 1912 - name: validation num_bytes: 340021 num_examples: 188 download_size: 1591445 dataset_size: 3569865 - config_name: MLQA.de.ar features: - name: id dtype: string - name: title dtype: string - name: context dtype: string - name: question dtype: string - name: answers sequence: - name: answer_start dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 1619978 num_examples: 1649 - name: validation num_bytes: 200146 num_examples: 207 download_size: 1044483 dataset_size: 1820124 - config_name: MLQA.de.de features: - name: id dtype: string - name: title dtype: string - name: context dtype: string - name: question dtype: string - name: answers sequence: - name: answer_start dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 4366074 num_examples: 4517 - name: validation num_bytes: 488339 num_examples: 512 download_size: 2798050 dataset_size: 4854413 - config_name: MLQA.de.en features: - name: id dtype: string - name: title dtype: string - name: context dtype: string - name: question dtype: string - name: answers sequence: - name: answer_start dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 4343116 num_examples: 4517 - name: validation num_bytes: 485866 num_examples: 512 download_size: 2778346 dataset_size: 4828982 - config_name: MLQA.de.es features: - name: id dtype: string - name: title dtype: string - name: context dtype: string - name: question dtype: string - name: answers sequence: - name: answer_start dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 1716587 num_examples: 1776 - name: validation num_bytes: 170554 num_examples: 196 download_size: 1118751 dataset_size: 1887141 - config_name: MLQA.de.hi features: - name: id dtype: string - name: title dtype: string - name: context dtype: string - name: question dtype: string - name: answers sequence: - name: answer_start dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 1371046 num_examples: 1430 - name: validation num_bytes: 153843 num_examples: 163 download_size: 880652 dataset_size: 1524889 - config_name: MLQA.de.vi features: - name: id dtype: string - name: title dtype: string - name: context dtype: string - name: question dtype: string - name: answers sequence: - name: answer_start dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 1688455 num_examples: 1675 - name: validation num_bytes: 216047 num_examples: 182 download_size: 1108163 dataset_size: 1904502 - config_name: MLQA.de.zh features: - name: id dtype: string - name: title dtype: string - name: context dtype: string - name: question dtype: string - name: answers sequence: - name: answer_start dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 1679152 num_examples: 1621 - name: validation num_bytes: 184290 num_examples: 190 download_size: 1045861 dataset_size: 1863442 - config_name: MLQA.en.ar features: - name: id dtype: string - name: title dtype: string - name: context dtype: string - name: question dtype: string - name: answers sequence: - name: answer_start dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 6739191 num_examples: 5335 - name: validation num_bytes: 630815 num_examples: 517 download_size: 3939135 dataset_size: 7370006 - config_name: MLQA.en.de features: - name: id dtype: string - name: title dtype: string - name: context dtype: string - name: question dtype: string - name: answers sequence: - name: answer_start dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 5056694 num_examples: 4517 - name: validation num_bytes: 594908 num_examples: 512 download_size: 3223196 dataset_size: 5651602 - config_name: MLQA.en.en features: - name: id dtype: string - name: title dtype: string - name: context dtype: string - name: question dtype: string - name: answers sequence: - name: answer_start dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 14004592 num_examples: 11590 - name: validation num_bytes: 1329084 num_examples: 1148 download_size: 8217519 dataset_size: 15333676 - config_name: MLQA.en.es features: - name: id dtype: string - name: title dtype: string - name: context dtype: string - name: question dtype: string - name: answers sequence: - name: answer_start dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 6179221 num_examples: 5253 - name: validation num_bytes: 555434 num_examples: 500 download_size: 3776828 dataset_size: 6734655 - config_name: MLQA.en.hi features: - name: id dtype: string - name: title dtype: string - name: context dtype: string - name: question dtype: string - name: answers sequence: - name: answer_start dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 6378838 num_examples: 4918 - name: validation num_bytes: 623143 num_examples: 507 download_size: 3517340 dataset_size: 7001981 - config_name: MLQA.en.vi features: - name: id dtype: string - name: title dtype: string - name: context dtype: string - name: question dtype: string - name: answers sequence: - name: answer_start dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 7056670 num_examples: 5495 - name: validation num_bytes: 640618 num_examples: 511 download_size: 4170642 dataset_size: 7697288 - config_name: MLQA.en.zh features: - name: id dtype: string - name: title dtype: string - name: context dtype: string - name: question dtype: string - name: answers sequence: - name: answer_start dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 6539279 num_examples: 5137 - name: validation num_bytes: 608416 num_examples: 504 download_size: 3929122 dataset_size: 7147695 - config_name: MLQA.es.ar features: - name: id dtype: string - name: title dtype: string - name: context dtype: string - name: question dtype: string - name: answers sequence: - name: answer_start dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 1740254 num_examples: 1978 - name: validation num_bytes: 148621 num_examples: 161 download_size: 1107435 dataset_size: 1888875 - config_name: MLQA.es.de features: - name: id dtype: string - name: title dtype: string - name: context dtype: string - name: question dtype: string - name: answers sequence: - name: answer_start dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 1403997 num_examples: 1776 - name: validation num_bytes: 144158 num_examples: 196 download_size: 950448 dataset_size: 1548155 - config_name: MLQA.es.en features: - name: id dtype: string - name: title dtype: string - name: context dtype: string - name: question dtype: string - name: answers sequence: - name: answer_start dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 4362709 num_examples: 5253 - name: validation num_bytes: 419040 num_examples: 500 download_size: 2842879 dataset_size: 4781749 - config_name: MLQA.es.es features: - name: id dtype: string - name: title dtype: string - name: context dtype: string - name: question dtype: string - name: answers sequence: - name: answer_start dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 4394305 num_examples: 5253 - name: validation num_bytes: 422043 num_examples: 500 download_size: 2856931 dataset_size: 4816348 - config_name: MLQA.es.hi features: - name: id dtype: string - name: title dtype: string - name: context dtype: string - name: question dtype: string - name: answers sequence: - name: answer_start dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 1523495 num_examples: 1723 - name: validation num_bytes: 181806 num_examples: 187 download_size: 954018 dataset_size: 1705301 - config_name: MLQA.es.vi features: - name: id dtype: string - name: title dtype: string - name: context dtype: string - name: question dtype: string - name: answers sequence: - name: answer_start dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 1747941 num_examples: 2018 - name: validation num_bytes: 176813 num_examples: 189 download_size: 1187949 dataset_size: 1924754 - config_name: MLQA.es.zh features: - name: id dtype: string - name: title dtype: string - name: context dtype: string - name: question dtype: string - name: answers sequence: - name: answer_start dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 1678423 num_examples: 1947 - name: validation num_bytes: 126618 num_examples: 161 download_size: 1100765 dataset_size: 1805041 - config_name: MLQA.hi.ar features: - name: id dtype: string - name: title dtype: string - name: context dtype: string - name: question dtype: string - name: answers sequence: - name: answer_start dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 4445561 num_examples: 1831 - name: validation num_bytes: 410396 num_examples: 186 download_size: 1542768 dataset_size: 4855957 - config_name: MLQA.hi.de features: - name: id dtype: string - name: title dtype: string - name: context dtype: string - name: question dtype: string - name: answers sequence: - name: answer_start dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 3022836 num_examples: 1430 - name: validation num_bytes: 301685 num_examples: 163 download_size: 1257846 dataset_size: 3324521 - config_name: MLQA.hi.en features: - name: id dtype: string - name: title dtype: string - name: context dtype: string - name: question dtype: string - name: answers sequence: - name: answer_start dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 11449233 num_examples: 4918 - name: validation num_bytes: 1097829 num_examples: 507 download_size: 4131083 dataset_size: 12547062 - config_name: MLQA.hi.es features: - name: id dtype: string - name: title dtype: string - name: context dtype: string - name: question dtype: string - name: answers sequence: - name: answer_start dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 3862201 num_examples: 1723 - name: validation num_bytes: 420374 num_examples: 187 download_size: 1493468 dataset_size: 4282575 - config_name: MLQA.hi.hi features: - name: id dtype: string - name: title dtype: string - name: context dtype: string - name: question dtype: string - name: answers sequence: - name: answer_start dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 11810447 num_examples: 4918 - name: validation num_bytes: 1136756 num_examples: 507 download_size: 4235981 dataset_size: 12947203 - config_name: MLQA.hi.vi features: - name: id dtype: string - name: title dtype: string - name: context dtype: string - name: question dtype: string - name: answers sequence: - name: answer_start dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 4743456 num_examples: 1947 - name: validation num_bytes: 419078 num_examples: 177 download_size: 1704964 dataset_size: 5162534 - config_name: MLQA.hi.zh features: - name: id dtype: string - name: title dtype: string - name: context dtype: string - name: question dtype: string - name: answers sequence: - name: answer_start dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 4354847 num_examples: 1767 - name: validation num_bytes: 424218 num_examples: 189 download_size: 1627107 dataset_size: 4779065 - config_name: MLQA.vi.ar features: - name: id dtype: string - name: title dtype: string - name: context dtype: string - name: question dtype: string - name: answers sequence: - name: answer_start dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 3205157 num_examples: 2047 - name: validation num_bytes: 230307 num_examples: 163 download_size: 1656661 dataset_size: 3435464 - config_name: MLQA.vi.de features: - name: id dtype: string - name: title dtype: string - name: context dtype: string - name: question dtype: string - name: answers sequence: - name: answer_start dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 2227005 num_examples: 1675 - name: validation num_bytes: 277157 num_examples: 182 download_size: 1268041 dataset_size: 2504162 - config_name: MLQA.vi.en features: - name: id dtype: string - name: title dtype: string - name: context dtype: string - name: question dtype: string - name: answers sequence: - name: answer_start dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 7843403 num_examples: 5495 - name: validation num_bytes: 719245 num_examples: 511 download_size: 4071703 dataset_size: 8562648 - config_name: MLQA.vi.es features: - name: id dtype: string - name: title dtype: string - name: context dtype: string - name: question dtype: string - name: answers sequence: - name: answer_start dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 2866569 num_examples: 2018 - name: validation num_bytes: 283433 num_examples: 189 download_size: 1607926 dataset_size: 3150002 - config_name: MLQA.vi.hi features: - name: id dtype: string - name: title dtype: string - name: context dtype: string - name: question dtype: string - name: answers sequence: - name: answer_start dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 2776636 num_examples: 1947 - name: validation num_bytes: 254979 num_examples: 177 download_size: 1366057 dataset_size: 3031615 - config_name: MLQA.vi.vi features: - name: id dtype: string - name: title dtype: string - name: context dtype: string - name: question dtype: string - name: answers sequence: - name: answer_start dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 7922057 num_examples: 5495 - name: validation num_bytes: 726490 num_examples: 511 download_size: 4105388 dataset_size: 8648547 - config_name: MLQA.vi.zh features: - name: id dtype: string - name: title dtype: string - name: context dtype: string - name: question dtype: string - name: answers sequence: - name: answer_start dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 2989632 num_examples: 1943 - name: validation num_bytes: 269361 num_examples: 184 download_size: 1570393 dataset_size: 3258993 - config_name: MLQA.zh.ar features: - name: id dtype: string - name: title dtype: string - name: context dtype: string - name: question dtype: string - name: answers sequence: - name: answer_start dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 1731455 num_examples: 1912 - name: validation num_bytes: 175321 num_examples: 188 download_size: 1223863 dataset_size: 1906776 - config_name: MLQA.zh.de features: - name: id dtype: string - name: title dtype: string - name: context dtype: string - name: question dtype: string - name: answers sequence: - name: answer_start dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 1389990 num_examples: 1621 - name: validation num_bytes: 174577 num_examples: 190 download_size: 1006829 dataset_size: 1564567 - config_name: MLQA.zh.en features: - name: id dtype: string - name: title dtype: string - name: context dtype: string - name: question dtype: string - name: answers sequence: - name: answer_start dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 4450957 num_examples: 5137 - name: validation num_bytes: 446840 num_examples: 504 download_size: 3108433 dataset_size: 4897797 - config_name: MLQA.zh.es features: - name: id dtype: string - name: title dtype: string - name: context dtype: string - name: question dtype: string - name: answers sequence: - name: answer_start dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 1736255 num_examples: 1947 - name: validation num_bytes: 138045 num_examples: 161 download_size: 1223467 dataset_size: 1874300 - config_name: MLQA.zh.hi features: - name: id dtype: string - name: title dtype: string - name: context dtype: string - name: question dtype: string - name: answers sequence: - name: answer_start dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 1578191 num_examples: 1767 - name: validation num_bytes: 184373 num_examples: 189 download_size: 1044599 dataset_size: 1762564 - config_name: MLQA.zh.vi features: - name: id dtype: string - name: title dtype: string - name: context dtype: string - name: question dtype: string - name: answers sequence: - name: answer_start dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 1806158 num_examples: 1943 - name: validation num_bytes: 172906 num_examples: 184 download_size: 1268213 dataset_size: 1979064 - config_name: MLQA.zh.zh features: - name: id dtype: string - name: title dtype: string - name: context dtype: string - name: question dtype: string - name: answers sequence: - name: answer_start dtype: int32 - name: text dtype: string splits: - name: test num_bytes: 4422322 num_examples: 5137 - name: validation num_bytes: 443782 num_examples: 504 download_size: 3105362 dataset_size: 4866104 - config_name: PAN-X.af features: - name: tokens sequence: string - name: ner_tags sequence: class_label: names: '0': O '1': B-PER '2': I-PER '3': B-ORG '4': I-ORG '5': B-LOC '6': I-LOC - name: langs sequence: string splits: - name: train num_bytes: 1321376 num_examples: 5000 - name: validation num_bytes: 259689 num_examples: 1000 - name: test num_bytes: 257184 num_examples: 1000 download_size: 389015 dataset_size: 1838249 - config_name: PAN-X.ar features: - name: tokens sequence: string - name: ner_tags sequence: class_label: names: '0': O '1': B-PER '2': I-PER '3': B-ORG '4': I-ORG '5': B-LOC '6': I-LOC - name: langs sequence: string splits: - name: train num_bytes: 3634096 num_examples: 20000 - name: validation num_bytes: 1808283 num_examples: 10000 - name: test num_bytes: 1811963 num_examples: 10000 download_size: 1567470 dataset_size: 7254342 - config_name: PAN-X.bg features: - name: tokens sequence: string - name: ner_tags sequence: class_label: names: '0': O '1': B-PER '2': I-PER '3': B-ORG '4': I-ORG '5': B-LOC '6': I-LOC - name: langs sequence: string splits: - name: train num_bytes: 4600733 num_examples: 20000 - name: validation num_bytes: 2310294 num_examples: 10000 - name: test num_bytes: 2306138 num_examples: 10000 download_size: 2030669 dataset_size: 9217165 - config_name: PAN-X.bn features: - name: tokens sequence: string - name: ner_tags sequence: class_label: names: '0': O '1': B-PER '2': I-PER '3': B-ORG '4': I-ORG '5': B-LOC '6': I-LOC - name: langs sequence: string splits: - name: train num_bytes: 1568825 num_examples: 10000 - name: validation num_bytes: 159068 num_examples: 1000 - name: test num_bytes: 159262 num_examples: 1000 download_size: 364024 dataset_size: 1887155 - config_name: PAN-X.de features: - name: tokens sequence: string - name: ner_tags sequence: class_label: names: '0': O '1': B-PER '2': I-PER '3': B-ORG '4': I-ORG '5': B-LOC '6': I-LOC - name: langs sequence: string splits: - name: train num_bytes: 4762312 num_examples: 20000 - name: validation num_bytes: 2381545 num_examples: 10000 - name: test num_bytes: 2377619 num_examples: 10000 download_size: 2360242 dataset_size: 9521476 - config_name: PAN-X.el features: - name: tokens sequence: string - name: ner_tags sequence: class_label: names: '0': O '1': B-PER '2': I-PER '3': B-ORG '4': I-ORG '5': B-LOC '6': I-LOC - name: langs sequence: string splits: - name: train num_bytes: 5063136 num_examples: 20000 - name: validation num_bytes: 2533786 num_examples: 10000 - name: test num_bytes: 2547574 num_examples: 10000 download_size: 2271726 dataset_size: 10144496 - config_name: PAN-X.en features: - name: tokens sequence: string - name: ner_tags sequence: class_label: names: '0': O '1': B-PER '2': I-PER '3': B-ORG '4': I-ORG '5': B-LOC '6': I-LOC - name: langs sequence: string splits: - name: train num_bytes: 3823434 num_examples: 20000 - name: validation num_bytes: 1920049 num_examples: 10000 - name: test num_bytes: 1916200 num_examples: 10000 download_size: 1886284 dataset_size: 7659683 - config_name: PAN-X.es features: - name: tokens sequence: string - name: ner_tags sequence: class_label: names: '0': O '1': B-PER '2': I-PER '3': B-ORG '4': I-ORG '5': B-LOC '6': I-LOC - name: langs sequence: string splits: - name: train num_bytes: 3199121 num_examples: 20000 - name: validation num_bytes: 1592505 num_examples: 10000 - name: test num_bytes: 1602271 num_examples: 10000 download_size: 1489562 dataset_size: 6393897 - config_name: PAN-X.et features: - name: tokens sequence: string - name: ner_tags sequence: class_label: names: '0': O '1': B-PER '2': I-PER '3': B-ORG '4': I-ORG '5': B-LOC '6': I-LOC - name: langs sequence: string splits: - name: train num_bytes: 3023171 num_examples: 15000 - name: validation num_bytes: 2030140 num_examples: 10000 - name: test num_bytes: 2021389 num_examples: 10000 download_size: 1915624 dataset_size: 7074700 - config_name: PAN-X.eu features: - name: tokens sequence: string - name: ner_tags sequence: class_label: names: '0': O '1': B-PER '2': I-PER '3': B-ORG '4': I-ORG '5': B-LOC '6': I-LOC - name: langs sequence: string splits: - name: train num_bytes: 2292307 num_examples: 10000 - name: validation num_bytes: 2296315 num_examples: 10000 - name: test num_bytes: 2249815 num_examples: 10000 download_size: 1393179 dataset_size: 6838437 - config_name: PAN-X.fa features: - name: tokens sequence: string - name: ner_tags sequence: class_label: names: '0': O '1': B-PER '2': I-PER '3': B-ORG '4': I-ORG '5': B-LOC '6': I-LOC - name: langs sequence: string splits: - name: train num_bytes: 3529314 num_examples: 20000 - name: validation num_bytes: 1782286 num_examples: 10000 - name: test num_bytes: 1770264 num_examples: 10000 download_size: 1401208 dataset_size: 7081864 - config_name: PAN-X.fi features: - name: tokens sequence: string - name: ner_tags sequence: class_label: names: '0': O '1': B-PER '2': I-PER '3': B-ORG '4': I-ORG '5': B-LOC '6': I-LOC - name: langs sequence: string splits: - name: train num_bytes: 4273753 num_examples: 20000 - name: validation num_bytes: 2131749 num_examples: 10000 - name: test num_bytes: 2130645 num_examples: 10000 download_size: 2459149 dataset_size: 8536147 - config_name: PAN-X.fr features: - name: tokens sequence: string - name: ner_tags sequence: class_label: names: '0': O '1': B-PER '2': I-PER '3': B-ORG '4': I-ORG '5': B-LOC '6': I-LOC - name: langs sequence: string splits: - name: train num_bytes: 3335384 num_examples: 20000 - name: validation num_bytes: 1664170 num_examples: 10000 - name: test num_bytes: 1675765 num_examples: 10000 download_size: 1679283 dataset_size: 6675319 - config_name: PAN-X.he features: - name: tokens sequence: string - name: ner_tags sequence: class_label: names: '0': O '1': B-PER '2': I-PER '3': B-ORG '4': I-ORG '5': B-LOC '6': I-LOC - name: langs sequence: string splits: - name: train num_bytes: 4667060 num_examples: 20000 - name: validation num_bytes: 2332740 num_examples: 10000 - name: test num_bytes: 2318736 num_examples: 10000 download_size: 2186463 dataset_size: 9318536 - config_name: PAN-X.hi features: - name: tokens sequence: string - name: ner_tags sequence: class_label: names: '0': O '1': B-PER '2': I-PER '3': B-ORG '4': I-ORG '5': B-LOC '6': I-LOC - name: langs sequence: string splits: - name: train num_bytes: 964192 num_examples: 5000 - name: validation num_bytes: 190651 num_examples: 1000 - name: test num_bytes: 196170 num_examples: 1000 download_size: 266086 dataset_size: 1351013 - config_name: PAN-X.hu features: - name: tokens sequence: string - name: ner_tags sequence: class_label: names: '0': O '1': B-PER '2': I-PER '3': B-ORG '4': I-ORG '5': B-LOC '6': I-LOC - name: langs sequence: string splits: - name: train num_bytes: 4499874 num_examples: 20000 - name: validation num_bytes: 2211831 num_examples: 10000 - name: test num_bytes: 2249759 num_examples: 10000 download_size: 2399390 dataset_size: 8961464 - config_name: PAN-X.id features: - name: tokens sequence: string - name: ner_tags sequence: class_label: names: '0': O '1': B-PER '2': I-PER '3': B-ORG '4': I-ORG '5': B-LOC '6': I-LOC - name: langs sequence: string splits: - name: train num_bytes: 3083967 num_examples: 20000 - name: validation num_bytes: 1537959 num_examples: 10000 - name: test num_bytes: 1536859 num_examples: 10000 download_size: 1412049 dataset_size: 6158785 - config_name: PAN-X.it features: - name: tokens sequence: string - name: ner_tags sequence: class_label: names: '0': O '1': B-PER '2': I-PER '3': B-ORG '4': I-ORG '5': B-LOC '6': I-LOC - name: langs sequence: string splits: - name: train num_bytes: 3874623 num_examples: 20000 - name: validation num_bytes: 1908509 num_examples: 10000 - name: test num_bytes: 1928388 num_examples: 10000 download_size: 1855798 dataset_size: 7711520 - config_name: PAN-X.ja features: - name: tokens sequence: string - name: ner_tags sequence: class_label: names: '0': O '1': B-PER '2': I-PER '3': B-ORG '4': I-ORG '5': B-LOC '6': I-LOC - name: langs sequence: string splits: - name: train num_bytes: 12670361 num_examples: 20000 - name: validation num_bytes: 6322983 num_examples: 10000 - name: test num_bytes: 6448940 num_examples: 10000 download_size: 2465674 dataset_size: 25442284 - config_name: PAN-X.jv features: - name: tokens sequence: string - name: ner_tags sequence: class_label: names: '0': O '1': B-PER '2': I-PER '3': B-ORG '4': I-ORG '5': B-LOC '6': I-LOC - name: langs sequence: string splits: - name: train num_bytes: 16086 num_examples: 100 - name: validation num_bytes: 14580 num_examples: 100 - name: test num_bytes: 16897 num_examples: 100 download_size: 20475 dataset_size: 47563 - config_name: PAN-X.ka features: - name: tokens sequence: string - name: ner_tags sequence: class_label: names: '0': O '1': B-PER '2': I-PER '3': B-ORG '4': I-ORG '5': B-LOC '6': I-LOC - name: langs sequence: string splits: - name: train num_bytes: 2777342 num_examples: 10000 - name: validation num_bytes: 2806881 num_examples: 10000 - name: test num_bytes: 2824621 num_examples: 10000 download_size: 1817280 dataset_size: 8408844 - config_name: PAN-X.kk features: - name: tokens sequence: string - name: ner_tags sequence: class_label: names: '0': O '1': B-PER '2': I-PER '3': B-ORG '4': I-ORG '5': B-LOC '6': I-LOC - name: langs sequence: string splits: - name: train num_bytes: 240256 num_examples: 1000 - name: validation num_bytes: 238089 num_examples: 1000 - name: test num_bytes: 236704 num_examples: 1000 download_size: 160554 dataset_size: 715049 - config_name: PAN-X.ko features: - name: tokens sequence: string - name: ner_tags sequence: class_label: names: '0': O '1': B-PER '2': I-PER '3': B-ORG '4': I-ORG '5': B-LOC '6': I-LOC - name: langs sequence: string splits: - name: train num_bytes: 4284693 num_examples: 20000 - name: validation num_bytes: 2138147 num_examples: 10000 - name: test num_bytes: 2138274 num_examples: 10000 download_size: 2539591 dataset_size: 8561114 - config_name: PAN-X.ml features: - name: tokens sequence: string - name: ner_tags sequence: class_label: names: '0': O '1': B-PER '2': I-PER '3': B-ORG '4': I-ORG '5': B-LOC '6': I-LOC - name: langs sequence: string splits: - name: train num_bytes: 2865184 num_examples: 10000 - name: validation num_bytes: 290735 num_examples: 1000 - name: test num_bytes: 276906 num_examples: 1000 download_size: 852955 dataset_size: 3432825 - config_name: PAN-X.mr features: - name: tokens sequence: string - name: ner_tags sequence: class_label: names: '0': O '1': B-PER '2': I-PER '3': B-ORG '4': I-ORG '5': B-LOC '6': I-LOC - name: langs sequence: string splits: - name: train num_bytes: 1248239 num_examples: 5000 - name: validation num_bytes: 245338 num_examples: 1000 - name: test num_bytes: 255884 num_examples: 1000 download_size: 347215 dataset_size: 1749461 - config_name: PAN-X.ms features: - name: tokens sequence: string - name: ner_tags sequence: class_label: names: '0': O '1': B-PER '2': I-PER '3': B-ORG '4': I-ORG '5': B-LOC '6': I-LOC - name: langs sequence: string splits: - name: train num_bytes: 2965008 num_examples: 20000 - name: validation num_bytes: 147495 num_examples: 1000 - name: test num_bytes: 147148 num_examples: 1000 download_size: 708795 dataset_size: 3259651 - config_name: PAN-X.my features: - name: tokens sequence: string - name: ner_tags sequence: class_label: names: '0': O '1': B-PER '2': I-PER '3': B-ORG '4': I-ORG '5': B-LOC '6': I-LOC - name: langs sequence: string splits: - name: train num_bytes: 32715 num_examples: 100 - name: validation num_bytes: 40408 num_examples: 100 - name: test num_bytes: 37346 num_examples: 100 download_size: 39008 dataset_size: 110469 - config_name: PAN-X.nl features: - name: tokens sequence: string - name: ner_tags sequence: class_label: names: '0': O '1': B-PER '2': I-PER '3': B-ORG '4': I-ORG '5': B-LOC '6': I-LOC - name: langs sequence: string splits: - name: train num_bytes: 4062149 num_examples: 20000 - name: validation num_bytes: 2016836 num_examples: 10000 - name: test num_bytes: 2038618 num_examples: 10000 download_size: 1943893 dataset_size: 8117603 - config_name: PAN-X.pt features: - name: tokens sequence: string - name: ner_tags sequence: class_label: names: '0': O '1': B-PER '2': I-PER '3': B-ORG '4': I-ORG '5': B-LOC '6': I-LOC - name: langs sequence: string splits: - name: train num_bytes: 3149243 num_examples: 20000 - name: validation num_bytes: 1575121 num_examples: 10000 - name: test num_bytes: 1562605 num_examples: 10000 download_size: 1540478 dataset_size: 6286969 - config_name: PAN-X.ru features: - name: tokens sequence: string - name: ner_tags sequence: class_label: names: '0': O '1': B-PER '2': I-PER '3': B-ORG '4': I-ORG '5': B-LOC '6': I-LOC - name: langs sequence: string splits: - name: train num_bytes: 4121751 num_examples: 20000 - name: validation num_bytes: 2053149 num_examples: 10000 - name: test num_bytes: 2074125 num_examples: 10000 download_size: 2127730 dataset_size: 8249025 - config_name: PAN-X.sw features: - name: tokens sequence: string - name: ner_tags sequence: class_label: names: '0': O '1': B-PER '2': I-PER '3': B-ORG '4': I-ORG '5': B-LOC '6': I-LOC - name: langs sequence: string splits: - name: train num_bytes: 135891 num_examples: 1000 - name: validation num_bytes: 136348 num_examples: 1000 - name: test num_bytes: 140211 num_examples: 1000 download_size: 87435 dataset_size: 412450 - config_name: PAN-X.ta features: - name: tokens sequence: string - name: ner_tags sequence: class_label: names: '0': O '1': B-PER '2': I-PER '3': B-ORG '4': I-ORG '5': B-LOC '6': I-LOC - name: langs sequence: string splits: - name: train num_bytes: 4122090 num_examples: 15000 - name: validation num_bytes: 277605 num_examples: 1000 - name: test num_bytes: 278094 num_examples: 1000 download_size: 1044729 dataset_size: 4677789 - config_name: PAN-X.te features: - name: tokens sequence: string - name: ner_tags sequence: class_label: names: '0': O '1': B-PER '2': I-PER '3': B-ORG '4': I-ORG '5': B-LOC '6': I-LOC - name: langs sequence: string splits: - name: train num_bytes: 295390 num_examples: 1000 - name: validation num_bytes: 293261 num_examples: 1000 - name: test num_bytes: 296943 num_examples: 1000 download_size: 200516 dataset_size: 885594 - config_name: PAN-X.th features: - name: tokens sequence: string - name: ner_tags sequence: class_label: names: '0': O '1': B-PER '2': I-PER '3': B-ORG '4': I-ORG '5': B-LOC '6': I-LOC - name: langs sequence: string splits: - name: train num_bytes: 27132989 num_examples: 20000 - name: validation num_bytes: 13262717 num_examples: 10000 - name: test num_bytes: 13586908 num_examples: 10000 download_size: 2569566 dataset_size: 53982614 - config_name: PAN-X.tl features: - name: tokens sequence: string - name: ner_tags sequence: class_label: names: '0': O '1': B-PER '2': I-PER '3': B-ORG '4': I-ORG '5': B-LOC '6': I-LOC - name: langs sequence: string splits: - name: train num_bytes: 1168697 num_examples: 10000 - name: validation num_bytes: 114136 num_examples: 1000 - name: test num_bytes: 117884 num_examples: 1000 download_size: 308160 dataset_size: 1400717 - config_name: PAN-X.tr features: - name: tokens sequence: string - name: ner_tags sequence: class_label: names: '0': O '1': B-PER '2': I-PER '3': B-ORG '4': I-ORG '5': B-LOC '6': I-LOC - name: langs sequence: string splits: - name: train num_bytes: 3779130 num_examples: 20000 - name: validation num_bytes: 1915332 num_examples: 10000 - name: test num_bytes: 1911483 num_examples: 10000 download_size: 2000699 dataset_size: 7605945 - config_name: PAN-X.ur features: - name: tokens sequence: string - name: ner_tags sequence: class_label: names: '0': O '1': B-PER '2': I-PER '3': B-ORG '4': I-ORG '5': B-LOC '6': I-LOC - name: langs sequence: string splits: - name: train num_bytes: 3072236 num_examples: 20000 - name: validation num_bytes: 152128 num_examples: 1000 - name: test num_bytes: 151902 num_examples: 1000 download_size: 610869 dataset_size: 3376266 - config_name: PAN-X.vi features: - name: tokens sequence: string - name: ner_tags sequence: class_label: names: '0': O '1': B-PER '2': I-PER '3': B-ORG '4': I-ORG '5': B-LOC '6': I-LOC - name: langs sequence: string splits: - name: train num_bytes: 3153187 num_examples: 20000 - name: validation num_bytes: 1565123 num_examples: 10000 - name: test num_bytes: 1580196 num_examples: 10000 download_size: 1375631 dataset_size: 6298506 - config_name: PAN-X.yo features: - name: tokens sequence: string - name: ner_tags sequence: class_label: names: '0': O '1': B-PER '2': I-PER '3': B-ORG '4': I-ORG '5': B-LOC '6': I-LOC - name: langs sequence: string splits: - name: train num_bytes: 14689 num_examples: 100 - name: validation num_bytes: 13225 num_examples: 100 - name: test num_bytes: 13513 num_examples: 100 download_size: 17337 dataset_size: 41427 - config_name: PAN-X.zh features: - name: tokens sequence: string - name: ner_tags sequence: class_label: names: '0': O '1': B-PER '2': I-PER '3': B-ORG '4': I-ORG '5': B-LOC '6': I-LOC - name: langs sequence: string splits: - name: train num_bytes: 8832011 num_examples: 20000 - name: validation num_bytes: 4491305 num_examples: 10000 - name: test num_bytes: 4363152 num_examples: 10000 download_size: 2083198 dataset_size: 17686468 - config_name: PAWS-X.de features: - name: sentence1 dtype: string - name: sentence2 dtype: string - name: label dtype: string splits: - name: train num_bytes: 12451823 num_examples: 49380 - name: validation num_bytes: 499997 num_examples: 2000 - name: test num_bytes: 510182 num_examples: 2000 download_size: 9294034 dataset_size: 13462002 - config_name: PAWS-X.en features: - name: sentence1 dtype: string - name: sentence2 dtype: string - name: label dtype: string splits: - name: train num_bytes: 11827659 num_examples: 49175 - name: validation num_bytes: 478279 num_examples: 2000 - name: test num_bytes: 480726 num_examples: 2000 download_size: 8717639 dataset_size: 12786664 - config_name: PAWS-X.es features: - name: sentence1 dtype: string - name: sentence2 dtype: string - name: label dtype: string splits: - name: train num_bytes: 12462047 num_examples: 49401 - name: validation num_bytes: 494057 num_examples: 1961 - name: test num_bytes: 505035 num_examples: 2000 download_size: 9229918 dataset_size: 13461139 - config_name: PAWS-X.fr features: - name: sentence1 dtype: string - name: sentence2 dtype: string - name: label dtype: string splits: - name: train num_bytes: 12948452 num_examples: 49399 - name: validation num_bytes: 516099 num_examples: 1988 - name: test num_bytes: 521019 num_examples: 2000 download_size: 9464987 dataset_size: 13985570 - config_name: PAWS-X.ja features: - name: sentence1 dtype: string - name: sentence2 dtype: string - name: label dtype: string splits: - name: train num_bytes: 14695593 num_examples: 49401 - name: validation num_bytes: 647762 num_examples: 2000 - name: test num_bytes: 654628 num_examples: 2000 download_size: 10136228 dataset_size: 15997983 - config_name: PAWS-X.ko features: - name: sentence1 dtype: string - name: sentence2 dtype: string - name: label dtype: string splits: - name: train num_bytes: 13542597 num_examples: 49164 - name: validation num_bytes: 540775 num_examples: 2000 - name: test num_bytes: 547966 num_examples: 1999 download_size: 9926292 dataset_size: 14631338 - config_name: PAWS-X.zh features: - name: sentence1 dtype: string - name: sentence2 dtype: string - name: label dtype: string splits: - name: train num_bytes: 10469652 num_examples: 49401 - name: validation num_bytes: 459108 num_examples: 2000 - name: test num_bytes: 460626 num_examples: 2000 download_size: 8878855 dataset_size: 11389386 - config_name: SQuAD features: - name: id dtype: string - name: title dtype: string - name: context dtype: string - name: question dtype: string - name: answers sequence: - name: answer_start dtype: int32 - name: text dtype: string splits: - name: train num_bytes: 79316858 num_examples: 87599 - name: validation num_bytes: 10472597 num_examples: 10570 download_size: 16272656 dataset_size: 89789455 - config_name: XNLI features: - name: language dtype: string - name: sentence1 dtype: string - name: sentence2 dtype: string - name: gold_label dtype: string splits: - name: test num_bytes: 20359372 num_examples: 75150 - name: validation num_bytes: 10049239 num_examples: 37350 download_size: 8881623 dataset_size: 30408611 - config_name: XQuAD.ar features: - name: id dtype: string - name: context dtype: string - name: question dtype: string - name: answers sequence: - name: answer_start dtype: int32 - name: text dtype: string splits: - name: validation num_bytes: 1722775 num_examples: 1190 download_size: 263032 dataset_size: 1722775 - config_name: XQuAD.de features: - name: id dtype: string - name: context dtype: string - name: question dtype: string - name: answers sequence: - name: answer_start dtype: int32 - name: text dtype: string splits: - name: validation num_bytes: 1283277 num_examples: 1190 download_size: 241987 dataset_size: 1283277 - config_name: XQuAD.el features: - name: id dtype: string - name: context dtype: string - name: question dtype: string - name: answers sequence: - name: answer_start dtype: int32 - name: text dtype: string splits: - name: validation num_bytes: 2206666 num_examples: 1190 download_size: 324409 dataset_size: 2206666 - config_name: XQuAD.en features: - name: id dtype: string - name: context dtype: string - name: question dtype: string - name: answers sequence: - name: answer_start dtype: int32 - name: text dtype: string splits: - name: validation num_bytes: 1116099 num_examples: 1190 download_size: 212402 dataset_size: 1116099 - config_name: XQuAD.es features: - name: id dtype: string - name: context dtype: string - name: question dtype: string - name: answers sequence: - name: answer_start dtype: int32 - name: text dtype: string splits: - name: validation num_bytes: 1273475 num_examples: 1190 download_size: 236904 dataset_size: 1273475 - config_name: XQuAD.hi features: - name: id dtype: string - name: context dtype: string - name: question dtype: string - name: answers sequence: - name: answer_start dtype: int32 - name: text dtype: string splits: - name: validation num_bytes: 2682951 num_examples: 1190 download_size: 322113 dataset_size: 2682951 - config_name: XQuAD.ru features: - name: id dtype: string - name: context dtype: string - name: question dtype: string - name: answers sequence: - name: answer_start dtype: int32 - name: text dtype: string splits: - name: validation num_bytes: 2136966 num_examples: 1190 download_size: 321758 dataset_size: 2136966 - config_name: XQuAD.th features: - name: id dtype: string - name: context dtype: string - name: question dtype: string - name: answers sequence: - name: answer_start dtype: int32 - name: text dtype: string splits: - name: validation num_bytes: 2854935 num_examples: 1190 download_size: 337337 dataset_size: 2854935 - config_name: XQuAD.tr features: - name: id dtype: string - name: context dtype: string - name: question dtype: string - name: answers sequence: - name: answer_start dtype: int32 - name: text dtype: string splits: - name: validation num_bytes: 1210739 num_examples: 1190 download_size: 228394 dataset_size: 1210739 - config_name: XQuAD.vi features: - name: id dtype: string - name: context dtype: string - name: question dtype: string - name: answers sequence: - name: answer_start dtype: int32 - name: text dtype: string splits: - name: validation num_bytes: 1477215 num_examples: 1190 download_size: 237674 dataset_size: 1477215 - config_name: XQuAD.zh features: - name: id dtype: string - name: context dtype: string - name: question dtype: string - name: answers sequence: - name: answer_start dtype: int32 - name: text dtype: string splits: - name: validation num_bytes: 984217 num_examples: 1190 download_size: 205798 dataset_size: 984217 - config_name: bucc18.de features: - name: source_sentence dtype: string - name: target_sentence dtype: string - name: source_lang dtype: string - name: target_lang dtype: string splits: - name: validation num_bytes: 248691 num_examples: 1038 - name: test num_bytes: 2325685 num_examples: 9580 download_size: 1636130 dataset_size: 2574376 - config_name: bucc18.fr features: - name: source_sentence dtype: string - name: target_sentence dtype: string - name: source_lang dtype: string - name: target_lang dtype: string splits: - name: validation num_bytes: 212497 num_examples: 929 - name: test num_bytes: 2082403 num_examples: 9086 download_size: 1437096 dataset_size: 2294900 - config_name: bucc18.ru features: - name: source_sentence dtype: string - name: target_sentence dtype: string - name: source_lang dtype: string - name: target_lang dtype: string splits: - name: validation num_bytes: 761331 num_examples: 2374 - name: test num_bytes: 4641646 num_examples: 14435 download_size: 3074476 dataset_size: 5402977 - config_name: bucc18.zh features: - name: source_sentence dtype: string - name: target_sentence dtype: string - name: source_lang dtype: string - name: target_lang dtype: string splits: - name: validation num_bytes: 55723 num_examples: 257 - name: test num_bytes: 415909 num_examples: 1899 download_size: 320378 dataset_size: 471632 - config_name: tatoeba.afr features: - name: source_sentence dtype: string - name: target_sentence dtype: string - name: source_lang dtype: string - name: target_lang dtype: string splits: - name: validation num_bytes: 250635 num_examples: 1000 download_size: 47676 dataset_size: 250635 - config_name: tatoeba.ara features: - name: source_sentence dtype: string - name: target_sentence dtype: string - name: source_lang dtype: string - name: target_lang dtype: string splits: - name: validation num_bytes: 263650 num_examples: 1000 download_size: 51228 dataset_size: 263650 - config_name: tatoeba.ben features: - name: source_sentence dtype: string - name: target_sentence dtype: string - name: source_lang dtype: string - name: target_lang dtype: string splits: - name: validation num_bytes: 282703 num_examples: 1000 download_size: 51362 dataset_size: 282703 - config_name: tatoeba.bul features: - name: source_sentence dtype: string - name: target_sentence dtype: string - name: source_lang dtype: string - name: target_lang dtype: string splits: - name: validation num_bytes: 293279 num_examples: 1000 download_size: 62454 dataset_size: 293279 - config_name: tatoeba.cmn features: - name: source_sentence dtype: string - name: target_sentence dtype: string - name: source_lang dtype: string - name: target_lang dtype: string splits: - name: validation num_bytes: 259931 num_examples: 1000 download_size: 58281 dataset_size: 259931 - config_name: tatoeba.deu features: - name: source_sentence dtype: string - name: target_sentence dtype: string - name: source_lang dtype: string - name: target_lang dtype: string splits: - name: validation num_bytes: 296567 num_examples: 1000 download_size: 79066 dataset_size: 296567 - config_name: tatoeba.ell features: - name: source_sentence dtype: string - name: target_sentence dtype: string - name: source_lang dtype: string - name: target_lang dtype: string splits: - name: validation num_bytes: 269961 num_examples: 1000 download_size: 52251 dataset_size: 269961 - config_name: tatoeba.est features: - name: source_sentence dtype: string - name: target_sentence dtype: string - name: source_lang dtype: string - name: target_lang dtype: string splits: - name: validation num_bytes: 250728 num_examples: 1000 download_size: 49968 dataset_size: 250728 - config_name: tatoeba.eus features: - name: source_sentence dtype: string - name: target_sentence dtype: string - name: source_lang dtype: string - name: target_lang dtype: string splits: - name: validation num_bytes: 257068 num_examples: 1000 download_size: 54271 dataset_size: 257068 - config_name: tatoeba.fin features: - name: source_sentence dtype: string - name: target_sentence dtype: string - name: source_lang dtype: string - name: target_lang dtype: string splits: - name: validation num_bytes: 266669 num_examples: 1000 download_size: 60580 dataset_size: 266669 - config_name: tatoeba.fra features: - name: source_sentence dtype: string - name: target_sentence dtype: string - name: source_lang dtype: string - name: target_lang dtype: string splits: - name: validation num_bytes: 271018 num_examples: 1000 download_size: 60925 dataset_size: 271018 - config_name: tatoeba.heb features: - name: source_sentence dtype: string - name: target_sentence dtype: string - name: source_lang dtype: string - name: target_lang dtype: string splits: - name: validation num_bytes: 274500 num_examples: 1000 download_size: 57306 dataset_size: 274500 - config_name: tatoeba.hin features: - name: source_sentence dtype: string - name: target_sentence dtype: string - name: source_lang dtype: string - name: target_lang dtype: string splits: - name: validation num_bytes: 313558 num_examples: 1000 download_size: 68816 dataset_size: 313558 - config_name: tatoeba.hun features: - name: source_sentence dtype: string - name: target_sentence dtype: string - name: source_lang dtype: string - name: target_lang dtype: string splits: - name: validation num_bytes: 259889 num_examples: 1000 download_size: 58096 dataset_size: 259889 - config_name: tatoeba.ind features: - name: source_sentence dtype: string - name: target_sentence dtype: string - name: source_lang dtype: string - name: target_lang dtype: string splits: - name: validation num_bytes: 265844 num_examples: 1000 download_size: 57047 dataset_size: 265844 - config_name: tatoeba.ita features: - name: source_sentence dtype: string - name: target_sentence dtype: string - name: source_lang dtype: string - name: target_lang dtype: string splits: - name: validation num_bytes: 256833 num_examples: 1000 download_size: 52422 dataset_size: 256833 - config_name: tatoeba.jav features: - name: source_sentence dtype: string - name: target_sentence dtype: string - name: source_lang dtype: string - name: target_lang dtype: string splits: - name: validation num_bytes: 53068 num_examples: 205 download_size: 15208 dataset_size: 53068 - config_name: tatoeba.jpn features: - name: source_sentence dtype: string - name: target_sentence dtype: string - name: source_lang dtype: string - name: target_lang dtype: string splits: - name: validation num_bytes: 284083 num_examples: 1000 download_size: 66620 dataset_size: 284083 - config_name: tatoeba.kat features: - name: source_sentence dtype: string - name: target_sentence dtype: string - name: source_lang dtype: string - name: target_lang dtype: string splits: - name: validation num_bytes: 214646 num_examples: 746 download_size: 41759 dataset_size: 214646 - config_name: tatoeba.kaz features: - name: source_sentence dtype: string - name: target_sentence dtype: string - name: source_lang dtype: string - name: target_lang dtype: string splits: - name: validation num_bytes: 157003 num_examples: 575 download_size: 35693 dataset_size: 157003 - config_name: tatoeba.kor features: - name: source_sentence dtype: string - name: target_sentence dtype: string - name: source_lang dtype: string - name: target_lang dtype: string splits: - name: validation num_bytes: 270139 num_examples: 1000 download_size: 61210 dataset_size: 270139 - config_name: tatoeba.mal features: - name: source_sentence dtype: string - name: target_sentence dtype: string - name: source_lang dtype: string - name: target_lang dtype: string splits: - name: validation num_bytes: 225934 num_examples: 687 download_size: 51077 dataset_size: 225934 - config_name: tatoeba.mar features: - name: source_sentence dtype: string - name: target_sentence dtype: string - name: source_lang dtype: string - name: target_lang dtype: string splits: - name: validation num_bytes: 291542 num_examples: 1000 download_size: 56575 dataset_size: 291542 - config_name: tatoeba.nld features: - name: source_sentence dtype: string - name: target_sentence dtype: string - name: source_lang dtype: string - name: target_lang dtype: string splits: - name: validation num_bytes: 264263 num_examples: 1000 download_size: 59774 dataset_size: 264263 - config_name: tatoeba.pes features: - name: source_sentence dtype: string - name: target_sentence dtype: string - name: source_lang dtype: string - name: target_lang dtype: string splits: - name: validation num_bytes: 284719 num_examples: 1000 download_size: 64642 dataset_size: 284719 - config_name: tatoeba.por features: - name: source_sentence dtype: string - name: target_sentence dtype: string - name: source_lang dtype: string - name: target_lang dtype: string splits: - name: validation num_bytes: 266185 num_examples: 1000 download_size: 58250 dataset_size: 266185 - config_name: tatoeba.rus features: - name: source_sentence dtype: string - name: target_sentence dtype: string - name: source_lang dtype: string - name: target_lang dtype: string splits: - name: validation num_bytes: 283472 num_examples: 1000 download_size: 61601 dataset_size: 283472 - config_name: tatoeba.spa features: - name: source_sentence dtype: string - name: target_sentence dtype: string - name: source_lang dtype: string - name: target_lang dtype: string splits: - name: validation num_bytes: 263266 num_examples: 1000 download_size: 57055 dataset_size: 263266 - config_name: tatoeba.swh features: - name: source_sentence dtype: string - name: target_sentence dtype: string - name: source_lang dtype: string - name: target_lang dtype: string splits: - name: validation num_bytes: 94957 num_examples: 390 download_size: 19362 dataset_size: 94957 - config_name: tatoeba.tam features: - name: source_sentence dtype: string - name: target_sentence dtype: string - name: source_lang dtype: string - name: target_lang dtype: string splits: - name: validation num_bytes: 98078 num_examples: 307 download_size: 23648 dataset_size: 98078 - config_name: tatoeba.tel features: - name: source_sentence dtype: string - name: target_sentence dtype: string - name: source_lang dtype: string - name: target_lang dtype: string splits: - name: validation num_bytes: 69837 num_examples: 234 download_size: 18260 dataset_size: 69837 - config_name: tatoeba.tgl features: - name: source_sentence dtype: string - name: target_sentence dtype: string - name: source_lang dtype: string - name: target_lang dtype: string splits: - name: validation num_bytes: 259138 num_examples: 1000 download_size: 53699 dataset_size: 259138 - config_name: tatoeba.tha features: - name: source_sentence dtype: string - name: target_sentence dtype: string - name: source_lang dtype: string - name: target_lang dtype: string splits: - name: validation num_bytes: 167866 num_examples: 548 download_size: 39659 dataset_size: 167866 - config_name: tatoeba.tur features: - name: source_sentence dtype: string - name: target_sentence dtype: string - name: source_lang dtype: string - name: target_lang dtype: string splits: - name: validation num_bytes: 262885 num_examples: 1000 download_size: 54137 dataset_size: 262885 - config_name: tatoeba.urd features: - name: source_sentence dtype: string - name: target_sentence dtype: string - name: source_lang dtype: string - name: target_lang dtype: string splits: - name: validation num_bytes: 279712 num_examples: 1000 download_size: 60399 dataset_size: 279712 - config_name: tatoeba.vie features: - name: source_sentence dtype: string - name: target_sentence dtype: string - name: source_lang dtype: string - name: target_lang dtype: string splits: - name: validation num_bytes: 282407 num_examples: 1000 download_size: 66746 dataset_size: 282407 - config_name: tydiqa features: - name: id dtype: string - name: title dtype: string - name: context dtype: string - name: question dtype: string - name: answers sequence: - name: answer_start dtype: int32 - name: text dtype: string splits: - name: train num_bytes: 52948467 num_examples: 49881 - name: validation num_bytes: 5006433 num_examples: 5077 download_size: 29402238 dataset_size: 57954900 - config_name: udpos.Afrikaans features: - name: tokens sequence: string - name: pos_tags sequence: class_label: names: '0': ADJ '1': ADP '2': ADV '3': AUX '4': CCONJ '5': DET '6': INTJ '7': NOUN '8': NUM '9': PART '10': PRON '11': PROPN '12': PUNCT '13': SCONJ '14': SYM '15': VERB '16': X splits: - name: train num_bytes: 586370 num_examples: 1315 - name: validation num_bytes: 91290 num_examples: 194 - name: test num_bytes: 174244 num_examples: 425 download_size: 193788 dataset_size: 851904 - config_name: udpos.Arabic features: - name: tokens sequence: string - name: pos_tags sequence: class_label: names: '0': ADJ '1': ADP '2': ADV '3': AUX '4': CCONJ '5': DET '6': INTJ '7': NOUN '8': NUM '9': PART '10': PRON '11': PROPN '12': PUNCT '13': SCONJ '14': SYM '15': VERB '16': X splits: - name: train num_bytes: 4453682 num_examples: 6075 - name: validation num_bytes: 593650 num_examples: 909 - name: test num_bytes: 973822 num_examples: 1680 download_size: 1186113 dataset_size: 6021154 - config_name: udpos.Basque features: - name: tokens sequence: string - name: pos_tags sequence: class_label: names: '0': ADJ '1': ADP '2': ADV '3': AUX '4': CCONJ '5': DET '6': INTJ '7': NOUN '8': NUM '9': PART '10': PRON '11': PROPN '12': PUNCT '13': SCONJ '14': SYM '15': VERB '16': X splits: - name: train num_bytes: 1327713 num_examples: 5396 - name: validation num_bytes: 438671 num_examples: 1798 - name: test num_bytes: 444644 num_examples: 1799 download_size: 703094 dataset_size: 2211028 - config_name: udpos.Bulgarian features: - name: tokens sequence: string - name: pos_tags sequence: class_label: names: '0': ADJ '1': ADP '2': ADV '3': AUX '4': CCONJ '5': DET '6': INTJ '7': NOUN '8': NUM '9': PART '10': PRON '11': PROPN '12': PUNCT '13': SCONJ '14': SYM '15': VERB '16': X splits: - name: train num_bytes: 2689767 num_examples: 8907 - name: validation num_bytes: 347117 num_examples: 1115 - name: test num_bytes: 339947 num_examples: 1116 download_size: 926186 dataset_size: 3376831 - config_name: udpos.Chinese features: - name: tokens sequence: string - name: pos_tags sequence: class_label: names: '0': ADJ '1': ADP '2': ADV '3': AUX '4': CCONJ '5': DET '6': INTJ '7': NOUN '8': NUM '9': PART '10': PRON '11': PROPN '12': PUNCT '13': SCONJ '14': SYM '15': VERB '16': X splits: - name: train num_bytes: 4218891 num_examples: 18998 - name: validation num_bytes: 594448 num_examples: 3038 - name: test num_bytes: 1236051 num_examples: 5528 download_size: 1471747 dataset_size: 6049390 - config_name: udpos.Dutch features: - name: tokens sequence: string - name: pos_tags sequence: class_label: names: '0': ADJ '1': ADP '2': ADV '3': AUX '4': CCONJ '5': DET '6': INTJ '7': NOUN '8': NUM '9': PART '10': PRON '11': PROPN '12': PUNCT '13': SCONJ '14': SYM '15': VERB '16': X splits: - name: train num_bytes: 4517994 num_examples: 18051 - name: validation num_bytes: 393592 num_examples: 1394 - name: test num_bytes: 397904 num_examples: 1471 download_size: 1410982 dataset_size: 5309490 - config_name: udpos.English features: - name: tokens sequence: string - name: pos_tags sequence: class_label: names: '0': ADJ '1': ADP '2': ADV '3': AUX '4': CCONJ '5': DET '6': INTJ '7': NOUN '8': NUM '9': PART '10': PRON '11': PROPN '12': PUNCT '13': SCONJ '14': SYM '15': VERB '16': X splits: - name: train num_bytes: 6225509 num_examples: 21253 - name: validation num_bytes: 1042040 num_examples: 3974 - name: test num_bytes: 1421148 num_examples: 5440 download_size: 2116535 dataset_size: 8688697 - config_name: udpos.Estonian features: - name: tokens sequence: string - name: pos_tags sequence: class_label: names: '0': ADJ '1': ADP '2': ADV '3': AUX '4': CCONJ '5': DET '6': INTJ '7': NOUN '8': NUM '9': PART '10': PRON '11': PROPN '12': PUNCT '13': SCONJ '14': SYM '15': VERB '16': X splits: - name: train num_bytes: 6614893 num_examples: 25749 - name: validation num_bytes: 814171 num_examples: 3125 - name: test num_bytes: 1065701 num_examples: 3760 download_size: 2619121 dataset_size: 8494765 - config_name: udpos.Finnish features: - name: tokens sequence: string - name: pos_tags sequence: class_label: names: '0': ADJ '1': ADP '2': ADV '3': AUX '4': CCONJ '5': DET '6': INTJ '7': NOUN '8': NUM '9': PART '10': PRON '11': PROPN '12': PUNCT '13': SCONJ '14': SYM '15': VERB '16': X splits: - name: train num_bytes: 5613706 num_examples: 27198 - name: validation num_bytes: 656646 num_examples: 3239 - name: test num_bytes: 1025726 num_examples: 4422 download_size: 2503217 dataset_size: 7296078 - config_name: udpos.French features: - name: tokens sequence: string - name: pos_tags sequence: class_label: names: '0': ADJ '1': ADP '2': ADV '3': AUX '4': CCONJ '5': DET '6': INTJ '7': NOUN '8': NUM '9': PART '10': PRON '11': PROPN '12': PUNCT '13': SCONJ '14': SYM '15': VERB '16': X splits: - name: train num_bytes: 10118933 num_examples: 47308 - name: validation num_bytes: 1294096 num_examples: 5979 - name: test num_bytes: 1731049 num_examples: 9465 download_size: 3378680 dataset_size: 13144078 - config_name: udpos.German features: - name: tokens sequence: string - name: pos_tags sequence: class_label: names: '0': ADJ '1': ADP '2': ADV '3': AUX '4': CCONJ '5': DET '6': INTJ '7': NOUN '8': NUM '9': PART '10': PRON '11': PROPN '12': PUNCT '13': SCONJ '14': SYM '15': VERB '16': X splits: - name: train num_bytes: 54773777 num_examples: 166849 - name: validation num_bytes: 6044838 num_examples: 19233 - name: test num_bytes: 7345863 num_examples: 22458 download_size: 18623155 dataset_size: 68164478 - config_name: udpos.Greek features: - name: tokens sequence: string - name: pos_tags sequence: class_label: names: '0': ADJ '1': ADP '2': ADV '3': AUX '4': CCONJ '5': DET '6': INTJ '7': NOUN '8': NUM '9': PART '10': PRON '11': PROPN '12': PUNCT '13': SCONJ '14': SYM '15': VERB '16': X splits: - name: train num_bytes: 8932104 num_examples: 28152 - name: validation num_bytes: 1062447 num_examples: 2559 - name: test num_bytes: 1028665 num_examples: 2809 download_size: 2763293 dataset_size: 11023216 - config_name: udpos.Hebrew features: - name: tokens sequence: string - name: pos_tags sequence: class_label: names: '0': ADJ '1': ADP '2': ADV '3': AUX '4': CCONJ '5': DET '6': INTJ '7': NOUN '8': NUM '9': PART '10': PRON '11': PROPN '12': PUNCT '13': SCONJ '14': SYM '15': VERB '16': X splits: - name: train num_bytes: 2505691 num_examples: 5241 - name: validation num_bytes: 210013 num_examples: 484 - name: test num_bytes: 223865 num_examples: 491 download_size: 624771 dataset_size: 2939569 - config_name: udpos.Hindi features: - name: tokens sequence: string - name: pos_tags sequence: class_label: names: '0': ADJ '1': ADP '2': ADV '3': AUX '4': CCONJ '5': DET '6': INTJ '7': NOUN '8': NUM '9': PART '10': PRON '11': PROPN '12': PUNCT '13': SCONJ '14': SYM '15': VERB '16': X splits: - name: train num_bytes: 6690250 num_examples: 13304 - name: validation num_bytes: 839702 num_examples: 1659 - name: test num_bytes: 1400225 num_examples: 2684 download_size: 1468314 dataset_size: 8930177 - config_name: udpos.Hungarian features: - name: tokens sequence: string - name: pos_tags sequence: class_label: names: '0': ADJ '1': ADP '2': ADV '3': AUX '4': CCONJ '5': DET '6': INTJ '7': NOUN '8': NUM '9': PART '10': PRON '11': PROPN '12': PUNCT '13': SCONJ '14': SYM '15': VERB '16': X splits: - name: train num_bytes: 372226 num_examples: 910 - name: validation num_bytes: 215879 num_examples: 441 - name: test num_bytes: 193728 num_examples: 449 download_size: 251882 dataset_size: 781833 - config_name: udpos.Indonesian features: - name: tokens sequence: string - name: pos_tags sequence: class_label: names: '0': ADJ '1': ADP '2': ADV '3': AUX '4': CCONJ '5': DET '6': INTJ '7': NOUN '8': NUM '9': PART '10': PRON '11': PROPN '12': PUNCT '13': SCONJ '14': SYM '15': VERB '16': X splits: - name: train num_bytes: 1710678 num_examples: 4477 - name: validation num_bytes: 220863 num_examples: 559 - name: test num_bytes: 557101 num_examples: 1557 download_size: 684225 dataset_size: 2488642 - config_name: udpos.Italian features: - name: tokens sequence: string - name: pos_tags sequence: class_label: names: '0': ADJ '1': ADP '2': ADV '3': AUX '4': CCONJ '5': DET '6': INTJ '7': NOUN '8': NUM '9': PART '10': PRON '11': PROPN '12': PUNCT '13': SCONJ '14': SYM '15': VERB '16': X splits: - name: train num_bytes: 11299293 num_examples: 29685 - name: validation num_bytes: 988996 num_examples: 2278 - name: test num_bytes: 1337869 num_examples: 3518 download_size: 3256246 dataset_size: 13626158 - config_name: udpos.Japanese features: - name: tokens sequence: string - name: pos_tags sequence: class_label: names: '0': ADJ '1': ADP '2': ADV '3': AUX '4': CCONJ '5': DET '6': INTJ '7': NOUN '8': NUM '9': PART '10': PRON '11': PROPN '12': PUNCT '13': SCONJ '14': SYM '15': VERB '16': X splits: - name: train num_bytes: 2792951 num_examples: 7125 - name: validation num_bytes: 200356 num_examples: 511 - name: test num_bytes: 928902 num_examples: 2372 download_size: 1012282 dataset_size: 3922209 - config_name: udpos.Kazakh features: - name: tokens sequence: string - name: pos_tags sequence: class_label: names: '0': ADJ '1': ADP '2': ADV '3': AUX '4': CCONJ '5': DET '6': INTJ '7': NOUN '8': NUM '9': PART '10': PRON '11': PROPN '12': PUNCT '13': SCONJ '14': SYM '15': VERB '16': X splits: - name: train num_bytes: 11438 num_examples: 31 - name: test num_bytes: 228924 num_examples: 1047 download_size: 76300 dataset_size: 240362 - config_name: udpos.Korean features: - name: tokens sequence: string - name: pos_tags sequence: class_label: names: '0': ADJ '1': ADP '2': ADV '3': AUX '4': CCONJ '5': DET '6': INTJ '7': NOUN '8': NUM '9': PART '10': PRON '11': PROPN '12': PUNCT '13': SCONJ '14': SYM '15': VERB '16': X splits: - name: train num_bytes: 7341267 num_examples: 27410 - name: validation num_bytes: 782587 num_examples: 3016 - name: test num_bytes: 1162539 num_examples: 4276 download_size: 3115101 dataset_size: 9286393 - config_name: udpos.Marathi features: - name: tokens sequence: string - name: pos_tags sequence: class_label: names: '0': ADJ '1': ADP '2': ADV '3': AUX '4': CCONJ '5': DET '6': INTJ '7': NOUN '8': NUM '9': PART '10': PRON '11': PROPN '12': PUNCT '13': SCONJ '14': SYM '15': VERB '16': X splits: - name: train num_bytes: 59023 num_examples: 373 - name: validation num_bytes: 8497 num_examples: 46 - name: test num_bytes: 7871 num_examples: 47 download_size: 22133 dataset_size: 75391 - config_name: udpos.Persian features: - name: tokens sequence: string - name: pos_tags sequence: class_label: names: '0': ADJ '1': ADP '2': ADV '3': AUX '4': CCONJ '5': DET '6': INTJ '7': NOUN '8': NUM '9': PART '10': PRON '11': PROPN '12': PUNCT '13': SCONJ '14': SYM '15': VERB '16': X splits: - name: train num_bytes: 2400776 num_examples: 4798 - name: validation num_bytes: 317053 num_examples: 599 - name: test num_bytes: 320683 num_examples: 600 download_size: 606912 dataset_size: 3038512 - config_name: udpos.Portuguese features: - name: tokens sequence: string - name: pos_tags sequence: class_label: names: '0': ADJ '1': ADP '2': ADV '3': AUX '4': CCONJ '5': DET '6': INTJ '7': NOUN '8': NUM '9': PART '10': PRON '11': PROPN '12': PUNCT '13': SCONJ '14': SYM '15': VERB '16': X splits: - name: train num_bytes: 7669556 num_examples: 17992 - name: validation num_bytes: 712397 num_examples: 1770 - name: test num_bytes: 1082582 num_examples: 2681 download_size: 2505672 dataset_size: 9464535 - config_name: udpos.Russian features: - name: tokens sequence: string - name: pos_tags sequence: class_label: names: '0': ADJ '1': ADP '2': ADV '3': AUX '4': CCONJ '5': DET '6': INTJ '7': NOUN '8': NUM '9': PART '10': PRON '11': PROPN '12': PUNCT '13': SCONJ '14': SYM '15': VERB '16': X splits: - name: train num_bytes: 24230098 num_examples: 67435 - name: validation num_bytes: 3457031 num_examples: 9960 - name: test num_bytes: 4236693 num_examples: 11336 download_size: 8818512 dataset_size: 31923822 - config_name: udpos.Spanish features: - name: tokens sequence: string - name: pos_tags sequence: class_label: names: '0': ADJ '1': ADP '2': ADV '3': AUX '4': CCONJ '5': DET '6': INTJ '7': NOUN '8': NUM '9': PART '10': PRON '11': PROPN '12': PUNCT '13': SCONJ '14': SYM '15': VERB '16': X splits: - name: train num_bytes: 13858406 num_examples: 28492 - name: validation num_bytes: 1498765 num_examples: 3054 - name: test num_bytes: 1476500 num_examples: 3147 download_size: 4347905 dataset_size: 16833671 - config_name: udpos.Tagalog features: - name: tokens sequence: string - name: pos_tags sequence: class_label: names: '0': ADJ '1': ADP '2': ADV '3': AUX '4': CCONJ '5': DET '6': INTJ '7': NOUN '8': NUM '9': PART '10': PRON '11': PROPN '12': PUNCT '13': SCONJ '14': SYM '15': VERB '16': X splits: - name: test num_bytes: 5153 num_examples: 55 download_size: 3345 dataset_size: 5153 - config_name: udpos.Tamil features: - name: tokens sequence: string - name: pos_tags sequence: class_label: names: '0': ADJ '1': ADP '2': ADV '3': AUX '4': CCONJ '5': DET '6': INTJ '7': NOUN '8': NUM '9': PART '10': PRON '11': PROPN '12': PUNCT '13': SCONJ '14': SYM '15': VERB '16': X splits: - name: train num_bytes: 202596 num_examples: 400 - name: validation num_bytes: 40031 num_examples: 80 - name: test num_bytes: 62366 num_examples: 120 download_size: 73764 dataset_size: 304993 - config_name: udpos.Telugu features: - name: tokens sequence: string - name: pos_tags sequence: class_label: names: '0': ADJ '1': ADP '2': ADV '3': AUX '4': CCONJ '5': DET '6': INTJ '7': NOUN '8': NUM '9': PART '10': PRON '11': PROPN '12': PUNCT '13': SCONJ '14': SYM '15': VERB '16': X splits: - name: train num_bytes: 138049 num_examples: 1051 - name: validation num_bytes: 17990 num_examples: 131 - name: test num_bytes: 19575 num_examples: 146 download_size: 46045 dataset_size: 175614 - config_name: udpos.Thai features: - name: tokens sequence: string - name: pos_tags sequence: class_label: names: '0': ADJ '1': ADP '2': ADV '3': AUX '4': CCONJ '5': DET '6': INTJ '7': NOUN '8': NUM '9': PART '10': PRON '11': PROPN '12': PUNCT '13': SCONJ '14': SYM '15': VERB '16': X splits: - name: test num_bytes: 561336 num_examples: 1000 download_size: 92925 dataset_size: 561336 - config_name: udpos.Turkish features: - name: tokens sequence: string - name: pos_tags sequence: class_label: names: '0': ADJ '1': ADP '2': ADV '3': AUX '4': CCONJ '5': DET '6': INTJ '7': NOUN '8': NUM '9': PART '10': PRON '11': PROPN '12': PUNCT '13': SCONJ '14': SYM '15': VERB '16': X splits: - name: train num_bytes: 704405 num_examples: 3664 - name: validation num_bytes: 186455 num_examples: 988 - name: test num_bytes: 827382 num_examples: 4785 download_size: 581177 dataset_size: 1718242 - config_name: udpos.Urdu features: - name: tokens sequence: string - name: pos_tags sequence: class_label: names: '0': ADJ '1': ADP '2': ADV '3': AUX '4': CCONJ '5': DET '6': INTJ '7': NOUN '8': NUM '9': PART '10': PRON '11': PROPN '12': PUNCT '13': SCONJ '14': SYM '15': VERB '16': X splits: - name: train num_bytes: 2107362 num_examples: 4043 - name: validation num_bytes: 284261 num_examples: 552 - name: test num_bytes: 288553 num_examples: 535 download_size: 499594 dataset_size: 2680176 - config_name: udpos.Vietnamese features: - name: tokens sequence: string - name: pos_tags sequence: class_label: names: '0': ADJ '1': ADP '2': ADV '3': AUX '4': CCONJ '5': DET '6': INTJ '7': NOUN '8': NUM '9': PART '10': PRON '11': PROPN '12': PUNCT '13': SCONJ '14': SYM '15': VERB '16': X splits: - name: train num_bytes: 367335 num_examples: 1400 - name: validation num_bytes: 206188 num_examples: 800 - name: test num_bytes: 214063 num_examples: 800 download_size: 181239 dataset_size: 787586 - config_name: udpos.Yoruba features: - name: tokens sequence: string - name: pos_tags sequence: class_label: names: '0': ADJ '1': ADP '2': ADV '3': AUX '4': CCONJ '5': DET '6': INTJ '7': NOUN '8': NUM '9': PART '10': PRON '11': PROPN '12': PUNCT '13': SCONJ '14': SYM '15': VERB '16': X splits: - name: test num_bytes: 44656 num_examples: 100 download_size: 10151 dataset_size: 44656 configs: - config_name: MLQA.ar.ar data_files: - split: test path: MLQA.ar.ar/test-* - split: validation path: MLQA.ar.ar/validation-* - config_name: MLQA.ar.de data_files: - split: test path: MLQA.ar.de/test-* - split: validation path: MLQA.ar.de/validation-* - config_name: MLQA.ar.en data_files: - split: test path: MLQA.ar.en/test-* - split: validation path: MLQA.ar.en/validation-* - config_name: MLQA.ar.es data_files: - split: test path: MLQA.ar.es/test-* - split: validation path: MLQA.ar.es/validation-* - config_name: MLQA.ar.hi data_files: - split: test path: MLQA.ar.hi/test-* - split: validation path: MLQA.ar.hi/validation-* - config_name: MLQA.ar.vi data_files: - split: test path: MLQA.ar.vi/test-* - split: validation path: MLQA.ar.vi/validation-* - config_name: MLQA.ar.zh data_files: - split: test path: MLQA.ar.zh/test-* - split: validation path: MLQA.ar.zh/validation-* - config_name: MLQA.de.ar data_files: - split: test path: MLQA.de.ar/test-* - split: validation path: MLQA.de.ar/validation-* - config_name: MLQA.de.de data_files: - split: test path: MLQA.de.de/test-* - split: validation path: MLQA.de.de/validation-* - config_name: MLQA.de.en data_files: - split: test path: MLQA.de.en/test-* - split: validation path: MLQA.de.en/validation-* - config_name: MLQA.de.es data_files: - split: test path: MLQA.de.es/test-* - split: validation path: MLQA.de.es/validation-* - config_name: MLQA.de.hi data_files: - split: test path: MLQA.de.hi/test-* - split: validation path: MLQA.de.hi/validation-* - config_name: MLQA.de.vi data_files: - split: test path: MLQA.de.vi/test-* - split: validation path: MLQA.de.vi/validation-* - config_name: MLQA.de.zh data_files: - split: test path: MLQA.de.zh/test-* - split: validation path: MLQA.de.zh/validation-* - config_name: MLQA.en.ar data_files: - split: test path: MLQA.en.ar/test-* - split: validation path: MLQA.en.ar/validation-* - config_name: MLQA.en.de data_files: - split: test path: MLQA.en.de/test-* - split: validation path: MLQA.en.de/validation-* - config_name: MLQA.en.en data_files: - split: test path: MLQA.en.en/test-* - split: validation path: MLQA.en.en/validation-* - config_name: MLQA.en.es data_files: - split: test path: MLQA.en.es/test-* - split: validation path: MLQA.en.es/validation-* - config_name: MLQA.en.hi data_files: - split: test path: MLQA.en.hi/test-* - split: validation path: MLQA.en.hi/validation-* - config_name: MLQA.en.vi data_files: - split: test path: MLQA.en.vi/test-* - split: validation path: MLQA.en.vi/validation-* - config_name: MLQA.en.zh data_files: - split: test path: MLQA.en.zh/test-* - split: validation path: MLQA.en.zh/validation-* - config_name: MLQA.es.ar data_files: - split: test path: MLQA.es.ar/test-* - split: validation path: MLQA.es.ar/validation-* - config_name: MLQA.es.de data_files: - split: test path: MLQA.es.de/test-* - split: validation path: MLQA.es.de/validation-* - config_name: MLQA.es.en data_files: - split: test path: MLQA.es.en/test-* - split: validation path: MLQA.es.en/validation-* - config_name: MLQA.es.es data_files: - split: test path: MLQA.es.es/test-* - split: validation path: MLQA.es.es/validation-* - config_name: MLQA.es.hi data_files: - split: test path: MLQA.es.hi/test-* - split: validation path: MLQA.es.hi/validation-* - config_name: MLQA.es.vi data_files: - split: test path: MLQA.es.vi/test-* - split: validation path: MLQA.es.vi/validation-* - config_name: MLQA.es.zh data_files: - split: test path: MLQA.es.zh/test-* - split: validation path: MLQA.es.zh/validation-* - config_name: MLQA.hi.ar data_files: - split: test path: MLQA.hi.ar/test-* - split: validation path: MLQA.hi.ar/validation-* - config_name: MLQA.hi.de data_files: - split: test path: MLQA.hi.de/test-* - split: validation path: MLQA.hi.de/validation-* - config_name: MLQA.hi.en data_files: - split: test path: MLQA.hi.en/test-* - split: validation path: MLQA.hi.en/validation-* - config_name: MLQA.hi.es data_files: - split: test path: MLQA.hi.es/test-* - split: validation path: MLQA.hi.es/validation-* - config_name: MLQA.hi.hi data_files: - split: test path: MLQA.hi.hi/test-* - split: validation path: MLQA.hi.hi/validation-* - config_name: MLQA.hi.vi data_files: - split: test path: MLQA.hi.vi/test-* - split: validation path: MLQA.hi.vi/validation-* - config_name: MLQA.hi.zh data_files: - split: test path: MLQA.hi.zh/test-* - split: validation path: MLQA.hi.zh/validation-* - config_name: MLQA.vi.ar data_files: - split: test path: MLQA.vi.ar/test-* - split: validation path: MLQA.vi.ar/validation-* - config_name: MLQA.vi.de data_files: - split: test path: MLQA.vi.de/test-* - split: validation path: MLQA.vi.de/validation-* - config_name: MLQA.vi.en data_files: - split: test path: MLQA.vi.en/test-* - split: validation path: MLQA.vi.en/validation-* - config_name: MLQA.vi.es data_files: - split: test path: MLQA.vi.es/test-* - split: validation path: MLQA.vi.es/validation-* - config_name: MLQA.vi.hi data_files: - split: test path: MLQA.vi.hi/test-* - split: validation path: MLQA.vi.hi/validation-* - config_name: MLQA.vi.vi data_files: - split: test path: MLQA.vi.vi/test-* - split: validation path: MLQA.vi.vi/validation-* - config_name: MLQA.vi.zh data_files: - split: test path: MLQA.vi.zh/test-* - split: validation path: MLQA.vi.zh/validation-* - config_name: MLQA.zh.ar data_files: - split: test path: MLQA.zh.ar/test-* - split: validation path: MLQA.zh.ar/validation-* - config_name: MLQA.zh.de data_files: - split: test path: MLQA.zh.de/test-* - split: validation path: MLQA.zh.de/validation-* - config_name: MLQA.zh.en data_files: - split: test path: MLQA.zh.en/test-* - split: validation path: MLQA.zh.en/validation-* - config_name: MLQA.zh.es data_files: - split: test path: MLQA.zh.es/test-* - split: validation path: MLQA.zh.es/validation-* - config_name: MLQA.zh.hi data_files: - split: test path: MLQA.zh.hi/test-* - split: validation path: MLQA.zh.hi/validation-* - config_name: MLQA.zh.vi data_files: - split: test path: MLQA.zh.vi/test-* - split: validation path: MLQA.zh.vi/validation-* - config_name: MLQA.zh.zh data_files: - split: test path: MLQA.zh.zh/test-* - split: validation path: MLQA.zh.zh/validation-* - config_name: PAN-X.af data_files: - split: train path: PAN-X.af/train-* - split: validation path: PAN-X.af/validation-* - split: test path: PAN-X.af/test-* - config_name: PAN-X.ar data_files: - split: train path: PAN-X.ar/train-* - split: validation path: PAN-X.ar/validation-* - split: test path: PAN-X.ar/test-* - config_name: PAN-X.bg data_files: - split: train path: PAN-X.bg/train-* - split: validation path: PAN-X.bg/validation-* - split: test path: PAN-X.bg/test-* - config_name: PAN-X.bn data_files: - split: train path: PAN-X.bn/train-* - split: validation path: PAN-X.bn/validation-* - split: test path: PAN-X.bn/test-* - config_name: PAN-X.de data_files: - split: train path: PAN-X.de/train-* - split: validation path: PAN-X.de/validation-* - split: test path: PAN-X.de/test-* - config_name: PAN-X.el data_files: - split: train path: PAN-X.el/train-* - split: validation path: PAN-X.el/validation-* - split: test path: PAN-X.el/test-* - config_name: PAN-X.en data_files: - split: train path: PAN-X.en/train-* - split: validation path: PAN-X.en/validation-* - split: test path: PAN-X.en/test-* - config_name: PAN-X.es data_files: - split: train path: PAN-X.es/train-* - split: validation path: PAN-X.es/validation-* - split: test path: PAN-X.es/test-* - config_name: PAN-X.et data_files: - split: train path: PAN-X.et/train-* - split: validation path: PAN-X.et/validation-* - split: test path: PAN-X.et/test-* - config_name: PAN-X.eu data_files: - split: train path: PAN-X.eu/train-* - split: validation path: PAN-X.eu/validation-* - split: test path: PAN-X.eu/test-* - config_name: PAN-X.fa data_files: - split: train path: PAN-X.fa/train-* - split: validation path: PAN-X.fa/validation-* - split: test path: PAN-X.fa/test-* - config_name: PAN-X.fi data_files: - split: train path: PAN-X.fi/train-* - split: validation path: PAN-X.fi/validation-* - split: test path: PAN-X.fi/test-* - config_name: PAN-X.fr data_files: - split: train path: PAN-X.fr/train-* - split: validation path: PAN-X.fr/validation-* - split: test path: PAN-X.fr/test-* - config_name: PAN-X.he data_files: - split: train path: PAN-X.he/train-* - split: validation path: PAN-X.he/validation-* - split: test path: PAN-X.he/test-* - config_name: PAN-X.hi data_files: - split: train path: PAN-X.hi/train-* - split: validation path: PAN-X.hi/validation-* - split: test path: PAN-X.hi/test-* - config_name: PAN-X.hu data_files: - split: train path: PAN-X.hu/train-* - split: validation path: PAN-X.hu/validation-* - split: test path: PAN-X.hu/test-* - config_name: PAN-X.id data_files: - split: train path: PAN-X.id/train-* - split: validation path: PAN-X.id/validation-* - split: test path: PAN-X.id/test-* - config_name: PAN-X.it data_files: - split: train path: PAN-X.it/train-* - split: validation path: PAN-X.it/validation-* - split: test path: PAN-X.it/test-* - config_name: PAN-X.ja data_files: - split: train path: PAN-X.ja/train-* - split: validation path: PAN-X.ja/validation-* - split: test path: PAN-X.ja/test-* - config_name: PAN-X.jv data_files: - split: train path: PAN-X.jv/train-* - split: validation path: PAN-X.jv/validation-* - split: test path: PAN-X.jv/test-* - config_name: PAN-X.ka data_files: - split: train path: PAN-X.ka/train-* - split: validation path: PAN-X.ka/validation-* - split: test path: PAN-X.ka/test-* - config_name: PAN-X.kk data_files: - split: train path: PAN-X.kk/train-* - split: validation path: PAN-X.kk/validation-* - split: test path: PAN-X.kk/test-* - config_name: PAN-X.ko data_files: - split: train path: PAN-X.ko/train-* - split: validation path: PAN-X.ko/validation-* - split: test path: PAN-X.ko/test-* - config_name: PAN-X.ml data_files: - split: train path: PAN-X.ml/train-* - split: validation path: PAN-X.ml/validation-* - split: test path: PAN-X.ml/test-* - config_name: PAN-X.mr data_files: - split: train path: PAN-X.mr/train-* - split: validation path: PAN-X.mr/validation-* - split: test path: PAN-X.mr/test-* - config_name: PAN-X.ms data_files: - split: train path: PAN-X.ms/train-* - split: validation path: PAN-X.ms/validation-* - split: test path: PAN-X.ms/test-* - config_name: PAN-X.my data_files: - split: train path: PAN-X.my/train-* - split: validation path: PAN-X.my/validation-* - split: test path: PAN-X.my/test-* - config_name: PAN-X.nl data_files: - split: train path: PAN-X.nl/train-* - split: validation path: PAN-X.nl/validation-* - split: test path: PAN-X.nl/test-* - config_name: PAN-X.pt data_files: - split: train path: PAN-X.pt/train-* - split: validation path: PAN-X.pt/validation-* - split: test path: PAN-X.pt/test-* - config_name: PAN-X.ru data_files: - split: train path: PAN-X.ru/train-* - split: validation path: PAN-X.ru/validation-* - split: test path: PAN-X.ru/test-* - config_name: PAN-X.sw data_files: - split: train path: PAN-X.sw/train-* - split: validation path: PAN-X.sw/validation-* - split: test path: PAN-X.sw/test-* - config_name: PAN-X.ta data_files: - split: train path: PAN-X.ta/train-* - split: validation path: PAN-X.ta/validation-* - split: test path: PAN-X.ta/test-* - config_name: PAN-X.te data_files: - split: train path: PAN-X.te/train-* - split: validation path: PAN-X.te/validation-* - split: test path: PAN-X.te/test-* - config_name: PAN-X.th data_files: - split: train path: PAN-X.th/train-* - split: validation path: PAN-X.th/validation-* - split: test path: PAN-X.th/test-* - config_name: PAN-X.tl data_files: - split: train path: PAN-X.tl/train-* - split: validation path: PAN-X.tl/validation-* - split: test path: PAN-X.tl/test-* - config_name: PAN-X.tr data_files: - split: train path: PAN-X.tr/train-* - split: validation path: PAN-X.tr/validation-* - split: test path: PAN-X.tr/test-* - config_name: PAN-X.ur data_files: - split: train path: PAN-X.ur/train-* - split: validation path: PAN-X.ur/validation-* - split: test path: PAN-X.ur/test-* - config_name: PAN-X.vi data_files: - split: train path: PAN-X.vi/train-* - split: validation path: PAN-X.vi/validation-* - split: test path: PAN-X.vi/test-* - config_name: PAN-X.yo data_files: - split: train path: PAN-X.yo/train-* - split: validation path: PAN-X.yo/validation-* - split: test path: PAN-X.yo/test-* - config_name: PAN-X.zh data_files: - split: train path: PAN-X.zh/train-* - split: validation path: PAN-X.zh/validation-* - split: test path: PAN-X.zh/test-* - config_name: PAWS-X.de data_files: - split: train path: PAWS-X.de/train-* - split: validation path: PAWS-X.de/validation-* - split: test path: PAWS-X.de/test-* - config_name: PAWS-X.en data_files: - split: train path: PAWS-X.en/train-* - split: validation path: PAWS-X.en/validation-* - split: test path: PAWS-X.en/test-* - config_name: PAWS-X.es data_files: - split: train path: PAWS-X.es/train-* - split: validation path: PAWS-X.es/validation-* - split: test path: PAWS-X.es/test-* - config_name: PAWS-X.fr data_files: - split: train path: PAWS-X.fr/train-* - split: validation path: PAWS-X.fr/validation-* - split: test path: PAWS-X.fr/test-* - config_name: PAWS-X.ja data_files: - split: train path: PAWS-X.ja/train-* - split: validation path: PAWS-X.ja/validation-* - split: test path: PAWS-X.ja/test-* - config_name: PAWS-X.ko data_files: - split: train path: PAWS-X.ko/train-* - split: validation path: PAWS-X.ko/validation-* - split: test path: PAWS-X.ko/test-* - config_name: PAWS-X.zh data_files: - split: train path: PAWS-X.zh/train-* - split: validation path: PAWS-X.zh/validation-* - split: test path: PAWS-X.zh/test-* - config_name: SQuAD data_files: - split: train path: SQuAD/train-* - split: validation path: SQuAD/validation-* - config_name: XNLI data_files: - split: test path: XNLI/test-* - split: validation path: XNLI/validation-* - config_name: XQuAD.ar data_files: - split: validation path: XQuAD.ar/validation-* - config_name: XQuAD.de data_files: - split: validation path: XQuAD.de/validation-* - config_name: XQuAD.el data_files: - split: validation path: XQuAD.el/validation-* - config_name: XQuAD.en data_files: - split: validation path: XQuAD.en/validation-* - config_name: XQuAD.es data_files: - split: validation path: XQuAD.es/validation-* - config_name: XQuAD.hi data_files: - split: validation path: XQuAD.hi/validation-* - config_name: XQuAD.ru data_files: - split: validation path: XQuAD.ru/validation-* - config_name: XQuAD.th data_files: - split: validation path: XQuAD.th/validation-* - config_name: XQuAD.tr data_files: - split: validation path: XQuAD.tr/validation-* - config_name: XQuAD.vi data_files: - split: validation path: XQuAD.vi/validation-* - config_name: XQuAD.zh data_files: - split: validation path: XQuAD.zh/validation-* - config_name: bucc18.de data_files: - split: validation path: bucc18.de/validation-* - split: test path: bucc18.de/test-* - config_name: bucc18.fr data_files: - split: validation path: bucc18.fr/validation-* - split: test path: bucc18.fr/test-* - config_name: bucc18.ru data_files: - split: validation path: bucc18.ru/validation-* - split: test path: bucc18.ru/test-* - config_name: bucc18.zh data_files: - split: validation path: bucc18.zh/validation-* - split: test path: bucc18.zh/test-* - config_name: tatoeba.afr data_files: - split: validation path: tatoeba.afr/validation-* - config_name: tatoeba.ara data_files: - split: validation path: tatoeba.ara/validation-* - config_name: tatoeba.ben data_files: - split: validation path: tatoeba.ben/validation-* - config_name: tatoeba.bul data_files: - split: validation path: tatoeba.bul/validation-* - config_name: tatoeba.cmn data_files: - split: validation path: tatoeba.cmn/validation-* - config_name: tatoeba.deu data_files: - split: validation path: tatoeba.deu/validation-* - config_name: tatoeba.ell data_files: - split: validation path: tatoeba.ell/validation-* - config_name: tatoeba.est data_files: - split: validation path: tatoeba.est/validation-* - config_name: tatoeba.eus data_files: - split: validation path: tatoeba.eus/validation-* - config_name: tatoeba.fin data_files: - split: validation path: tatoeba.fin/validation-* - config_name: tatoeba.fra data_files: - split: validation path: tatoeba.fra/validation-* - config_name: tatoeba.heb data_files: - split: validation path: tatoeba.heb/validation-* - config_name: tatoeba.hin data_files: - split: validation path: tatoeba.hin/validation-* - config_name: tatoeba.hun data_files: - split: validation path: tatoeba.hun/validation-* - config_name: tatoeba.ind data_files: - split: validation path: tatoeba.ind/validation-* - config_name: tatoeba.ita data_files: - split: validation path: tatoeba.ita/validation-* - config_name: tatoeba.jav data_files: - split: validation path: tatoeba.jav/validation-* - config_name: tatoeba.jpn data_files: - split: validation path: tatoeba.jpn/validation-* - config_name: tatoeba.kat data_files: - split: validation path: tatoeba.kat/validation-* - config_name: tatoeba.kaz data_files: - split: validation path: tatoeba.kaz/validation-* - config_name: tatoeba.kor data_files: - split: validation path: tatoeba.kor/validation-* - config_name: tatoeba.mal data_files: - split: validation path: tatoeba.mal/validation-* - config_name: tatoeba.mar data_files: - split: validation path: tatoeba.mar/validation-* - config_name: tatoeba.nld data_files: - split: validation path: tatoeba.nld/validation-* - config_name: tatoeba.pes data_files: - split: validation path: tatoeba.pes/validation-* - config_name: tatoeba.por data_files: - split: validation path: tatoeba.por/validation-* - config_name: tatoeba.rus data_files: - split: validation path: tatoeba.rus/validation-* - config_name: tatoeba.spa data_files: - split: validation path: tatoeba.spa/validation-* - config_name: tatoeba.swh data_files: - split: validation path: tatoeba.swh/validation-* - config_name: tatoeba.tam data_files: - split: validation path: tatoeba.tam/validation-* - config_name: tatoeba.tel data_files: - split: validation path: tatoeba.tel/validation-* - config_name: tatoeba.tgl data_files: - split: validation path: tatoeba.tgl/validation-* - config_name: tatoeba.tha data_files: - split: validation path: tatoeba.tha/validation-* - config_name: tatoeba.tur data_files: - split: validation path: tatoeba.tur/validation-* - config_name: tatoeba.urd data_files: - split: validation path: tatoeba.urd/validation-* - config_name: tatoeba.vie data_files: - split: validation path: tatoeba.vie/validation-* - config_name: tydiqa data_files: - split: train path: tydiqa/train-* - split: validation path: tydiqa/validation-* - config_name: udpos.Afrikaans data_files: - split: train path: udpos.Afrikaans/train-* - split: validation path: udpos.Afrikaans/validation-* - split: test path: udpos.Afrikaans/test-* - config_name: udpos.Arabic data_files: - split: train path: udpos.Arabic/train-* - split: validation path: udpos.Arabic/validation-* - split: test path: udpos.Arabic/test-* - config_name: udpos.Basque data_files: - split: train path: udpos.Basque/train-* - split: validation path: udpos.Basque/validation-* - split: test path: udpos.Basque/test-* - config_name: udpos.Bulgarian data_files: - split: train path: udpos.Bulgarian/train-* - split: validation path: udpos.Bulgarian/validation-* - split: test path: udpos.Bulgarian/test-* - config_name: udpos.Chinese data_files: - split: train path: udpos.Chinese/train-* - split: validation path: udpos.Chinese/validation-* - split: test path: udpos.Chinese/test-* - config_name: udpos.Dutch data_files: - split: train path: udpos.Dutch/train-* - split: validation path: udpos.Dutch/validation-* - split: test path: udpos.Dutch/test-* - config_name: udpos.English data_files: - split: train path: udpos.English/train-* - split: validation path: udpos.English/validation-* - split: test path: udpos.English/test-* - config_name: udpos.Estonian data_files: - split: train path: udpos.Estonian/train-* - split: validation path: udpos.Estonian/validation-* - split: test path: udpos.Estonian/test-* - config_name: udpos.Finnish data_files: - split: train path: udpos.Finnish/train-* - split: validation path: udpos.Finnish/validation-* - split: test path: udpos.Finnish/test-* - config_name: udpos.French data_files: - split: train path: udpos.French/train-* - split: validation path: udpos.French/validation-* - split: test path: udpos.French/test-* - config_name: udpos.German data_files: - split: train path: udpos.German/train-* - split: validation path: udpos.German/validation-* - split: test path: udpos.German/test-* - config_name: udpos.Greek data_files: - split: train path: udpos.Greek/train-* - split: validation path: udpos.Greek/validation-* - split: test path: udpos.Greek/test-* - config_name: udpos.Hebrew data_files: - split: train path: udpos.Hebrew/train-* - split: validation path: udpos.Hebrew/validation-* - split: test path: udpos.Hebrew/test-* - config_name: udpos.Hindi data_files: - split: train path: udpos.Hindi/train-* - split: validation path: udpos.Hindi/validation-* - split: test path: udpos.Hindi/test-* - config_name: udpos.Hungarian data_files: - split: train path: udpos.Hungarian/train-* - split: validation path: udpos.Hungarian/validation-* - split: test path: udpos.Hungarian/test-* - config_name: udpos.Indonesian data_files: - split: train path: udpos.Indonesian/train-* - split: validation path: udpos.Indonesian/validation-* - split: test path: udpos.Indonesian/test-* - config_name: udpos.Italian data_files: - split: train path: udpos.Italian/train-* - split: validation path: udpos.Italian/validation-* - split: test path: udpos.Italian/test-* - config_name: udpos.Japanese data_files: - split: train path: udpos.Japanese/train-* - split: validation path: udpos.Japanese/validation-* - split: test path: udpos.Japanese/test-* - config_name: udpos.Kazakh data_files: - split: train path: udpos.Kazakh/train-* - split: test path: udpos.Kazakh/test-* - config_name: udpos.Korean data_files: - split: train path: udpos.Korean/train-* - split: validation path: udpos.Korean/validation-* - split: test path: udpos.Korean/test-* - config_name: udpos.Marathi data_files: - split: train path: udpos.Marathi/train-* - split: validation path: udpos.Marathi/validation-* - split: test path: udpos.Marathi/test-* - config_name: udpos.Persian data_files: - split: train path: udpos.Persian/train-* - split: validation path: udpos.Persian/validation-* - split: test path: udpos.Persian/test-* - config_name: udpos.Portuguese data_files: - split: train path: udpos.Portuguese/train-* - split: validation path: udpos.Portuguese/validation-* - split: test path: udpos.Portuguese/test-* - config_name: udpos.Russian data_files: - split: train path: udpos.Russian/train-* - split: validation path: udpos.Russian/validation-* - split: test path: udpos.Russian/test-* - config_name: udpos.Spanish data_files: - split: train path: udpos.Spanish/train-* - split: validation path: udpos.Spanish/validation-* - split: test path: udpos.Spanish/test-* - config_name: udpos.Tagalog data_files: - split: test path: udpos.Tagalog/test-* - config_name: udpos.Tamil data_files: - split: train path: udpos.Tamil/train-* - split: validation path: udpos.Tamil/validation-* - split: test path: udpos.Tamil/test-* - config_name: udpos.Telugu data_files: - split: train path: udpos.Telugu/train-* - split: validation path: udpos.Telugu/validation-* - split: test path: udpos.Telugu/test-* - config_name: udpos.Thai data_files: - split: test path: udpos.Thai/test-* - config_name: udpos.Turkish data_files: - split: train path: udpos.Turkish/train-* - split: validation path: udpos.Turkish/validation-* - split: test path: udpos.Turkish/test-* - config_name: udpos.Urdu data_files: - split: train path: udpos.Urdu/train-* - split: validation path: udpos.Urdu/validation-* - split: test path: udpos.Urdu/test-* - config_name: udpos.Vietnamese data_files: - split: train path: udpos.Vietnamese/train-* - split: validation path: udpos.Vietnamese/validation-* - split: test path: udpos.Vietnamese/test-* - config_name: udpos.Yoruba data_files: - split: test path: udpos.Yoruba/test-* --- # Dataset Card for "xtreme" ## Table of Contents - [Dataset Description](#dataset-description) - [Dataset Summary](#dataset-summary) - [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards) - [Languages](#languages) - [Dataset Structure](#dataset-structure) - [Data Instances](#data-instances) - [Data Fields](#data-fields) - [Data Splits](#data-splits) - [Dataset Creation](#dataset-creation) - [Curation Rationale](#curation-rationale) - [Source Data](#source-data) - [Annotations](#annotations) - [Personal and Sensitive Information](#personal-and-sensitive-information) - [Considerations for Using the Data](#considerations-for-using-the-data) - [Social Impact of Dataset](#social-impact-of-dataset) - [Discussion of Biases](#discussion-of-biases) - [Other Known Limitations](#other-known-limitations) - [Additional Information](#additional-information) - [Dataset Curators](#dataset-curators) - [Licensing Information](#licensing-information) - [Citation Information](#citation-information) - [Contributions](#contributions) ## Dataset Description - **Homepage:** [https://github.com/google-research/xtreme](https://github.com/google-research/xtreme) - **Repository:** [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) - **Paper:** [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) - **Point of Contact:** [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) - **Size of downloaded dataset files:** 15.88 GB - **Size of the generated dataset:** 1.08 GB - **Total amount of disk used:** 16.96 GB ### Dataset Summary The Cross-lingual Natural Language Inference (XNLI) corpus is a crowd-sourced collection of 5,000 test and 2,500 dev pairs for the MultiNLI corpus. The pairs are annotated with textual entailment and translated into 14 languages: French, Spanish, German, Greek, Bulgarian, Russian, Turkish, Arabic, Vietnamese, Thai, Chinese, Hindi, Swahili and Urdu. This results in 112.5k annotated pairs. Each premise can be associated with the corresponding hypothesis in the 15 languages, summing up to more than 1.5M combinations. The corpus is made to evaluate how to perform inference in any language (including low-resources ones like Swahili or Urdu) when only English NLI data is available at training time. One solution is cross-lingual sentence encoding, for which XNLI is an evaluation benchmark. The Cross-lingual TRansfer Evaluation of Multilingual Encoders (XTREME) benchmark is a benchmark for the evaluation of the cross-lingual generalization ability of pre-trained multilingual models. It covers 40 typologically diverse languages (spanning 12 language families) and includes nine tasks that collectively require reasoning about different levels of syntax and semantics. The languages in XTREME are selected to maximize language diversity, coverage in existing tasks, and availability of training data. Among these are many under-studied languages, such as the Dravidian languages Tamil (spoken in southern India, Sri Lanka, and Singapore), Telugu and Malayalam (spoken mainly in southern India), and the Niger-Congo languages Swahili and Yoruba, spoken in Africa. ### Supported Tasks and Leaderboards [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Languages [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ## Dataset Structure ### Data Instances #### MLQA.ar.ar - **Size of downloaded dataset files:** 75.72 MB - **Size of the generated dataset:** 9.20 MB - **Total amount of disk used:** 84.91 MB An example of 'validation' looks as follows. ``` ``` #### MLQA.ar.de - **Size of downloaded dataset files:** 75.72 MB - **Size of the generated dataset:** 2.55 MB - **Total amount of disk used:** 78.27 MB An example of 'validation' looks as follows. ``` ``` #### MLQA.ar.en - **Size of downloaded dataset files:** 75.72 MB - **Size of the generated dataset:** 9.04 MB - **Total amount of disk used:** 84.76 MB An example of 'validation' looks as follows. ``` ``` #### MLQA.ar.es - **Size of downloaded dataset files:** 75.72 MB - **Size of the generated dataset:** 3.27 MB - **Total amount of disk used:** 78.99 MB An example of 'validation' looks as follows. ``` ``` #### MLQA.ar.hi - **Size of downloaded dataset files:** 75.72 MB - **Size of the generated dataset:** 3.32 MB - **Total amount of disk used:** 79.04 MB An example of 'validation' looks as follows. ``` ``` ### Data Fields The data fields are the same among all splits. #### MLQA.ar.ar - `id`: a `string` feature. - `title`: a `string` feature. - `context`: a `string` feature. - `question`: a `string` feature. - `answers`: a dictionary feature containing: - `answer_start`: a `int32` feature. - `text`: a `string` feature. #### MLQA.ar.de - `id`: a `string` feature. - `title`: a `string` feature. - `context`: a `string` feature. - `question`: a `string` feature. - `answers`: a dictionary feature containing: - `answer_start`: a `int32` feature. - `text`: a `string` feature. #### MLQA.ar.en - `id`: a `string` feature. - `title`: a `string` feature. - `context`: a `string` feature. - `question`: a `string` feature. - `answers`: a dictionary feature containing: - `answer_start`: a `int32` feature. - `text`: a `string` feature. #### MLQA.ar.es - `id`: a `string` feature. - `title`: a `string` feature. - `context`: a `string` feature. - `question`: a `string` feature. - `answers`: a dictionary feature containing: - `answer_start`: a `int32` feature. - `text`: a `string` feature. #### MLQA.ar.hi - `id`: a `string` feature. - `title`: a `string` feature. - `context`: a `string` feature. - `question`: a `string` feature. - `answers`: a dictionary feature containing: - `answer_start`: a `int32` feature. - `text`: a `string` feature. ### Data Splits | name |validation|test| |----------|---------:|---:| |MLQA.ar.ar| 517|5335| |MLQA.ar.de| 207|1649| |MLQA.ar.en| 517|5335| |MLQA.ar.es| 161|1978| |MLQA.ar.hi| 186|1831| ## Dataset Creation ### Curation Rationale [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Source Data #### Initial Data Collection and Normalization [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) #### Who are the source language producers? [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Annotations #### Annotation process [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) #### Who are the annotators? [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Personal and Sensitive Information [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ## Considerations for Using the Data ### Social Impact of Dataset [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Discussion of Biases [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Other Known Limitations [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ## Additional Information ### Dataset Curators [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Licensing Information [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Citation Information ``` @InProceedings{conneau2018xnli, author = {Conneau, Alexis and Rinott, Ruty and Lample, Guillaume and Williams, Adina and Bowman, Samuel R. and Schwenk, Holger and Stoyanov, Veselin}, title = {XNLI: Evaluating Cross-lingual Sentence Representations}, booktitle = {Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing}, year = {2018}, publisher = {Association for Computational Linguistics}, location = {Brussels, Belgium}, } @article{hu2020xtreme, author = {Junjie Hu and Sebastian Ruder and Aditya Siddhant and Graham Neubig and Orhan Firat and Melvin Johnson}, title = {XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalization}, journal = {CoRR}, volume = {abs/2003.11080}, year = {2020}, archivePrefix = {arXiv}, eprint = {2003.11080} } ``` ### Contributions Thanks to [@thomwolf](https://github.com/thomwolf), [@jplu](https://github.com/jplu), [@lewtun](https://github.com/lewtun), [@lvwerra](https://github.com/lvwerra), [@lhoestq](https://github.com/lhoestq), [@patrickvonplaten](https://github.com/patrickvonplaten), [@mariamabarham](https://github.com/mariamabarham) for adding this dataset.

lmms-lab/DocVQA

lmms-lab

--- license: apache-2.0 dataset_info: - config_name: DocVQA features: - name: questionId dtype: string - name: question dtype: string - name: question_types sequence: string - name: image dtype: image - name: docId dtype: int64 - name: ucsf_document_id dtype: string - name: ucsf_document_page_no dtype: string - name: answers sequence: string - name: data_split dtype: string splits: # - name: train # num_bytes: 5659006943.631 # num_examples: 39463 - name: validation num_bytes: 2532447207.066 num_examples: 5349 - name: test num_bytes: 2500408525.732 num_examples: 5188 download_size: 9555791945 dataset_size: 10691862676.428999 - config_name: InfographicVQA features: - name: questionId dtype: string - name: question dtype: string - name: answers sequence: string - name: answer_type sequence: string - name: image dtype: image - name: image_url dtype: string - name: operation/reasoning sequence: string - name: ocr dtype: string - name: data_split dtype: string splits: # - name: train # num_bytes: 11559694546.32 # num_examples: 23946 - name: validation num_bytes: 1863177404.253 num_examples: 2801 - name: test num_bytes: 1851304047.712 num_examples: 3288 download_size: 2544892079 dataset_size: 15274175998.285 configs: - config_name: DocVQA data_files: # - split: train # path: DocVQA/train-* - split: validation path: DocVQA/validation-* - split: test path: DocVQA/test-* - config_name: InfographicVQA data_files: # - split: train # path: InfographicVQA/train-* - split: validation path: InfographicVQA/validation-* - split: test path: InfographicVQA/test-* --- <p align="center" width="100%"> <img src="https://i.postimg.cc/g0QRgMVv/WX20240228-113337-2x.png" width="100%" height="80%"> </p> # Large-scale Multi-modality Models Evaluation Suite > Accelerating the development of large-scale multi-modality models (LMMs) with `lmms-eval` 🏠 [Homepage](https://lmms-lab.github.io/) | 📚 [Documentation](docs/README.md) | 🤗 [Huggingface Datasets](https://huggingface.co./lmms-lab) # This Dataset This is a formatted version of [DocVQA](https://arxiv.org/abs/2007.00398). It is used in our `lmms-eval` pipeline to allow for one-click evaluations of large multi-modality models. ``` @article{mathew2020docvqa, title={DocVQA: A Dataset for VQA on Document Images. CoRR abs/2007.00398 (2020)}, author={Mathew, Minesh and Karatzas, Dimosthenis and Manmatha, R and Jawahar, CV}, journal={arXiv preprint arXiv:2007.00398}, year={2020} } ```

SadilKhan/Text2CAD

SadilKhan

--- language: - en license: cc-by-nc-sa-4.0 pipeline_tag: text-to-3D tags: - text-to-cad - dataset - annotation extra_gated_heading: Acknowledge license to accept the repository extra_gated_prompt: "### Text2CAD Community License Agreement\n\n [](https://creativecommons.org/licenses/by-nc-sa/4.0/)\n\ \ \n This named Dataset, **Text2CAD.v1**, was developed by [Deutsche Forschungszentrum\ \ für Kuntlische Inlligenz (DFKI GmbH)] (Germany).\ \ It is licensed under the Creative Commons Attribution-NonCommercial-ShareAlike\ \ 4.0 International License.\n \n ## Attribution-NonCommercial-ShareAlike 4.0 International\ \ (CC BY-NC-SA 4.0)\n You are free to:\n - **Share**: copy and redistribute the\ \ material in any medium or format.\n - **Adapt**: remix, transform, and build upon\ \ the material.\n \n\n Under the following terms:\n - **Attribution**: You must\ \ give appropriate credit, provide a link to the license, and indicate if changes\ \ were made. You may do so in any reasonable manner, but not in any way that suggests\ \ the licensor endorses you or your use.\n - **NonCommercial**: You may not use\ \ the material for commercial purposes.\n - **ShareAlike**: If you remix, transform,\ \ or build upon the material, you must distribute your contributions under the same\ \ license as the original.\n \n \n \n To view a copy of this license, visit [https://creativecommons.org/licenses/by-nc-sa/4.0/](https://creativecommons.org/licenses/by-nc-sa/4.0/).\n\ \ \n If you use this dataset in your work, please cite the following publication:\n\ \ \n Mohammad Sadil Khan*, Sankalp Sinha*, Talha Uddin Sheikh, Didier Stricker,\ \ Sk Aziz Ali, Muhammad Zeshan Afzal. \"Text2CAD: Generating Sequential CAD Designs\ \ from Beginner-to-Expert Level Text Prompts.\" In The Thirty-eighth Annual Conference\ \ on Neural Information Processing Systems (2024).\n \n \n \n For inquiries or additional\ \ information, contact:\n \n \n \n - [DFKI GmbH  Contact Information]\n \n Deutsches\ \ Forschungszentrum Fur Kunstliche Intelligenz GmbH\n Trippstadter Str. 122\n\ \ 67663 Kaiserslautern\n Germany\n Phone: +49 631 20575 0\n link: https://www.dfki.de/web\n\ " extra_gated_fields: First Name: text Last Name: text Country: country Affiliation: text I want to use this dataset for: type: select options: - Research - Education - label: Other value: other I agree to use this dataset for non-commercial use ONLY: checkbox --- <div align="center"> <p style="font-size:40px;"> 🚀 Text2CAD: Generating Sequential CAD Designs from Beginner-to-Expert Level Text Prompts 🎨 </p> [Mohammad Sadil Khan*](https://scholar.google.com/citations?user=XIDQo_IAAAAJ&hl=en&authuser=1) · [Sankalp Sinha*](https://scholar.google.com/citations?user=QYcfOjEAAAAJ&hl=en&authuser=1&oi=ao) · [Talha Uddin Sheikh](https://scholar.google.com/citations?hl=en&authuser=1&user=yW7VfAgAAAAJ) · [Didier Stricker](https://scholar.google.com/citations?hl=en&authuser=1&user=ImhXfxgAAAAJ) · [Sk Aziz Ali](https://scholar.google.com/citations?hl=en&authuser=1&user=zywjMeMAAAAJ) · [Muhammad Zeshan Afzal](https://scholar.google.com/citations?user=kHMVj6oAAAAJ&hl=en&authuser=1&oi=ao) _*equal contributions_ <div style="display: flex; justify-content: center; gap: 10px;"> <a href="https://arxiv.org/abs/2409.17106"> <img src="https://img.shields.io/badge/Arxiv-3498db?style=for-the-badge&logoWidth=40&logoColor=white" alt="Paper" /> </a> <a href="https://sadilkhan.github.io/text2cad-project/"> <img src="https://img.shields.io/badge/Project-2ecc71?style=for-the-badge&logoWidth=40&logoColor=white" alt="Project" /> </a> <a href="https://github.com/SadilKhan/Text2CAD"> <img src="https://img.shields.io/badge/Code-89AAE6?style=for-the-badge&logoWidth=40&logoColor=white" alt="Code" /> </a> </div> <p style="font-size:35px;"> NeurIPS 2024 </p> </div> <div align="left"> <p style="font-size:30px;"> 📊 Dataset Versions </p> </div> We are releasing the following versions of the Text2CAD dataset. <table><thead> <tr> <th>Dataset</th> <th>🤖 VLM</th> <th>🤖 LLM</th> <th>📝 Remarks</th> </tr></thead> <tbody> <tr> <td><b>Text2CAD 1.0</b></td> <td><code>LLaVA-NeXT</code></td> <td><code>Mistral-7x8B-Instruct</code></td> <td>The original dataset used in NeurIPS Paper</td> </tr> <tr> <td><b>Text2CAD 1.1</b></td> <td><code>Qwen2-VL 14B</code></td> <td><code>Qwen2.5-72B-Instruct (8bit)</code></td> <td> Updated dataset with latest VLM and LLM.</td> </tr> </tbody> </table> <div align="left"> <p style="font-size:30px;"> ✅ Tasks </p> </div> - [x] Extra Data (Minimal Json, CAD Sequence, RGB, Depth) Release - [x] Code Release - [x] Text2CAD v1.1 Release - [x] Text2CAD v1.0 Release <div align="left"> <p style="font-size:30px;"> 🗂️ Folder Description </p> </div> _Warning: Full Storage 555GB_. `cad_seq.zip` `(579MB)` - CAD Vector Representation <details><summary> Text2CAD v1.1</summary> <p> - 📌 `text2cad_v1.1.csv` (`1.3GB`) - `uid`: Identifier (Same as DeepCAD). - `abstract`: Abstract Level Annotation (Level 0). - `beginner`: Beginner Level Annotation (Level 1). - `intermediate`: Intermediate Level Annotation (Level 2). - `expert`: Expert Level Annotation (Level 3). - `description` (_New_): Description of the CAD Model generated by VLM. - `keywords` (_New_): List of Keywords generated by VLM. - `all_level_data`: All the level annotations generated by LLM before spliting. - `nli_data`: The intermediate NLI response. - 📌 `misc/` - `minimal_json/` (`246MB`): Simplified JSON generated from DeepCAD original JSON. Random UIDs, redundant information is removed. _This json can be used by an LLM to generate more captions_. - `rgb_images/` (`397GB`): RGB images of the final CAD Model as well as the intermediate ones using Blender. It contains 10 images (8 side views in circular trajectory, bottom and top) and their respective camera parameters for each model. (_Note: The camera matrices follow Blender coordinate system_. Use [this](https://github.com/facebookresearch/pytorch3d/issues/1105#issuecomment-1784095670) to convert them to pytorch3D coordinate system.) - 📌 `train_test_val.json`: Train,Test and Validation UIDs. It contains filtered training samples with `5%` cuboid and cylindrical models (Original json has ~ `25%` cuboid and ~ `8%` cylindtrical samples in the training dataset). </p> </details> <br> <details><summary> Text2CAD v1.0</summary> <p> - 📌 `text2cad_v1.0.csv` `(1.1GB)` - `uid`: Identifier (Same as DeepCAD). - `abstract`: Abstract Level Annotation (Level 0). - `beginner`: Beginner Level Annotation (Level 1). - `intermediate`: Intermediate Level Annotation (Level 2). - `expert`: Expert Level Annotation (Level 3). - `all_level_data`: All the level annotations generated by LLM before spliting. - `nli_data`: The intermediate NLI response. - 📌 `misc/` - `minimal_json/` (`110MB`): Simplified JSON generated from DeepCAD original JSON. Random UIDs, redundant information is removed. _This json is used in our NeurIPS paper_. - `rgb_images/` (`48GB`): Random 9 multi-view rgb images of the CAD model and their intermediate models using `Open3D`. - `depth_images/` (`37GB`): Depth images of the corresponding rgb images using `Open3D`. - 📌 `train_test_val.json`: Original train,test and validation json. - 📌 `Text2CAD_1.0.pth`: Text2CAD Transformer model weights (Used in our paper). </p> </details> <div align="left"> <p style="font-size:30px;"> 📜 Citation</p> </div> If you use this dataset in your work, please cite the following publications. ``` @inproceedings{khan2024textcad, title={Text2CAD: Generating Sequential CAD Designs from Beginner-to-Expert Level Text Prompts}, author={Mohammad Sadil Khan and Sankalp Sinha and Sheikh Talha Uddin and Didier Stricker and Sk Aziz Ali and Muhammad Zeshan Afzal}, booktitle={The Thirty-eighth Annual Conference on Neural Information Processing Systems}, year={2024}, url={https://openreview.net/forum?id=5k9XeHIK3L} } @InProceedings{Khan_2024_CVPR, author = {Khan, Mohammad Sadil and Dupont, Elona and Ali, Sk Aziz and Cherenkova, Kseniya and Kacem, Anis and Aouada, Djamila}, title = {CAD-SIGNet: CAD Language Inference from Point Clouds using Layer-wise Sketch Instance Guided Attention}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {4713-4722} } ```

bigcode/the-stack-v2

bigcode

--- annotations_creators: [] language_creators: - crowdsourced - expert-generated language: - code license: - other multilinguality: - multilingual pretty_name: The-Stack-v2 size_categories: - unknown source_datasets: [] task_categories: - text-generation task_ids: [] extra_gated_prompt: |- ## Terms of Use for The Stack v2 The Stack v2 dataset is a collection of source code in over 600 programming languages. We ask that you read and acknowledge the following points before using the dataset: 1. Downloading the dataset in bulk requires a an agreement with SoftwareHeritage and INRIA. Contact [[email protected]](mailto:[email protected]?subject=TheStackV2%20request%20for%20dataset%20access%20information) for more information. 2. If you are using the dataset to train models you must adhere to the SoftwareHeritage [principles for language model training](https://www.softwareheritage.org/2023/10/19/swh-statement-on-llm-for-code/). 3. The Stack v2 is a collection of source code from repositories with various licenses. Any use of all or part of the code gathered in The Stack v2 must abide by the terms of the original licenses, including attribution clauses when relevant. We facilitate this by providing provenance information for each data point. 4. The Stack v2 is regularly updated to enact validated data removal requests. By clicking on "Access repository", you agree to update your own version of The Stack v2 to the most recent usable version. By clicking on "Access repository" below, you accept that your contact information (email address and username) can be shared with the dataset maintainers as well. extra_gated_fields: Email: text I have read the License and agree with its terms: checkbox dataset_info: features: - name: blob_id dtype: string - name: directory_id dtype: string - name: path dtype: string - name: content_id dtype: string - name: detected_licenses sequence: string - name: license_type dtype: string - name: repo_name dtype: string - name: snapshot_id dtype: string - name: revision_id dtype: string - name: branch_name dtype: string - name: visit_date dtype: timestamp[ns] - name: revision_date dtype: timestamp[ns] - name: committer_date dtype: timestamp[ns] - name: github_id dtype: int64 - name: star_events_count dtype: int64 - name: fork_events_count dtype: int64 - name: gha_license_id dtype: string - name: gha_event_created_at dtype: timestamp[ns] - name: gha_created_at dtype: timestamp[ns] - name: gha_language dtype: string - name: src_encoding dtype: string - name: language dtype: string - name: is_vendor dtype: bool - name: is_generated dtype: bool - name: length_bytes dtype: int64 - name: extension dtype: string configs: - config_name: default default: true data_files: - split: train path: "data/*/*.parquet" - config_name: "1C_Enterprise" data_files: - split: train path: "data/1C_Enterprise/*.parquet" - config_name: "2-Dimensional_Array" data_files: - split: train path: "data/2-Dimensional_Array/*.parquet" - config_name: "4D" data_files: - split: train path: "data/4D/*.parquet" - config_name: "ABAP" data_files: - split: train path: "data/ABAP/*.parquet" - config_name: "ABAP_CDS" data_files: - split: train path: "data/ABAP_CDS/*.parquet" - config_name: "ABNF" data_files: - split: train path: "data/ABNF/*.parquet" - config_name: "AGS_Script" data_files: - split: train path: "data/AGS_Script/*.parquet" - config_name: "AIDL" data_files: - split: train path: "data/AIDL/*.parquet" - config_name: "AL" data_files: - split: train path: "data/AL/*.parquet" - config_name: "AMPL" data_files: - split: train path: "data/AMPL/*.parquet" - config_name: "ANTLR" data_files: - split: train path: "data/ANTLR/*.parquet" - config_name: "API_Blueprint" data_files: - split: train path: "data/API_Blueprint/*.parquet" - config_name: "APL" data_files: - split: train path: "data/APL/*.parquet" - config_name: "ASL" data_files: - split: train path: "data/ASL/*.parquet" - config_name: "ASN.1" data_files: - split: train path: "data/ASN.1/*.parquet" - config_name: "ASP.NET" data_files: - split: train path: "data/ASP.NET/*.parquet" - config_name: "ATS" data_files: - split: train path: "data/ATS/*.parquet" - config_name: "ActionScript" data_files: - split: train path: "data/ActionScript/*.parquet" - config_name: "Ada" data_files: - split: train path: "data/Ada/*.parquet" - config_name: "Adobe_Font_Metrics" data_files: - split: train path: "data/Adobe_Font_Metrics/*.parquet" - config_name: "Agda" data_files: - split: train path: "data/Agda/*.parquet" - config_name: "Alloy" data_files: - split: train path: "data/Alloy/*.parquet" - config_name: "Alpine_Abuild" data_files: - split: train path: "data/Alpine_Abuild/*.parquet" - config_name: "Altium_Designer" data_files: - split: train path: "data/Altium_Designer/*.parquet" - config_name: "AngelScript" data_files: - split: train path: "data/AngelScript/*.parquet" - config_name: "Ant_Build_System" data_files: - split: train path: "data/Ant_Build_System/*.parquet" - config_name: "Antlers" data_files: - split: train path: "data/Antlers/*.parquet" - config_name: "ApacheConf" data_files: - split: train path: "data/ApacheConf/*.parquet" - config_name: "Apex" data_files: - split: train path: "data/Apex/*.parquet" - config_name: "Apollo_Guidance_Computer" data_files: - split: train path: "data/Apollo_Guidance_Computer/*.parquet" - config_name: "AppleScript" data_files: - split: train path: "data/AppleScript/*.parquet" - config_name: "Arc" data_files: - split: train path: "data/Arc/*.parquet" - config_name: "AsciiDoc" data_files: - split: train path: "data/AsciiDoc/*.parquet" - config_name: "AspectJ" data_files: - split: train path: "data/AspectJ/*.parquet" - config_name: "Assembly" data_files: - split: train path: "data/Assembly/*.parquet" - config_name: "Astro" data_files: - split: train path: "data/Astro/*.parquet" - config_name: "Asymptote" data_files: - split: train path: "data/Asymptote/*.parquet" - config_name: "Augeas" data_files: - split: train path: "data/Augeas/*.parquet" - config_name: "AutoHotkey" data_files: - split: train path: "data/AutoHotkey/*.parquet" - config_name: "AutoIt" data_files: - split: train path: "data/AutoIt/*.parquet" - config_name: "Avro_IDL" data_files: - split: train path: "data/Avro_IDL/*.parquet" - config_name: "Awk" data_files: - split: train path: "data/Awk/*.parquet" - config_name: "BASIC" data_files: - split: train path: "data/BASIC/*.parquet" - config_name: "Ballerina" data_files: - split: train path: "data/Ballerina/*.parquet" - config_name: "Batchfile" data_files: - split: train path: "data/Batchfile/*.parquet" - config_name: "Beef" data_files: - split: train path: "data/Beef/*.parquet" - config_name: "Befunge" data_files: - split: train path: "data/Befunge/*.parquet" - config_name: "Berry" data_files: - split: train path: "data/Berry/*.parquet" - config_name: "BibTeX" data_files: - split: train path: "data/BibTeX/*.parquet" - config_name: "Bicep" data_files: - split: train path: "data/Bicep/*.parquet" - config_name: "Bikeshed" data_files: - split: train path: "data/Bikeshed/*.parquet" - config_name: "Bison" data_files: - split: train path: "data/Bison/*.parquet" - config_name: "BitBake" data_files: - split: train path: "data/BitBake/*.parquet" - config_name: "Blade" data_files: - split: train path: "data/Blade/*.parquet" - config_name: "BlitzBasic" data_files: - split: train path: "data/BlitzBasic/*.parquet" - config_name: "BlitzMax" data_files: - split: train path: "data/BlitzMax/*.parquet" - config_name: "Bluespec" data_files: - split: train path: "data/Bluespec/*.parquet" - config_name: "Boo" data_files: - split: train path: "data/Boo/*.parquet" - config_name: "Boogie" data_files: - split: train path: "data/Boogie/*.parquet" - config_name: "Brainfuck" data_files: - split: train path: "data/Brainfuck/*.parquet" - config_name: "BrighterScript" data_files: - split: train path: "data/BrighterScript/*.parquet" - config_name: "Brightscript" data_files: - split: train path: "data/Brightscript/*.parquet" - config_name: "Browserslist" data_files: - split: train path: "data/Browserslist/*.parquet" - config_name: "C" data_files: - split: train path: "data/C/*.parquet" - config_name: "C++" data_files: - split: train path: "data/C++/*.parquet" - config_name: "C-ObjDump" data_files: - split: train path: "data/C-ObjDump/*.parquet" - config_name: "C-Sharp" data_files: - split: train path: "data/C-Sharp/*.parquet" - config_name: "C2hs_Haskell" data_files: - split: train path: "data/C2hs_Haskell/*.parquet" - config_name: "CAP_CDS" data_files: - split: train path: "data/CAP_CDS/*.parquet" - config_name: "CIL" data_files: - split: train path: "data/CIL/*.parquet" - config_name: "CLIPS" data_files: - split: train path: "data/CLIPS/*.parquet" - config_name: "CMake" data_files: - split: train path: "data/CMake/*.parquet" - config_name: "COBOL" data_files: - split: train path: "data/COBOL/*.parquet" - config_name: "CODEOWNERS" data_files: - split: train path: "data/CODEOWNERS/*.parquet" - config_name: "COLLADA" data_files: - split: train path: "data/COLLADA/*.parquet" - config_name: "CSON" data_files: - split: train path: "data/CSON/*.parquet" - config_name: "CSS" data_files: - split: train path: "data/CSS/*.parquet" - config_name: "CSV" data_files: - split: train path: "data/CSV/*.parquet" - config_name: "CUE" data_files: - split: train path: "data/CUE/*.parquet" - config_name: "CWeb" data_files: - split: train path: "data/CWeb/*.parquet" - config_name: "Cabal_Config" data_files: - split: train path: "data/Cabal_Config/*.parquet" - config_name: "Cadence" data_files: - split: train path: "data/Cadence/*.parquet" - config_name: "Cairo" data_files: - split: train path: "data/Cairo/*.parquet" - config_name: "CameLIGO" data_files: - split: train path: "data/CameLIGO/*.parquet" - config_name: "Cap-n_Proto" data_files: - split: train path: "data/Cap-n_Proto/*.parquet" - config_name: "CartoCSS" data_files: - split: train path: "data/CartoCSS/*.parquet" - config_name: "Ceylon" data_files: - split: train path: "data/Ceylon/*.parquet" - config_name: "Chapel" data_files: - split: train path: "data/Chapel/*.parquet" - config_name: "Charity" data_files: - split: train path: "data/Charity/*.parquet" - config_name: "Checksums" data_files: - split: train path: "data/Checksums/*.parquet" - config_name: "ChucK" data_files: - split: train path: "data/ChucK/*.parquet" - config_name: "Cirru" data_files: - split: train path: "data/Cirru/*.parquet" - config_name: "Clarion" data_files: - split: train path: "data/Clarion/*.parquet" - config_name: "Clarity" data_files: - split: train path: "data/Clarity/*.parquet" - config_name: "Classic_ASP" data_files: - split: train path: "data/Classic_ASP/*.parquet" - config_name: "Clean" data_files: - split: train path: "data/Clean/*.parquet" - config_name: "Click" data_files: - split: train path: "data/Click/*.parquet" - config_name: "Clojure" data_files: - split: train path: "data/Clojure/*.parquet" - config_name: "Closure_Templates" data_files: - split: train path: "data/Closure_Templates/*.parquet" - config_name: "Cloud_Firestore_Security_Rules" data_files: - split: train path: "data/Cloud_Firestore_Security_Rules/*.parquet" - config_name: "CoNLL-U" data_files: - split: train path: "data/CoNLL-U/*.parquet" - config_name: "CodeQL" data_files: - split: train path: "data/CodeQL/*.parquet" - config_name: "CoffeeScript" data_files: - split: train path: "data/CoffeeScript/*.parquet" - config_name: "ColdFusion" data_files: - split: train path: "data/ColdFusion/*.parquet" - config_name: "ColdFusion_CFC" data_files: - split: train path: "data/ColdFusion_CFC/*.parquet" - config_name: "Common_Lisp" data_files: - split: train path: "data/Common_Lisp/*.parquet" - config_name: "Common_Workflow_Language" data_files: - split: train path: "data/Common_Workflow_Language/*.parquet" - config_name: "Component_Pascal" data_files: - split: train path: "data/Component_Pascal/*.parquet" - config_name: "Cool" data_files: - split: train path: "data/Cool/*.parquet" - config_name: "Coq" data_files: - split: train path: "data/Coq/*.parquet" - config_name: "Creole" data_files: - split: train path: "data/Creole/*.parquet" - config_name: "Crystal" data_files: - split: train path: "data/Crystal/*.parquet" - config_name: "Csound" data_files: - split: train path: "data/Csound/*.parquet" - config_name: "Csound_Document" data_files: - split: train path: "data/Csound_Document/*.parquet" - config_name: "Csound_Score" data_files: - split: train path: "data/Csound_Score/*.parquet" - config_name: "Cuda" data_files: - split: train path: "data/Cuda/*.parquet" - config_name: "Cue_Sheet" data_files: - split: train path: "data/Cue_Sheet/*.parquet" - config_name: "Curry" data_files: - split: train path: "data/Curry/*.parquet" - config_name: "Cycript" data_files: - split: train path: "data/Cycript/*.parquet" - config_name: "Cython" data_files: - split: train path: "data/Cython/*.parquet" - config_name: "D" data_files: - split: train path: "data/D/*.parquet" - config_name: "DIGITAL_Command_Language" data_files: - split: train path: "data/DIGITAL_Command_Language/*.parquet" - config_name: "DM" data_files: - split: train path: "data/DM/*.parquet" - config_name: "DNS_Zone" data_files: - split: train path: "data/DNS_Zone/*.parquet" - config_name: "DTrace" data_files: - split: train path: "data/DTrace/*.parquet" - config_name: "Dafny" data_files: - split: train path: "data/Dafny/*.parquet" - config_name: "Darcs_Patch" data_files: - split: train path: "data/Darcs_Patch/*.parquet" - config_name: "Dart" data_files: - split: train path: "data/Dart/*.parquet" - config_name: "DataWeave" data_files: - split: train path: "data/DataWeave/*.parquet" - config_name: "Debian_Package_Control_File" data_files: - split: train path: "data/Debian_Package_Control_File/*.parquet" - config_name: "DenizenScript" data_files: - split: train path: "data/DenizenScript/*.parquet" - config_name: "Dhall" data_files: - split: train path: "data/Dhall/*.parquet" - config_name: "Diff" data_files: - split: train path: "data/Diff/*.parquet" - config_name: "DirectX_3D_File" data_files: - split: train path: "data/DirectX_3D_File/*.parquet" - config_name: "Dockerfile" data_files: - split: train path: "data/Dockerfile/*.parquet" - config_name: "Dogescript" data_files: - split: train path: "data/Dogescript/*.parquet" - config_name: "Dylan" data_files: - split: train path: "data/Dylan/*.parquet" - config_name: "E" data_files: - split: train path: "data/E/*.parquet" - config_name: "E-mail" data_files: - split: train path: "data/E-mail/*.parquet" - config_name: "EBNF" data_files: - split: train path: "data/EBNF/*.parquet" - config_name: "ECL" data_files: - split: train path: "data/ECL/*.parquet" - config_name: "ECLiPSe" data_files: - split: train path: "data/ECLiPSe/*.parquet" - config_name: "EJS" data_files: - split: train path: "data/EJS/*.parquet" - config_name: "EQ" data_files: - split: train path: "data/EQ/*.parquet" - config_name: "Eagle" data_files: - split: train path: "data/Eagle/*.parquet" - config_name: "Earthly" data_files: - split: train path: "data/Earthly/*.parquet" - config_name: "Easybuild" data_files: - split: train path: "data/Easybuild/*.parquet" - config_name: "Ecere_Projects" data_files: - split: train path: "data/Ecere_Projects/*.parquet" - config_name: "EditorConfig" data_files: - split: train path: "data/EditorConfig/*.parquet" - config_name: "Edje_Data_Collection" data_files: - split: train path: "data/Edje_Data_Collection/*.parquet" - config_name: "Eiffel" data_files: - split: train path: "data/Eiffel/*.parquet" - config_name: "Elixir" data_files: - split: train path: "data/Elixir/*.parquet" - config_name: "Elm" data_files: - split: train path: "data/Elm/*.parquet" - config_name: "Elvish" data_files: - split: train path: "data/Elvish/*.parquet" - config_name: "Emacs_Lisp" data_files: - split: train path: "data/Emacs_Lisp/*.parquet" - config_name: "EmberScript" data_files: - split: train path: "data/EmberScript/*.parquet" - config_name: "Erlang" data_files: - split: train path: "data/Erlang/*.parquet" - config_name: "Euphoria" data_files: - split: train path: "data/Euphoria/*.parquet" - config_name: "F-Sharp" data_files: - split: train path: "data/F-Sharp/*.parquet" - config_name: "F-Star" data_files: - split: train path: "data/F-Star/*.parquet" - config_name: "FIGlet_Font" data_files: - split: train path: "data/FIGlet_Font/*.parquet" - config_name: "FLUX" data_files: - split: train path: "data/FLUX/*.parquet" - config_name: "Factor" data_files: - split: train path: "data/Factor/*.parquet" - config_name: "Fancy" data_files: - split: train path: "data/Fancy/*.parquet" - config_name: "Fantom" data_files: - split: train path: "data/Fantom/*.parquet" - config_name: "Faust" data_files: - split: train path: "data/Faust/*.parquet" - config_name: "Fennel" data_files: - split: train path: "data/Fennel/*.parquet" - config_name: "Filebench_WML" data_files: - split: train path: "data/Filebench_WML/*.parquet" - config_name: "Filterscript" data_files: - split: train path: "data/Filterscript/*.parquet" - config_name: "Fluent" data_files: - split: train path: "data/Fluent/*.parquet" - config_name: "Formatted" data_files: - split: train path: "data/Formatted/*.parquet" - config_name: "Forth" data_files: - split: train path: "data/Forth/*.parquet" - config_name: "Fortran" data_files: - split: train path: "data/Fortran/*.parquet" - config_name: "Fortran_Free_Form" data_files: - split: train path: "data/Fortran_Free_Form/*.parquet" - config_name: "FreeBasic" data_files: - split: train path: "data/FreeBasic/*.parquet" - config_name: "FreeMarker" data_files: - split: train path: "data/FreeMarker/*.parquet" - config_name: "Frege" data_files: - split: train path: "data/Frege/*.parquet" - config_name: "Futhark" data_files: - split: train path: "data/Futhark/*.parquet" - config_name: "G-code" data_files: - split: train path: "data/G-code/*.parquet" - config_name: "GAML" data_files: - split: train path: "data/GAML/*.parquet" - config_name: "GAMS" data_files: - split: train path: "data/GAMS/*.parquet" - config_name: "GAP" data_files: - split: train path: "data/GAP/*.parquet" - config_name: "GCC_Machine_Description" data_files: - split: train path: "data/GCC_Machine_Description/*.parquet" - config_name: "GDB" data_files: - split: train path: "data/GDB/*.parquet" - config_name: "GDScript" data_files: - split: train path: "data/GDScript/*.parquet" - config_name: "GEDCOM" data_files: - split: train path: "data/GEDCOM/*.parquet" - config_name: "GLSL" data_files: - split: train path: "data/GLSL/*.parquet" - config_name: "GN" data_files: - split: train path: "data/GN/*.parquet" - config_name: "GSC" data_files: - split: train path: "data/GSC/*.parquet" - config_name: "Game_Maker_Language" data_files: - split: train path: "data/Game_Maker_Language/*.parquet" - config_name: "Gemfile.lock" data_files: - split: train path: "data/Gemfile.lock/*.parquet" - config_name: "Gemini" data_files: - split: train path: "data/Gemini/*.parquet" - config_name: "Genero" data_files: - split: train path: "data/Genero/*.parquet" - config_name: "Genero_Forms" data_files: - split: train path: "data/Genero_Forms/*.parquet" - config_name: "Genie" data_files: - split: train path: "data/Genie/*.parquet" - config_name: "Genshi" data_files: - split: train path: "data/Genshi/*.parquet" - config_name: "Gentoo_Ebuild" data_files: - split: train path: "data/Gentoo_Ebuild/*.parquet" - config_name: "Gentoo_Eclass" data_files: - split: train path: "data/Gentoo_Eclass/*.parquet" - config_name: "Gerber_Image" data_files: - split: train path: "data/Gerber_Image/*.parquet" - config_name: "Gettext_Catalog" data_files: - split: train path: "data/Gettext_Catalog/*.parquet" - config_name: "Gherkin" data_files: - split: train path: "data/Gherkin/*.parquet" - config_name: "Git_Attributes" data_files: - split: train path: "data/Git_Attributes/*.parquet" - config_name: "Git_Config" data_files: - split: train path: "data/Git_Config/*.parquet" - config_name: "Git_Revision_List" data_files: - split: train path: "data/Git_Revision_List/*.parquet" - config_name: "Gleam" data_files: - split: train path: "data/Gleam/*.parquet" - config_name: "Glyph" data_files: - split: train path: "data/Glyph/*.parquet" - config_name: "Glyph_Bitmap_Distribution_Format" data_files: - split: train path: "data/Glyph_Bitmap_Distribution_Format/*.parquet" - config_name: "Gnuplot" data_files: - split: train path: "data/Gnuplot/*.parquet" - config_name: "Go" data_files: - split: train path: "data/Go/*.parquet" - config_name: "Go_Checksums" data_files: - split: train path: "data/Go_Checksums/*.parquet" - config_name: "Go_Module" data_files: - split: train path: "data/Go_Module/*.parquet" - config_name: "Golo" data_files: - split: train path: "data/Golo/*.parquet" - config_name: "Gosu" data_files: - split: train path: "data/Gosu/*.parquet" - config_name: "Grace" data_files: - split: train path: "data/Grace/*.parquet" - config_name: "Gradle" data_files: - split: train path: "data/Gradle/*.parquet" - config_name: "Grammatical_Framework" data_files: - split: train path: "data/Grammatical_Framework/*.parquet" - config_name: "GraphQL" data_files: - split: train path: "data/GraphQL/*.parquet" - config_name: "Graph_Modeling_Language" data_files: - split: train path: "data/Graph_Modeling_Language/*.parquet" - config_name: "Graphviz_(DOT)" data_files: - split: train path: "data/Graphviz_(DOT)/*.parquet" - config_name: "Groovy" data_files: - split: train path: "data/Groovy/*.parquet" - config_name: "Groovy_Server_Pages" data_files: - split: train path: "data/Groovy_Server_Pages/*.parquet" - config_name: "HAProxy" data_files: - split: train path: "data/HAProxy/*.parquet" - config_name: "HCL" data_files: - split: train path: "data/HCL/*.parquet" - config_name: "HLSL" data_files: - split: train path: "data/HLSL/*.parquet" - config_name: "HOCON" data_files: - split: train path: "data/HOCON/*.parquet" - config_name: "HTML" data_files: - split: train path: "data/HTML/*.parquet" - config_name: "HTML+ECR" data_files: - split: train path: "data/HTML+ECR/*.parquet" - config_name: "HTML+EEX" data_files: - split: train path: "data/HTML+EEX/*.parquet" - config_name: "HTML+ERB" data_files: - split: train path: "data/HTML+ERB/*.parquet" - config_name: "HTML+PHP" data_files: - split: train path: "data/HTML+PHP/*.parquet" - config_name: "HTML+Razor" data_files: - split: train path: "data/HTML+Razor/*.parquet" - config_name: "HTTP" data_files: - split: train path: "data/HTTP/*.parquet" - config_name: "HXML" data_files: - split: train path: "data/HXML/*.parquet" - config_name: "Hack" data_files: - split: train path: "data/Hack/*.parquet" - config_name: "Haml" data_files: - split: train path: "data/Haml/*.parquet" - config_name: "Handlebars" data_files: - split: train path: "data/Handlebars/*.parquet" - config_name: "Harbour" data_files: - split: train path: "data/Harbour/*.parquet" - config_name: "Haskell" data_files: - split: train path: "data/Haskell/*.parquet" - config_name: "Haxe" data_files: - split: train path: "data/Haxe/*.parquet" - config_name: "HiveQL" data_files: - split: train path: "data/HiveQL/*.parquet" - config_name: "HolyC" data_files: - split: train path: "data/HolyC/*.parquet" - config_name: "Hy" data_files: - split: train path: "data/Hy/*.parquet" - config_name: "HyPhy" data_files: - split: train path: "data/HyPhy/*.parquet" - config_name: "IDL" data_files: - split: train path: "data/IDL/*.parquet" - config_name: "IGOR_Pro" data_files: - split: train path: "data/IGOR_Pro/*.parquet" - config_name: "INI" data_files: - split: train path: "data/INI/*.parquet" - config_name: "IRC_log" data_files: - split: train path: "data/IRC_log/*.parquet" - config_name: "Idris" data_files: - split: train path: "data/Idris/*.parquet" - config_name: "Ignore_List" data_files: - split: train path: "data/Ignore_List/*.parquet" - config_name: "ImageJ_Macro" data_files: - split: train path: "data/ImageJ_Macro/*.parquet" - config_name: "Inform_7" data_files: - split: train path: "data/Inform_7/*.parquet" - config_name: "Inno_Setup" data_files: - split: train path: "data/Inno_Setup/*.parquet" - config_name: "Io" data_files: - split: train path: "data/Io/*.parquet" - config_name: "Ioke" data_files: - split: train path: "data/Ioke/*.parquet" - config_name: "Isabelle" data_files: - split: train path: "data/Isabelle/*.parquet" - config_name: "Isabelle_ROOT" data_files: - split: train path: "data/Isabelle_ROOT/*.parquet" - config_name: "J" data_files: - split: train path: "data/J/*.parquet" - config_name: "JAR_Manifest" data_files: - split: train path: "data/JAR_Manifest/*.parquet" - config_name: "JFlex" data_files: - split: train path: "data/JFlex/*.parquet" - config_name: "JSON" data_files: - split: train path: "data/JSON/*.parquet" - config_name: "JSON5" data_files: - split: train path: "data/JSON5/*.parquet" - config_name: "JSONLD" data_files: - split: train path: "data/JSONLD/*.parquet" - config_name: "JSON_with_Comments" data_files: - split: train path: "data/JSON_with_Comments/*.parquet" - config_name: "JSONiq" data_files: - split: train path: "data/JSONiq/*.parquet" - config_name: "Janet" data_files: - split: train path: "data/Janet/*.parquet" - config_name: "Jasmin" data_files: - split: train path: "data/Jasmin/*.parquet" - config_name: "Java" data_files: - split: train path: "data/Java/*.parquet" - config_name: "JavaScript" data_files: - split: train path: "data/JavaScript/*.parquet" - config_name: "JavaScript+ERB" data_files: - split: train path: "data/JavaScript+ERB/*.parquet" - config_name: "Java_Properties" data_files: - split: train path: "data/Java_Properties/*.parquet" - config_name: "Java_Server_Pages" data_files: - split: train path: "data/Java_Server_Pages/*.parquet" - config_name: "Jest_Snapshot" data_files: - split: train path: "data/Jest_Snapshot/*.parquet" - config_name: "JetBrains_MPS" data_files: - split: train path: "data/JetBrains_MPS/*.parquet" - config_name: "Jinja" data_files: - split: train path: "data/Jinja/*.parquet" - config_name: "Jison" data_files: - split: train path: "data/Jison/*.parquet" - config_name: "Jison_Lex" data_files: - split: train path: "data/Jison_Lex/*.parquet" - config_name: "Jolie" data_files: - split: train path: "data/Jolie/*.parquet" - config_name: "Jsonnet" data_files: - split: train path: "data/Jsonnet/*.parquet" - config_name: "Julia" data_files: - split: train path: "data/Julia/*.parquet" - config_name: "Jupyter_Notebook" data_files: - split: train path: "data/Jupyter_Notebook/*.parquet" - config_name: "KRL" data_files: - split: train path: "data/KRL/*.parquet" - config_name: "Kaitai_Struct" data_files: - split: train path: "data/Kaitai_Struct/*.parquet" - config_name: "KakouneScript" data_files: - split: train path: "data/KakouneScript/*.parquet" - config_name: "KiCad_Layout" data_files: - split: train path: "data/KiCad_Layout/*.parquet" - config_name: "KiCad_Legacy_Layout" data_files: - split: train path: "data/KiCad_Legacy_Layout/*.parquet" - config_name: "KiCad_Schematic" data_files: - split: train path: "data/KiCad_Schematic/*.parquet" - config_name: "Kit" data_files: - split: train path: "data/Kit/*.parquet" - config_name: "Kotlin" data_files: - split: train path: "data/Kotlin/*.parquet" - config_name: "Kusto" data_files: - split: train path: "data/Kusto/*.parquet" - config_name: "LFE" data_files: - split: train path: "data/LFE/*.parquet" - config_name: "LLVM" data_files: - split: train path: "data/LLVM/*.parquet" - config_name: "LOLCODE" data_files: - split: train path: "data/LOLCODE/*.parquet" - config_name: "LSL" data_files: - split: train path: "data/LSL/*.parquet" - config_name: "LTspice_Symbol" data_files: - split: train path: "data/LTspice_Symbol/*.parquet" - config_name: "LabVIEW" data_files: - split: train path: "data/LabVIEW/*.parquet" - config_name: "Lark" data_files: - split: train path: "data/Lark/*.parquet" - config_name: "Lasso" data_files: - split: train path: "data/Lasso/*.parquet" - config_name: "Latte" data_files: - split: train path: "data/Latte/*.parquet" - config_name: "Lean" data_files: - split: train path: "data/Lean/*.parquet" - config_name: "Less" data_files: - split: train path: "data/Less/*.parquet" - config_name: "Lex" data_files: - split: train path: "data/Lex/*.parquet" - config_name: "LigoLANG" data_files: - split: train path: "data/LigoLANG/*.parquet" - config_name: "LilyPond" data_files: - split: train path: "data/LilyPond/*.parquet" - config_name: "Limbo" data_files: - split: train path: "data/Limbo/*.parquet" - config_name: "Linker_Script" data_files: - split: train path: "data/Linker_Script/*.parquet" - config_name: "Linux_Kernel_Module" data_files: - split: train path: "data/Linux_Kernel_Module/*.parquet" - config_name: "Liquid" data_files: - split: train path: "data/Liquid/*.parquet" - config_name: "Literate_Agda" data_files: - split: train path: "data/Literate_Agda/*.parquet" - config_name: "Literate_CoffeeScript" data_files: - split: train path: "data/Literate_CoffeeScript/*.parquet" - config_name: "Literate_Haskell" data_files: - split: train path: "data/Literate_Haskell/*.parquet" - config_name: "LiveScript" data_files: - split: train path: "data/LiveScript/*.parquet" - config_name: "Logos" data_files: - split: train path: "data/Logos/*.parquet" - config_name: "Logtalk" data_files: - split: train path: "data/Logtalk/*.parquet" - config_name: "LookML" data_files: - split: train path: "data/LookML/*.parquet" - config_name: "LoomScript" data_files: - split: train path: "data/LoomScript/*.parquet" - config_name: "Lua" data_files: - split: train path: "data/Lua/*.parquet" - config_name: "M" data_files: - split: train path: "data/M/*.parquet" - config_name: "M4" data_files: - split: train path: "data/M4/*.parquet" - config_name: "M4Sugar" data_files: - split: train path: "data/M4Sugar/*.parquet" - config_name: "MATLAB" data_files: - split: train path: "data/MATLAB/*.parquet" - config_name: "MAXScript" data_files: - split: train path: "data/MAXScript/*.parquet" - config_name: "MLIR" data_files: - split: train path: "data/MLIR/*.parquet" - config_name: "MQL4" data_files: - split: train path: "data/MQL4/*.parquet" - config_name: "MQL5" data_files: - split: train path: "data/MQL5/*.parquet" - config_name: "MTML" data_files: - split: train path: "data/MTML/*.parquet" - config_name: "MUF" data_files: - split: train path: "data/MUF/*.parquet" - config_name: "Macaulay2" data_files: - split: train path: "data/Macaulay2/*.parquet" - config_name: "Makefile" data_files: - split: train path: "data/Makefile/*.parquet" - config_name: "Mako" data_files: - split: train path: "data/Mako/*.parquet" - config_name: "Markdown" data_files: - split: train path: "data/Markdown/*.parquet" - config_name: "Marko" data_files: - split: train path: "data/Marko/*.parquet" - config_name: "Mask" data_files: - split: train path: "data/Mask/*.parquet" - config_name: "Mathematica" data_files: - split: train path: "data/Mathematica/*.parquet" - config_name: "Maven_POM" data_files: - split: train path: "data/Maven_POM/*.parquet" - config_name: "Max" data_files: - split: train path: "data/Max/*.parquet" - config_name: "Mercury" data_files: - split: train path: "data/Mercury/*.parquet" - config_name: "Meson" data_files: - split: train path: "data/Meson/*.parquet" - config_name: "Metal" data_files: - split: train path: "data/Metal/*.parquet" - config_name: "Microsoft_Developer_Studio_Project" data_files: - split: train path: "data/Microsoft_Developer_Studio_Project/*.parquet" - config_name: "Microsoft_Visual_Studio_Solution" data_files: - split: train path: "data/Microsoft_Visual_Studio_Solution/*.parquet" - config_name: "MiniD" data_files: - split: train path: "data/MiniD/*.parquet" - config_name: "MiniYAML" data_files: - split: train path: "data/MiniYAML/*.parquet" - config_name: "Mint" data_files: - split: train path: "data/Mint/*.parquet" - config_name: "Mirah" data_files: - split: train path: "data/Mirah/*.parquet" - config_name: "Modelica" data_files: - split: train path: "data/Modelica/*.parquet" - config_name: "Modula-2" data_files: - split: train path: "data/Modula-2/*.parquet" - config_name: "Modula-3" data_files: - split: train path: "data/Modula-3/*.parquet" - config_name: "Module_Management_System" data_files: - split: train path: "data/Module_Management_System/*.parquet" - config_name: "Monkey" data_files: - split: train path: "data/Monkey/*.parquet" - config_name: "Monkey_C" data_files: - split: train path: "data/Monkey_C/*.parquet" - config_name: "Moocode" data_files: - split: train path: "data/Moocode/*.parquet" - config_name: "MoonScript" data_files: - split: train path: "data/MoonScript/*.parquet" - config_name: "Motoko" data_files: - split: train path: "data/Motoko/*.parquet" - config_name: "Motorola_68K_Assembly" data_files: - split: train path: "data/Motorola_68K_Assembly/*.parquet" - config_name: "Move" data_files: - split: train path: "data/Move/*.parquet" - config_name: "Muse" data_files: - split: train path: "data/Muse/*.parquet" - config_name: "Mustache" data_files: - split: train path: "data/Mustache/*.parquet" - config_name: "Myghty" data_files: - split: train path: "data/Myghty/*.parquet" - config_name: "NASL" data_files: - split: train path: "data/NASL/*.parquet" - config_name: "NCL" data_files: - split: train path: "data/NCL/*.parquet" - config_name: "NEON" data_files: - split: train path: "data/NEON/*.parquet" - config_name: "NL" data_files: - split: train path: "data/NL/*.parquet" - config_name: "NPM_Config" data_files: - split: train path: "data/NPM_Config/*.parquet" - config_name: "NSIS" data_files: - split: train path: "data/NSIS/*.parquet" - config_name: "NWScript" data_files: - split: train path: "data/NWScript/*.parquet" - config_name: "Nasal" data_files: - split: train path: "data/Nasal/*.parquet" - config_name: "Nearley" data_files: - split: train path: "data/Nearley/*.parquet" - config_name: "Nemerle" data_files: - split: train path: "data/Nemerle/*.parquet" - config_name: "NetLinx" data_files: - split: train path: "data/NetLinx/*.parquet" - config_name: "NetLinx+ERB" data_files: - split: train path: "data/NetLinx+ERB/*.parquet" - config_name: "NetLogo" data_files: - split: train path: "data/NetLogo/*.parquet" - config_name: "NewLisp" data_files: - split: train path: "data/NewLisp/*.parquet" - config_name: "Nextflow" data_files: - split: train path: "data/Nextflow/*.parquet" - config_name: "Nginx" data_files: - split: train path: "data/Nginx/*.parquet" - config_name: "Nim" data_files: - split: train path: "data/Nim/*.parquet" - config_name: "Ninja" data_files: - split: train path: "data/Ninja/*.parquet" - config_name: "Nit" data_files: - split: train path: "data/Nit/*.parquet" - config_name: "Nix" data_files: - split: train path: "data/Nix/*.parquet" - config_name: "Nu" data_files: - split: train path: "data/Nu/*.parquet" - config_name: "NumPy" data_files: - split: train path: "data/NumPy/*.parquet" - config_name: "Nunjucks" data_files: - split: train path: "data/Nunjucks/*.parquet" - config_name: "OCaml" data_files: - split: train path: "data/OCaml/*.parquet" - config_name: "ObjDump" data_files: - split: train path: "data/ObjDump/*.parquet" - config_name: "ObjectScript" data_files: - split: train path: "data/ObjectScript/*.parquet" - config_name: "Object_Data_Instance_Notation" data_files: - split: train path: "data/Object_Data_Instance_Notation/*.parquet" - config_name: "Objective-C" data_files: - split: train path: "data/Objective-C/*.parquet" - config_name: "Objective-C++" data_files: - split: train path: "data/Objective-C++/*.parquet" - config_name: "Objective-J" data_files: - split: train path: "data/Objective-J/*.parquet" - config_name: "Odin" data_files: - split: train path: "data/Odin/*.parquet" - config_name: "Omgrofl" data_files: - split: train path: "data/Omgrofl/*.parquet" - config_name: "Opa" data_files: - split: train path: "data/Opa/*.parquet" - config_name: "Opal" data_files: - split: train path: "data/Opal/*.parquet" - config_name: "OpenCL" data_files: - split: train path: "data/OpenCL/*.parquet" - config_name: "OpenEdge_ABL" data_files: - split: train path: "data/OpenEdge_ABL/*.parquet" - config_name: "OpenQASM" data_files: - split: train path: "data/OpenQASM/*.parquet" - config_name: "OpenRC_runscript" data_files: - split: train path: "data/OpenRC_runscript/*.parquet" - config_name: "OpenSCAD" data_files: - split: train path: "data/OpenSCAD/*.parquet" - config_name: "OpenStep_Property_List" data_files: - split: train path: "data/OpenStep_Property_List/*.parquet" - config_name: "OpenType_Feature_File" data_files: - split: train path: "data/OpenType_Feature_File/*.parquet" - config_name: "Open_Policy_Agent" data_files: - split: train path: "data/Open_Policy_Agent/*.parquet" - config_name: "Org" data_files: - split: train path: "data/Org/*.parquet" - config_name: "Ox" data_files: - split: train path: "data/Ox/*.parquet" - config_name: "Oxygene" data_files: - split: train path: "data/Oxygene/*.parquet" - config_name: "Oz" data_files: - split: train path: "data/Oz/*.parquet" - config_name: "P4" data_files: - split: train path: "data/P4/*.parquet" - config_name: "PEG.js" data_files: - split: train path: "data/PEG.js/*.parquet" - config_name: "PHP" data_files: - split: train path: "data/PHP/*.parquet" - config_name: "PLSQL" data_files: - split: train path: "data/PLSQL/*.parquet" - config_name: "PLpgSQL" data_files: - split: train path: "data/PLpgSQL/*.parquet" - config_name: "POV-Ray_SDL" data_files: - split: train path: "data/POV-Ray_SDL/*.parquet" - config_name: "Pan" data_files: - split: train path: "data/Pan/*.parquet" - config_name: "Papyrus" data_files: - split: train path: "data/Papyrus/*.parquet" - config_name: "Parrot" data_files: - split: train path: "data/Parrot/*.parquet" - config_name: "Parrot_Assembly" data_files: - split: train path: "data/Parrot_Assembly/*.parquet" - config_name: "Parrot_Internal_Representation" data_files: - split: train path: "data/Parrot_Internal_Representation/*.parquet" - config_name: "Pascal" data_files: - split: train path: "data/Pascal/*.parquet" - config_name: "Pawn" data_files: - split: train path: "data/Pawn/*.parquet" - config_name: "Pep8" data_files: - split: train path: "data/Pep8/*.parquet" - config_name: "Perl" data_files: - split: train path: "data/Perl/*.parquet" - config_name: "Pic" data_files: - split: train path: "data/Pic/*.parquet" - config_name: "Pickle" data_files: - split: train path: "data/Pickle/*.parquet" - config_name: "PicoLisp" data_files: - split: train path: "data/PicoLisp/*.parquet" - config_name: "PigLatin" data_files: - split: train path: "data/PigLatin/*.parquet" - config_name: "Pike" data_files: - split: train path: "data/Pike/*.parquet" - config_name: "PlantUML" data_files: - split: train path: "data/PlantUML/*.parquet" - config_name: "Pod" data_files: - split: train path: "data/Pod/*.parquet" - config_name: "Pod_6" data_files: - split: train path: "data/Pod_6/*.parquet" - config_name: "PogoScript" data_files: - split: train path: "data/PogoScript/*.parquet" - config_name: "Pony" data_files: - split: train path: "data/Pony/*.parquet" - config_name: "Portugol" data_files: - split: train path: "data/Portugol/*.parquet" - config_name: "PostCSS" data_files: - split: train path: "data/PostCSS/*.parquet" - config_name: "PostScript" data_files: - split: train path: "data/PostScript/*.parquet" - config_name: "PowerBuilder" data_files: - split: train path: "data/PowerBuilder/*.parquet" - config_name: "PowerShell" data_files: - split: train path: "data/PowerShell/*.parquet" - config_name: "Prisma" data_files: - split: train path: "data/Prisma/*.parquet" - config_name: "Processing" data_files: - split: train path: "data/Processing/*.parquet" - config_name: "Procfile" data_files: - split: train path: "data/Procfile/*.parquet" - config_name: "Proguard" data_files: - split: train path: "data/Proguard/*.parquet" - config_name: "Prolog" data_files: - split: train path: "data/Prolog/*.parquet" - config_name: "Promela" data_files: - split: train path: "data/Promela/*.parquet" - config_name: "Propeller_Spin" data_files: - split: train path: "data/Propeller_Spin/*.parquet" - config_name: "Protocol_Buffer" data_files: - split: train path: "data/Protocol_Buffer/*.parquet" - config_name: "Protocol_Buffer_Text_Format" data_files: - split: train path: "data/Protocol_Buffer_Text_Format/*.parquet" - config_name: "Public_Key" data_files: - split: train path: "data/Public_Key/*.parquet" - config_name: "Pug" data_files: - split: train path: "data/Pug/*.parquet" - config_name: "Puppet" data_files: - split: train path: "data/Puppet/*.parquet" - config_name: "PureBasic" data_files: - split: train path: "data/PureBasic/*.parquet" - config_name: "PureScript" data_files: - split: train path: "data/PureScript/*.parquet" - config_name: "Pure_Data" data_files: - split: train path: "data/Pure_Data/*.parquet" - config_name: "Python" data_files: - split: train path: "data/Python/*.parquet" - config_name: "Python_traceback" data_files: - split: train path: "data/Python_traceback/*.parquet" - config_name: "Q-Sharp" data_files: - split: train path: "data/Q-Sharp/*.parquet" - config_name: "QML" data_files: - split: train path: "data/QML/*.parquet" - config_name: "QMake" data_files: - split: train path: "data/QMake/*.parquet" - config_name: "Qt_Script" data_files: - split: train path: "data/Qt_Script/*.parquet" - config_name: "Quake" data_files: - split: train path: "data/Quake/*.parquet" - config_name: "R" data_files: - split: train path: "data/R/*.parquet" - config_name: "RAML" data_files: - split: train path: "data/RAML/*.parquet" - config_name: "RDoc" data_files: - split: train path: "data/RDoc/*.parquet" - config_name: "REALbasic" data_files: - split: train path: "data/REALbasic/*.parquet" - config_name: "REXX" data_files: - split: train path: "data/REXX/*.parquet" - config_name: "RMarkdown" data_files: - split: train path: "data/RMarkdown/*.parquet" - config_name: "RPC" data_files: - split: train path: "data/RPC/*.parquet" - config_name: "RPGLE" data_files: - split: train path: "data/RPGLE/*.parquet" - config_name: "RPM_Spec" data_files: - split: train path: "data/RPM_Spec/*.parquet" - config_name: "RUNOFF" data_files: - split: train path: "data/RUNOFF/*.parquet" - config_name: "Racket" data_files: - split: train path: "data/Racket/*.parquet" - config_name: "Ragel" data_files: - split: train path: "data/Ragel/*.parquet" - config_name: "Raku" data_files: - split: train path: "data/Raku/*.parquet" - config_name: "Rascal" data_files: - split: train path: "data/Rascal/*.parquet" - config_name: "Raw_token_data" data_files: - split: train path: "data/Raw_token_data/*.parquet" - config_name: "ReScript" data_files: - split: train path: "data/ReScript/*.parquet" - config_name: "Readline_Config" data_files: - split: train path: "data/Readline_Config/*.parquet" - config_name: "Reason" data_files: - split: train path: "data/Reason/*.parquet" - config_name: "ReasonLIGO" data_files: - split: train path: "data/ReasonLIGO/*.parquet" - config_name: "Rebol" data_files: - split: train path: "data/Rebol/*.parquet" - config_name: "Record_Jar" data_files: - split: train path: "data/Record_Jar/*.parquet" - config_name: "Red" data_files: - split: train path: "data/Red/*.parquet" - config_name: "Redcode" data_files: - split: train path: "data/Redcode/*.parquet" - config_name: "Redirect_Rules" data_files: - split: train path: "data/Redirect_Rules/*.parquet" - config_name: "Regular_Expression" data_files: - split: train path: "data/Regular_Expression/*.parquet" - config_name: "Ren-Py" data_files: - split: train path: "data/Ren-Py/*.parquet" - config_name: "RenderScript" data_files: - split: train path: "data/RenderScript/*.parquet" - config_name: "Rich_Text_Format" data_files: - split: train path: "data/Rich_Text_Format/*.parquet" - config_name: "Ring" data_files: - split: train path: "data/Ring/*.parquet" - config_name: "Riot" data_files: - split: train path: "data/Riot/*.parquet" - config_name: "RobotFramework" data_files: - split: train path: "data/RobotFramework/*.parquet" - config_name: "Roff" data_files: - split: train path: "data/Roff/*.parquet" - config_name: "Roff_Manpage" data_files: - split: train path: "data/Roff_Manpage/*.parquet" - config_name: "Rouge" data_files: - split: train path: "data/Rouge/*.parquet" - config_name: "RouterOS_Script" data_files: - split: train path: "data/RouterOS_Script/*.parquet" - config_name: "Ruby" data_files: - split: train path: "data/Ruby/*.parquet" - config_name: "Rust" data_files: - split: train path: "data/Rust/*.parquet" - config_name: "SAS" data_files: - split: train path: "data/SAS/*.parquet" - config_name: "SCSS" data_files: - split: train path: "data/SCSS/*.parquet" - config_name: "SELinux_Policy" data_files: - split: train path: "data/SELinux_Policy/*.parquet" - config_name: "SMT" data_files: - split: train path: "data/SMT/*.parquet" - config_name: "SPARQL" data_files: - split: train path: "data/SPARQL/*.parquet" - config_name: "SQF" data_files: - split: train path: "data/SQF/*.parquet" - config_name: "SQL" data_files: - split: train path: "data/SQL/*.parquet" - config_name: "SQLPL" data_files: - split: train path: "data/SQLPL/*.parquet" - config_name: "SRecode_Template" data_files: - split: train path: "data/SRecode_Template/*.parquet" - config_name: "SSH_Config" data_files: - split: train path: "data/SSH_Config/*.parquet" - config_name: "STAR" data_files: - split: train path: "data/STAR/*.parquet" - config_name: "STL" data_files: - split: train path: "data/STL/*.parquet" - config_name: "STON" data_files: - split: train path: "data/STON/*.parquet" - config_name: "SVG" data_files: - split: train path: "data/SVG/*.parquet" - config_name: "SWIG" data_files: - split: train path: "data/SWIG/*.parquet" - config_name: "Sage" data_files: - split: train path: "data/Sage/*.parquet" - config_name: "SaltStack" data_files: - split: train path: "data/SaltStack/*.parquet" - config_name: "Sass" data_files: - split: train path: "data/Sass/*.parquet" - config_name: "Scala" data_files: - split: train path: "data/Scala/*.parquet" - config_name: "Scaml" data_files: - split: train path: "data/Scaml/*.parquet" - config_name: "Scheme" data_files: - split: train path: "data/Scheme/*.parquet" - config_name: "Scilab" data_files: - split: train path: "data/Scilab/*.parquet" - config_name: "Self" data_files: - split: train path: "data/Self/*.parquet" - config_name: "ShaderLab" data_files: - split: train path: "data/ShaderLab/*.parquet" - config_name: "Shell" data_files: - split: train path: "data/Shell/*.parquet" - config_name: "ShellCheck_Config" data_files: - split: train path: "data/ShellCheck_Config/*.parquet" - config_name: "ShellSession" data_files: - split: train path: "data/ShellSession/*.parquet" - config_name: "Shen" data_files: - split: train path: "data/Shen/*.parquet" - config_name: "Sieve" data_files: - split: train path: "data/Sieve/*.parquet" - config_name: "Singularity" data_files: - split: train path: "data/Singularity/*.parquet" - config_name: "Slash" data_files: - split: train path: "data/Slash/*.parquet" - config_name: "Slice" data_files: - split: train path: "data/Slice/*.parquet" - config_name: "Slim" data_files: - split: train path: "data/Slim/*.parquet" - config_name: "SmPL" data_files: - split: train path: "data/SmPL/*.parquet" - config_name: "Smali" data_files: - split: train path: "data/Smali/*.parquet" - config_name: "Smalltalk" data_files: - split: train path: "data/Smalltalk/*.parquet" - config_name: "Smarty" data_files: - split: train path: "data/Smarty/*.parquet" - config_name: "Solidity" data_files: - split: train path: "data/Solidity/*.parquet" - config_name: "Soong" data_files: - split: train path: "data/Soong/*.parquet" - config_name: "SourcePawn" data_files: - split: train path: "data/SourcePawn/*.parquet" - config_name: "Spline_Font_Database" data_files: - split: train path: "data/Spline_Font_Database/*.parquet" - config_name: "Squirrel" data_files: - split: train path: "data/Squirrel/*.parquet" - config_name: "Stan" data_files: - split: train path: "data/Stan/*.parquet" - config_name: "Standard_ML" data_files: - split: train path: "data/Standard_ML/*.parquet" - config_name: "Starlark" data_files: - split: train path: "data/Starlark/*.parquet" - config_name: "Stata" data_files: - split: train path: "data/Stata/*.parquet" - config_name: "StringTemplate" data_files: - split: train path: "data/StringTemplate/*.parquet" - config_name: "Stylus" data_files: - split: train path: "data/Stylus/*.parquet" - config_name: "SubRip_Text" data_files: - split: train path: "data/SubRip_Text/*.parquet" - config_name: "SugarSS" data_files: - split: train path: "data/SugarSS/*.parquet" - config_name: "SuperCollider" data_files: - split: train path: "data/SuperCollider/*.parquet" - config_name: "Svelte" data_files: - split: train path: "data/Svelte/*.parquet" - config_name: "Swift" data_files: - split: train path: "data/Swift/*.parquet" - config_name: "SystemVerilog" data_files: - split: train path: "data/SystemVerilog/*.parquet" - config_name: "TI_Program" data_files: - split: train path: "data/TI_Program/*.parquet" - config_name: "TLA" data_files: - split: train path: "data/TLA/*.parquet" - config_name: "TOML" data_files: - split: train path: "data/TOML/*.parquet" - config_name: "TSQL" data_files: - split: train path: "data/TSQL/*.parquet" - config_name: "TSV" data_files: - split: train path: "data/TSV/*.parquet" - config_name: "TSX" data_files: - split: train path: "data/TSX/*.parquet" - config_name: "TXL" data_files: - split: train path: "data/TXL/*.parquet" - config_name: "Talon" data_files: - split: train path: "data/Talon/*.parquet" - config_name: "Tcl" data_files: - split: train path: "data/Tcl/*.parquet" - config_name: "Tcsh" data_files: - split: train path: "data/Tcsh/*.parquet" - config_name: "TeX" data_files: - split: train path: "data/TeX/*.parquet" - config_name: "Tea" data_files: - split: train path: "data/Tea/*.parquet" - config_name: "Terra" data_files: - split: train path: "data/Terra/*.parquet" - config_name: "Texinfo" data_files: - split: train path: "data/Texinfo/*.parquet" - config_name: "Text" data_files: - split: train path: "data/Text/*.parquet" - config_name: "TextMate_Properties" data_files: - split: train path: "data/TextMate_Properties/*.parquet" - config_name: "Textile" data_files: - split: train path: "data/Textile/*.parquet" - config_name: "Thrift" data_files: - split: train path: "data/Thrift/*.parquet" - config_name: "Turing" data_files: - split: train path: "data/Turing/*.parquet" - config_name: "Turtle" data_files: - split: train path: "data/Turtle/*.parquet" - config_name: "Twig" data_files: - split: train path: "data/Twig/*.parquet" - config_name: "TypeScript" data_files: - split: train path: "data/TypeScript/*.parquet" - config_name: "Type_Language" data_files: - split: train path: "data/Type_Language/*.parquet" - config_name: "Unified_Parallel_C" data_files: - split: train path: "data/Unified_Parallel_C/*.parquet" - config_name: "Unity3D_Asset" data_files: - split: train path: "data/Unity3D_Asset/*.parquet" - config_name: "Unix_Assembly" data_files: - split: train path: "data/Unix_Assembly/*.parquet" - config_name: "Uno" data_files: - split: train path: "data/Uno/*.parquet" - config_name: "UnrealScript" data_files: - split: train path: "data/UnrealScript/*.parquet" - config_name: "UrWeb" data_files: - split: train path: "data/UrWeb/*.parquet" - config_name: "V" data_files: - split: train path: "data/V/*.parquet" - config_name: "VBA" data_files: - split: train path: "data/VBA/*.parquet" - config_name: "VBScript" data_files: - split: train path: "data/VBScript/*.parquet" - config_name: "VCL" data_files: - split: train path: "data/VCL/*.parquet" - config_name: "VHDL" data_files: - split: train path: "data/VHDL/*.parquet" - config_name: "Vala" data_files: - split: train path: "data/Vala/*.parquet" - config_name: "Valve_Data_Format" data_files: - split: train path: "data/Valve_Data_Format/*.parquet" - config_name: "Velocity_Template_Language" data_files: - split: train path: "data/Velocity_Template_Language/*.parquet" - config_name: "Verilog" data_files: - split: train path: "data/Verilog/*.parquet" - config_name: "Vim_Help_File" data_files: - split: train path: "data/Vim_Help_File/*.parquet" - config_name: "Vim_Script" data_files: - split: train path: "data/Vim_Script/*.parquet" - config_name: "Vim_Snippet" data_files: - split: train path: "data/Vim_Snippet/*.parquet" - config_name: "Visual_Basic_.NET" data_files: - split: train path: "data/Visual_Basic_.NET/*.parquet" - config_name: "Volt" data_files: - split: train path: "data/Volt/*.parquet" - config_name: "Vue" data_files: - split: train path: "data/Vue/*.parquet" - config_name: "Vyper" data_files: - split: train path: "data/Vyper/*.parquet" - config_name: "Wavefront_Material" data_files: - split: train path: "data/Wavefront_Material/*.parquet" - config_name: "Wavefront_Object" data_files: - split: train path: "data/Wavefront_Object/*.parquet" - config_name: "WebAssembly" data_files: - split: train path: "data/WebAssembly/*.parquet" - config_name: "WebIDL" data_files: - split: train path: "data/WebIDL/*.parquet" - config_name: "WebVTT" data_files: - split: train path: "data/WebVTT/*.parquet" - config_name: "Web_Ontology_Language" data_files: - split: train path: "data/Web_Ontology_Language/*.parquet" - config_name: "Wget_Config" data_files: - split: train path: "data/Wget_Config/*.parquet" - config_name: "Whiley" data_files: - split: train path: "data/Whiley/*.parquet" - config_name: "Wikitext" data_files: - split: train path: "data/Wikitext/*.parquet" - config_name: "Win32_Message_File" data_files: - split: train path: "data/Win32_Message_File/*.parquet" - config_name: "Windows_Registry_Entries" data_files: - split: train path: "data/Windows_Registry_Entries/*.parquet" - config_name: "Witcher_Script" data_files: - split: train path: "data/Witcher_Script/*.parquet" - config_name: "Wollok" data_files: - split: train path: "data/Wollok/*.parquet" - config_name: "World_of_Warcraft_Addon_Data" data_files: - split: train path: "data/World_of_Warcraft_Addon_Data/*.parquet" - config_name: "Wren" data_files: - split: train path: "data/Wren/*.parquet" - config_name: "X10" data_files: - split: train path: "data/X10/*.parquet" - config_name: "XC" data_files: - split: train path: "data/XC/*.parquet" - config_name: "XCompose" data_files: - split: train path: "data/XCompose/*.parquet" - config_name: "XML" data_files: - split: train path: "data/XML/*.parquet" - config_name: "XML_Property_List" data_files: - split: train path: "data/XML_Property_List/*.parquet" - config_name: "XPages" data_files: - split: train path: "data/XPages/*.parquet" - config_name: "XProc" data_files: - split: train path: "data/XProc/*.parquet" - config_name: "XQuery" data_files: - split: train path: "data/XQuery/*.parquet" - config_name: "XS" data_files: - split: train path: "data/XS/*.parquet" - config_name: "XSLT" data_files: - split: train path: "data/XSLT/*.parquet" - config_name: "X_BitMap" data_files: - split: train path: "data/X_BitMap/*.parquet" - config_name: "X_Font_Directory_Index" data_files: - split: train path: "data/X_Font_Directory_Index/*.parquet" - config_name: "X_PixMap" data_files: - split: train path: "data/X_PixMap/*.parquet" - config_name: "Xojo" data_files: - split: train path: "data/Xojo/*.parquet" - config_name: "Xonsh" data_files: - split: train path: "data/Xonsh/*.parquet" - config_name: "Xtend" data_files: - split: train path: "data/Xtend/*.parquet" - config_name: "YAML" data_files: - split: train path: "data/YAML/*.parquet" - config_name: "YANG" data_files: - split: train path: "data/YANG/*.parquet" - config_name: "YARA" data_files: - split: train path: "data/YARA/*.parquet" - config_name: "YASnippet" data_files: - split: train path: "data/YASnippet/*.parquet" - config_name: "Yacc" data_files: - split: train path: "data/Yacc/*.parquet" - config_name: "Yul" data_files: - split: train path: "data/Yul/*.parquet" - config_name: "ZAP" data_files: - split: train path: "data/ZAP/*.parquet" - config_name: "ZIL" data_files: - split: train path: "data/ZIL/*.parquet" - config_name: "Zeek" data_files: - split: train path: "data/Zeek/*.parquet" - config_name: "ZenScript" data_files: - split: train path: "data/ZenScript/*.parquet" - config_name: "Zephir" data_files: - split: train path: "data/Zephir/*.parquet" - config_name: "Zig" data_files: - split: train path: "data/Zig/*.parquet" - config_name: "Zimpl" data_files: - split: train path: "data/Zimpl/*.parquet" - config_name: "cURL_Config" data_files: - split: train path: "data/cURL_Config/*.parquet" - config_name: "desktop" data_files: - split: train path: "data/desktop/*.parquet" - config_name: "dircolors" data_files: - split: train path: "data/dircolors/*.parquet" - config_name: "eC" data_files: - split: train path: "data/eC/*.parquet" - config_name: "edn" data_files: - split: train path: "data/edn/*.parquet" - config_name: "fish" data_files: - split: train path: "data/fish/*.parquet" - config_name: "hoon" data_files: - split: train path: "data/hoon/*.parquet" - config_name: "jq" data_files: - split: train path: "data/jq/*.parquet" - config_name: "kvlang" data_files: - split: train path: "data/kvlang/*.parquet" - config_name: "mIRC_Script" data_files: - split: train path: "data/mIRC_Script/*.parquet" - config_name: "mcfunction" data_files: - split: train path: "data/mcfunction/*.parquet" - config_name: "mupad" data_files: - split: train path: "data/mupad/*.parquet" - config_name: "nanorc" data_files: - split: train path: "data/nanorc/*.parquet" - config_name: "nesC" data_files: - split: train path: "data/nesC/*.parquet" - config_name: "ooc" data_files: - split: train path: "data/ooc/*.parquet" - config_name: "q" data_files: - split: train path: "data/q/*.parquet" - config_name: "reStructuredText" data_files: - split: train path: "data/reStructuredText/*.parquet" - config_name: "robots.txt" data_files: - split: train path: "data/robots.txt/*.parquet" - config_name: "sed" data_files: - split: train path: "data/sed/*.parquet" - config_name: "wdl" data_files: - split: train path: "data/wdl/*.parquet" - config_name: "wisp" data_files: - split: train path: "data/wisp/*.parquet" - config_name: "xBase" data_files: - split: train path: "data/xBase/*.parquet" --- # The Stack v2 <center> <img src="https://huggingface.co./datasets/bigcode/admin_private/resolve/main/thestackv2_banner.png" alt="Stackv2" width="900" height="600"> </center> ## Dataset Description - **Homepage:** https://www.bigcode-project.org/ - **Repository:** https://github.com/bigcode-project - **Paper:** [Link](https://huggingface.co./papers/2402.19173) - **Point of Contact:** [email protected] The dataset consists of 4 versions: - [`bigcode/the-stack-v2`](https://huggingface.co./datasets/bigcode/the-stack-v2): the full "The Stack v2" dataset **<-- you are here** - [`bigcode/the-stack-v2-dedup`](https://huggingface.co./datasets/bigcode/the-stack-v2-dedup): based on the `bigcode/the-stack-v2` but further near-deduplicated - [`bigcode/the-stack-v2-train-full-ids`](https://huggingface.co./datasets/bigcode/the-stack-v2-train-full-ids): based on the `bigcode/the-stack-v2-dedup` dataset but further filtered with heuristics and spanning 600+ programming languages. The data is grouped into repositories. - [`bigcode/the-stack-v2-train-smol-ids`](https://huggingface.co./datasets/bigcode/the-stack-v2-train-smol-ids): based on the `bigcode/the-stack-v2-dedup` dataset but further filtered with heuristics and spanning 17 programming languages. The data is grouped into repositories. **These datasets only contain the SWHIDs to download the code files and not the content of the files itself. See examples below to see how to download content. We are working on making the training datasets available in the coming weeks.** The Stack v2 is significantly larger than v1: ||The Stack v1|The Stack v2| |-|-|-| | full | 6.4TB | 67.5TB | | dedup | 2.9TB | 32.1TB | | train (full) | ~200B tokens | ~900B tokens | ### Changelog |Release|Description| |-|-| | v2.1.0 | Removed repositories that opted out before 2024-04-09. Removed unreachable/private repositories (according to SWH) | | v2.0.1 | Removed repositories that opted out before 2023-10-20. StarCoder2 was trained on this version | | v2.0 | Initial release of the Stack v2 | ### Dataset Summary The Stack v2 contains over 3B files in 600+ programming and markup languages. The dataset was created as part of the [BigCode Project](https://www.bigcode-project.org/), an open scientific collaboration working on the responsible development of Large Language Models for Code (Code LLMs). The Stack serves as a pre-training dataset for Code LLMs, i.e., code-generating AI systems which enable the synthesis of programs from natural language descriptions as well as other from code snippets. This dataset is derived from the Software Heritage archive, the largest public archive of software source code and accompanying development history. Software Heritage is an open, non profit initiative to collect, preserve, and share the source code of all publicly available software, launched by Inria, in partnership with UNESCO. We acknowledge Software Heritage for providing access to this invaluable resource. For more details, visit the [Software Heritage website](https://www.softwareheritage.org). ### Languages The dataset contains 658 languages. The full list can be found in the [language stats table](https://huggingface.co./datasets/bigcode/the-stack-v2/blob/main/language_stats.csv). ### How to use it ```python from datasets import load_dataset # full dataset (file IDs only) ds = load_dataset("bigcode/the-stack-v2", split="train") # specific language (e.g. Dockerfiles) ds = load_dataset("bigcode/the-stack-v2", "Dockerfile", split="train") # dataset streaming (will only download the data as needed) ds = load_dataset("bigcode/the-stack-v2", streaming=True, split="train") for sample in iter(ds): print(sample) ``` #### Downloading the file contents The file contents are stored in the Software Heritage S3 bucket to ensure data compliance. Downloading data in bulk requires an agreement with SoftwareHeritage and INRIA as stated in the dataset agreement. Make sure to configure your environment with your [AWS credentials](https://awscli.amazonaws.com/v2/documentation/api/latest/reference/configure/index.html#examples). ```bash pip install smart_open[s3] ``` ```python import os import boto3 from smart_open import open from datasets import load_dataset session = boto3.Session( aws_access_key_id=os.environ["AWS_ACCESS_KEY_ID"], aws_secret_access_key=os.environ["AWS_SECRET_ACCESS_KEY"]) s3 = session.client("s3") def download_contents(blob_id, src_encoding): s3_url = f"s3://softwareheritage/content/{blob_id}" with open(s3_url, "rb", compression=".gz", transport_params={"client": s3}) as fin: content = fin.read().decode(src_encoding) return {"content": content} ds = load_dataset("bigcode/the-stack-v2", split="train", streaming=True) ds = ds.map(lambda row: download_contents(row["blob_id"], row["src_encoding"])) for row in ds: print(row["content"]) break ``` ## Dataset Structure ### Data Fields * `blob_id` (`string`): Software Heritage (SWH) ID of the file on AWS S3. * `directory_id` (`string`): SWH ID of the root directory of the repository. * `path` (`string`): The file path within the repository. * `content_id` (`string`): SWH content ID. * `detected_licenses` (`string[]`): List of licenses (SPDX) detected by ScanCode. * `license_type` (`string`): Inferred license type (`permissive` or `no_license`). * `repo_name` (`string`): Repository name on GitHub. * `snapshot_id` (`string`): SWH snapshot ID. * `revision_id` (`string`): SWH revision (commit) ID. * `branch_name` (`string`): Repository branch name. * `visit_date` (`timestamp[ns]`): SWH crawl (snapshot) timestamp. * `revision_date` (`timestamp[ns]`): SWH revision (commit) timestamp. * `committer_date` (`timestamp[ns]`): SWH revision (commit) timestamp reported by the committer. * `github_id` (`int64`): GitHub identifier for the repository. * `star_events_count` (`int64`): number of stars calculated from GHArchive events. * `fork_events_count` (`int64`): number of forks calculated from GHArchive events. * `gha_license_id` (`string`): GHArchive SPDX license identifier, `None` if the repo is missing. * `gha_event_created_at` (`timestamp[ns]`): Timestamp of the latest event on GHArchive for this repository. * `gha_created_at` (`timestamp[ns]`): Timestamp of repository creation on GitHub, `None` if the repo is missing. * `gha_language` (`string`): Repository's primary programming language on GitHub, `None` if the repo is missing. * `src_encoding` (`string`): Original encoding of the file content befre converting to UTF-8. * `language` (`string`): Programming language of the file, detected by `go-enry / linguist`. * `is_vendor` (`bool`): Indicator of vendor file (external library), detected by `go-enry`. * `is_generated` (`bool`): Indicator of generated file (external library), detected by `go-enry`. * `length_bytes` (`int64`): Length of the file content in UTF-8 bytes. * `extension` (`string`): File extension. ### Data Splits The dataset has no splits and all data is loaded as train split by default. If you want to setup a custom train-test split beware that dataset contains a lot of near-duplicates which can cause leakage into the test split. ## Dataset Creation For more information on the dataset creation pipeline please refer to the [technical report](https://huggingface.co./papers/2402.19173). ### Curation Rationale One of the challenges faced by researchers working on code LLMs is the lack of openness and transparency around the development of these systems. Most prior works described the high-level data collection process but did not release the training data. It is therefore difficult for other researchers to fully reproduce these models and understand what kind of pre-training data leads to high-performing code LLMs. By releasing an open large-scale code dataset we hope to make training of code LLMs more reproducible. ### Source Data #### Data Collection 3.28B unique files belonging to 104.2M github repositories were collected by traversing the Software Heritage [2023-09-06](https://docs.softwareheritage.org/devel/swh-dataset/graph/dataset.html#graph-dataset-2023-09-06) graph dataset. Additional repository-level metadata was collected from [GitHub Archive](https://www.gharchive.org/) data up to 2023-09-14. The total uncompressed size of all files is 67.53TB. Near-deduplication was implemented in the pre-processing pipeline on top of exact deduplication. Roughly 40% of permissively licensed files were (near-)duplicates. The following are not stored: * Files that cannot contribute to training code: binary, empty, could not be decoded * Files larger than 10MB **Training Datasets**: For the training datasets the programming languages were filtered further to 17 and 600+ for the `the-stack-v2-smol-ids` and `the-stack-v2-full-ids` dataset, respecively. In addition, heuristics were applied to further increase the quality of the dataset. The code files are also grouped into repositories to allow to pretrain with full repository context. For more details see the [technical report](https://drive.google.com/file/d/17iGn3c-sYNiLyRSY-A85QOzgzGnGiVI3/view?usp=sharing). ##### License detection We extract repository-level license information from [GH Archive](https://www.gharchive.org/) for all repositories with matching names in the SWH dataset. When the repo-level license is not available, i.e., for 96.93\% of repositories, we use the [ScanCode Toolkit](https://github.com/nexB/scancode-toolkit) to detect file-level licenses as follows: * Find all filenames that could contain a license (e.g., LICENSE, MIT.txt, Apache2.0) or contain a reference to the license (e.g., README.md, GUIDELINES); * Apply ScanCode's license detection to the matching files and gather the SPDX IDs of the detected licenses; * Propagate the detected licenses to all files that have the same base path within the repository as the license file. The licenses we consider permissive are listed [here](https://huggingface.co./datasets/bigcode/the-stack-v2/blob/main/license_stats.csv). This list was compiled from the licenses approved by the [Blue Oak Council](https://blueoakcouncil.org/list), as well as licenses categorized as "Permissive" or "Public Domain" by [ScanCode](https://scancode-licensedb.aboutcode.org/). #### Who are the source language producers? The source (code) language producers are users of GitHub that created unique repository names up until 2023-09-06 (cutoff date). ### Personal and Sensitive Information The released dataset may contain sensitive information such as emails, IP addresses, and API/ssh keys that have previously been published to public repositories on GitHub. Deduplication has helped to reduce the amount of sensitive data that may exist. In the event that the dataset contains personal information, researchers should only use public, non-personal information in support of conducting and publishing their [open-access](https://en.wikipedia.org/wiki/Open_access) research. Personal information should not be used for spamming purposes, including sending unsolicited emails or selling of personal information. Complaints, removal requests, and "do not contact" requests can be sent to [email protected]. ### Opting out of The Stack v2 We are giving developers the ability to have their code removed from the dataset upon request. The process for submitting and enacting removal requests will keep evolving throughout the project as we receive feedback and build up more data governance tools. You can check if your code is in The Stack v2 with the following ["Am I In The Stack?" Space](https://huggingface.co./spaces/bigcode/in-the-stack). If you'd like to have your data removed from the dataset follow the [instructions on GitHub](https://github.com/bigcode-project/opt-out-v2). ## Considerations for Using the Data ### Social Impact of Dataset The Stack v2 is an output of the BigCode Project. BigCode aims to be responsible by design and by default. The project is conducted in the spirit of Open Science, focused on the responsible development of LLMs for code. With the release of The Stack v2, we aim to increase access, reproducibility, and transparency of code LLMs in the research community. Work to de-risk and improve on the implementation of ethical best practices of code LLMs is conducted in various BigCode working groups. The Legal, Ethics, and Governance working group has explored topics such as licensing (including copyleft and the intended use of permissively licensed code), attribution of generated code to original code, rights to restrict processing, the inclusion of Personally Identifiable Information (PII), and risks of malicious code, among other topics. This work is ongoing as of October 25th, 2022. We expect code LLMs to enable people from diverse backgrounds to write higher quality code and develop low-code applications. Mission-critical software could become easier to maintain as professional developers are guided by code-generating systems on how to write more robust and efficient code. While the social impact is intended to be positive, the increased accessibility of code LLMs comes with certain risks such as over-reliance on the generated code and long-term effects on the software development job market. A broader impact analysis relating to Code LLMs can be found in section 7 of this [paper](https://arxiv.org/abs/2107.03374). An in-depth risk assessments for Code LLMs can be found in section 4 of this [paper](https://arxiv.org/abs/2207.14157). ### Discussion of Biases The code collected from GitHub does not contain demographic information or proxy information about the demographics. However, it is not without risks, as the comments within the code may contain harmful or offensive language, which could be learned by the models. Widely adopted programming languages like C and Javascript are overrepresented compared to niche programming languages like Julia and Scala. Some programming languages such as SQL, Batchfile, TypeScript are less likely to be permissively licensed (4% vs the average 10%). This may result in a biased representation of those languages. Permissively licensed files also tend to be longer. The majority of natural language present in code from GitHub is English. ### Other Known Limitations One of the current limitations of The Stack v2 is that scraped HTML for websites may not be compliant with Web Content Accessibility Guidelines ([WCAG](https://www.w3.org/WAI/standards-guidelines/wcag/)). This could have an impact on HTML-generated code that may introduce web accessibility issues. The training dataset could contain malicious code and/or the model could be used to generate malware or ransomware. To the best of our knowledge, all files contained in the dataset are licensed with one of the permissive licenses (see list in [Licensing information](#licensing-information)) or no license. The accuracy of license attribution is limited by the accuracy of GHArchive and ScanCode Toolkit. Any mistakes should be reported to BigCode Project for review and follow-up as needed. ## Additional Information ### Dataset Curators 1. Harm de Vries, ServiceNow Research, [email protected] 2. Leandro von Werra, Hugging Face, [email protected] ### Licensing Information The Stack v2 is a collection of source code from repositories with various licenses. Any use of all or part of the code gathered in The Stack v2 must abide by the terms of the original licenses, including attribution clauses when relevant. We facilitate this by providing provenance information for each data point. The list of [SPDX license identifiers](https://spdx.org/licenses/) included in the dataset can be found [here](https://huggingface.co./datasets/bigcode/the-stack-v2/blob/main/license_stats.csv). ### Citation Information ```bash @misc{lozhkov2024starcoder, title={StarCoder 2 and The Stack v2: The Next Generation}, author={Anton Lozhkov and Raymond Li and Loubna Ben Allal and Federico Cassano and Joel Lamy-Poirier and Nouamane Tazi and Ao Tang and Dmytro Pykhtar and Jiawei Liu and Yuxiang Wei and Tianyang Liu and Max Tian and Denis Kocetkov and Arthur Zucker and Younes Belkada and Zijian Wang and Qian Liu and Dmitry Abulkhanov and Indraneil Paul and Zhuang Li and Wen-Ding Li and Megan Risdal and Jia Li and Jian Zhu and Terry Yue Zhuo and Evgenii Zheltonozhskii and Nii Osae Osae Dade and Wenhao Yu and Lucas Krauß and Naman Jain and Yixuan Su and Xuanli He and Manan Dey and Edoardo Abati and Yekun Chai and Niklas Muennighoff and Xiangru Tang and Muhtasham Oblokulov and Christopher Akiki and Marc Marone and Chenghao Mou and Mayank Mishra and Alex Gu and Binyuan Hui and Tri Dao and Armel Zebaze and Olivier Dehaene and Nicolas Patry and Canwen Xu and Julian McAuley and Han Hu and Torsten Scholak and Sebastien Paquet and Jennifer Robinson and Carolyn Jane Anderson and Nicolas Chapados and Mostofa Patwary and Nima Tajbakhsh and Yacine Jernite and Carlos Muñoz Ferrandis and Lingming Zhang and Sean Hughes and Thomas Wolf and Arjun Guha and Leandro von Werra and Harm de Vries}, year={2024}, eprint={2402.19173}, archivePrefix={arXiv}, primaryClass={cs.SE} } ```

cardiffnlp/tweet_eval

cardiffnlp

--- annotations_creators: - found language_creators: - found language: - en license: - unknown multilinguality: - monolingual size_categories: - 100K<n<1M - 10K<n<100K - 1K<n<10K - n<1K source_datasets: - extended|other-tweet-datasets task_categories: - text-classification task_ids: - intent-classification - multi-class-classification - sentiment-classification paperswithcode_id: tweeteval pretty_name: TweetEval config_names: - emoji - emotion - hate - irony - offensive - sentiment - stance_abortion - stance_atheism - stance_climate - stance_feminist - stance_hillary dataset_info: - config_name: emoji features: - name: text dtype: string - name: label dtype: class_label: names: '0': ❤ '1': 😍 '2': 😂 '3': 💕 '4': 🔥 '5': 😊 '6': 😎 '7': ✨ '8': 💙 '9': 😘 '10': 📷 '11': 🇺🇸 '12': ☀ '13': 💜 '14': 😉 '15': 💯 '16': 😁 '17': 🎄 '18': 📸 '19': 😜 splits: - name: train num_bytes: 3803167 num_examples: 45000 - name: test num_bytes: 4255901 num_examples: 50000 - name: validation num_bytes: 396079 num_examples: 5000 download_size: 5939308 dataset_size: 8455147 - config_name: emotion features: - name: text dtype: string - name: label dtype: class_label: names: '0': anger '1': joy '2': optimism '3': sadness splits: - name: train num_bytes: 338871 num_examples: 3257 - name: test num_bytes: 146645 num_examples: 1421 - name: validation num_bytes: 38273 num_examples: 374 download_size: 367016 dataset_size: 523789 - config_name: hate features: - name: text dtype: string - name: label dtype: class_label: names: '0': non-hate '1': hate splits: - name: train num_bytes: 1223650 num_examples: 9000 - name: test num_bytes: 428934 num_examples: 2970 - name: validation num_bytes: 154144 num_examples: 1000 download_size: 1196346 dataset_size: 1806728 - config_name: irony features: - name: text dtype: string - name: label dtype: class_label: names: '0': non_irony '1': irony splits: - name: train num_bytes: 259187 num_examples: 2862 - name: test num_bytes: 75897 num_examples: 784 - name: validation num_bytes: 86017 num_examples: 955 download_size: 297647 dataset_size: 421101 - config_name: offensive features: - name: text dtype: string - name: label dtype: class_label: names: '0': non-offensive '1': offensive splits: - name: train num_bytes: 1648061 num_examples: 11916 - name: test num_bytes: 135473 num_examples: 860 - name: validation num_bytes: 192417 num_examples: 1324 download_size: 1234528 dataset_size: 1975951 - config_name: sentiment features: - name: text dtype: string - name: label dtype: class_label: names: '0': negative '1': neutral '2': positive splits: - name: train num_bytes: 5425122 num_examples: 45615 - name: test num_bytes: 1279540 num_examples: 12284 - name: validation num_bytes: 239084 num_examples: 2000 download_size: 4849675 dataset_size: 6943746 - config_name: stance_abortion features: - name: text dtype: string - name: label dtype: class_label: names: '0': none '1': against '2': favor splits: - name: train num_bytes: 68694 num_examples: 587 - name: test num_bytes: 33171 num_examples: 280 - name: validation num_bytes: 7657 num_examples: 66 download_size: 73517 dataset_size: 109522 - config_name: stance_atheism features: - name: text dtype: string - name: label dtype: class_label: names: '0': none '1': against '2': favor splits: - name: train num_bytes: 54775 num_examples: 461 - name: test num_bytes: 25716 num_examples: 220 - name: validation num_bytes: 6320 num_examples: 52 download_size: 62265 dataset_size: 86811 - config_name: stance_climate features: - name: text dtype: string - name: label dtype: class_label: names: '0': none '1': against '2': favor splits: - name: train num_bytes: 40249 num_examples: 355 - name: test num_bytes: 19925 num_examples: 169 - name: validation num_bytes: 4801 num_examples: 40 download_size: 48493 dataset_size: 64975 - config_name: stance_feminist features: - name: text dtype: string - name: label dtype: class_label: names: '0': none '1': against '2': favor splits: - name: train num_bytes: 70509 num_examples: 597 - name: test num_bytes: 33305 num_examples: 285 - name: validation num_bytes: 8035 num_examples: 67 download_size: 76345 dataset_size: 111849 - config_name: stance_hillary features: - name: text dtype: string - name: label dtype: class_label: names: '0': none '1': against '2': favor splits: - name: train num_bytes: 69596 num_examples: 620 - name: test num_bytes: 34487 num_examples: 295 - name: validation num_bytes: 7532 num_examples: 69 download_size: 74057 dataset_size: 111615 configs: - config_name: emoji data_files: - split: train path: emoji/train-* - split: test path: emoji/test-* - split: validation path: emoji/validation-* - config_name: emotion data_files: - split: train path: emotion/train-* - split: test path: emotion/test-* - split: validation path: emotion/validation-* - config_name: hate data_files: - split: train path: hate/train-* - split: test path: hate/test-* - split: validation path: hate/validation-* - config_name: irony data_files: - split: train path: irony/train-* - split: test path: irony/test-* - split: validation path: irony/validation-* - config_name: offensive data_files: - split: train path: offensive/train-* - split: test path: offensive/test-* - split: validation path: offensive/validation-* - config_name: sentiment data_files: - split: train path: sentiment/train-* - split: test path: sentiment/test-* - split: validation path: sentiment/validation-* - config_name: stance_abortion data_files: - split: train path: stance_abortion/train-* - split: test path: stance_abortion/test-* - split: validation path: stance_abortion/validation-* - config_name: stance_atheism data_files: - split: train path: stance_atheism/train-* - split: test path: stance_atheism/test-* - split: validation path: stance_atheism/validation-* - config_name: stance_climate data_files: - split: train path: stance_climate/train-* - split: test path: stance_climate/test-* - split: validation path: stance_climate/validation-* - config_name: stance_feminist data_files: - split: train path: stance_feminist/train-* - split: test path: stance_feminist/test-* - split: validation path: stance_feminist/validation-* - config_name: stance_hillary data_files: - split: train path: stance_hillary/train-* - split: test path: stance_hillary/test-* - split: validation path: stance_hillary/validation-* train-eval-index: - config: emotion task: text-classification task_id: multi_class_classification splits: train_split: train eval_split: test col_mapping: text: text label: target metrics: - type: accuracy name: Accuracy - type: f1 name: F1 macro args: average: macro - type: f1 name: F1 micro args: average: micro - type: f1 name: F1 weighted args: average: weighted - type: precision name: Precision macro args: average: macro - type: precision name: Precision micro args: average: micro - type: precision name: Precision weighted args: average: weighted - type: recall name: Recall macro args: average: macro - type: recall name: Recall micro args: average: micro - type: recall name: Recall weighted args: average: weighted - config: hate task: text-classification task_id: binary_classification splits: train_split: train eval_split: test col_mapping: text: text label: target metrics: - type: accuracy name: Accuracy - type: f1 name: F1 binary args: average: binary - type: precision name: Precision macro args: average: macro - type: precision name: Precision micro args: average: micro - type: precision name: Precision weighted args: average: weighted - type: recall name: Recall macro args: average: macro - type: recall name: Recall micro args: average: micro - type: recall name: Recall weighted args: average: weighted - config: irony task: text-classification task_id: binary_classification splits: train_split: train eval_split: test col_mapping: text: text label: target metrics: - type: accuracy name: Accuracy - type: f1 name: F1 binary args: average: binary - type: precision name: Precision macro args: average: macro - type: precision name: Precision micro args: average: micro - type: precision name: Precision weighted args: average: weighted - type: recall name: Recall macro args: average: macro - type: recall name: Recall micro args: average: micro - type: recall name: Recall weighted args: average: weighted - config: offensive task: text-classification task_id: binary_classification splits: train_split: train eval_split: test col_mapping: text: text label: target metrics: - type: accuracy name: Accuracy - type: f1 name: F1 binary args: average: binary - type: precision name: Precision macro args: average: macro - type: precision name: Precision micro args: average: micro - type: precision name: Precision weighted args: average: weighted - type: recall name: Recall macro args: average: macro - type: recall name: Recall micro args: average: micro - type: recall name: Recall weighted args: average: weighted - config: sentiment task: text-classification task_id: multi_class_classification splits: train_split: train eval_split: test col_mapping: text: text label: target metrics: - type: accuracy name: Accuracy - type: f1 name: F1 macro args: average: macro - type: f1 name: F1 micro args: average: micro - type: f1 name: F1 weighted args: average: weighted - type: precision name: Precision macro args: average: macro - type: precision name: Precision micro args: average: micro - type: precision name: Precision weighted args: average: weighted - type: recall name: Recall macro args: average: macro - type: recall name: Recall micro args: average: micro - type: recall name: Recall weighted args: average: weighted --- # Dataset Card for tweet_eval ## Table of Contents - [Dataset Description](#dataset-description) - [Dataset Summary](#dataset-summary) - [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards) - [Languages](#languages) - [Dataset Structure](#dataset-structure) - [Data Instances](#data-instances) - [Data Fields](#data-fields) - [Data Splits](#data-splits) - [Dataset Creation](#dataset-creation) - [Curation Rationale](#curation-rationale) - [Source Data](#source-data) - [Annotations](#annotations) - [Personal and Sensitive Information](#personal-and-sensitive-information) - [Considerations for Using the Data](#considerations-for-using-the-data) - [Social Impact of Dataset](#social-impact-of-dataset) - [Discussion of Biases](#discussion-of-biases) - [Other Known Limitations](#other-known-limitations) - [Additional Information](#additional-information) - [Dataset Curators](#dataset-curators) - [Licensing Information](#licensing-information) - [Citation Information](#citation-information) - [Contributions](#contributions) ## Dataset Description - **Homepage:** [Needs More Information] - **Repository:** [GitHub](https://github.com/cardiffnlp/tweeteval) - **Paper:** [EMNLP Paper](https://arxiv.org/pdf/2010.12421.pdf) - **Leaderboard:** [GitHub Leaderboard](https://github.com/cardiffnlp/tweeteval) - **Point of Contact:** [Needs More Information] ### Dataset Summary TweetEval consists of seven heterogenous tasks in Twitter, all framed as multi-class tweet classification. The tasks include - irony, hate, offensive, stance, emoji, emotion, and sentiment. All tasks have been unified into the same benchmark, with each dataset presented in the same format and with fixed training, validation and test splits. ### Supported Tasks and Leaderboards - `text_classification`: The dataset can be trained using a SentenceClassification model from HuggingFace transformers. ### Languages The text in the dataset is in English, as spoken by Twitter users. ## Dataset Structure ### Data Instances An instance from `emoji` config: ``` {'label': 12, 'text': 'Sunday afternoon walking through Venice in the sun with @user ️ ️ ️ @ Abbot Kinney, Venice'} ``` An instance from `emotion` config: ``` {'label': 2, 'text': "“Worry is a down payment on a problem you may never have'. \xa0Joyce Meyer. #motivation #leadership #worry"} ``` An instance from `hate` config: ``` {'label': 0, 'text': '@user nice new signage. Are you not concerned by Beatlemania -style hysterical crowds crongregating on you…'} ``` An instance from `irony` config: ``` {'label': 1, 'text': 'seeing ppl walking w/ crutches makes me really excited for the next 3 weeks of my life'} ``` An instance from `offensive` config: ``` {'label': 0, 'text': '@user Bono... who cares. Soon people will understand that they gain nothing from following a phony celebrity. Become a Leader of your people instead or help and support your fellow countrymen.'} ``` An instance from `sentiment` config: ``` {'label': 2, 'text': '"QT @user In the original draft of the 7th book, Remus Lupin survived the Battle of Hogwarts. #HappyBirthdayRemusLupin"'} ``` An instance from `stance_abortion` config: ``` {'label': 1, 'text': 'we remind ourselves that love means to be willing to give until it hurts - Mother Teresa'} ``` An instance from `stance_atheism` config: ``` {'label': 1, 'text': '@user Bless Almighty God, Almighty Holy Spirit and the Messiah. #SemST'} ``` An instance from `stance_climate` config: ``` {'label': 0, 'text': 'Why Is The Pope Upset? via @user #UnzippedTruth #PopeFrancis #SemST'} ``` An instance from `stance_feminist` config: ``` {'label': 1, 'text': "@user @user is the UK's answer to @user and @user #GamerGate #SemST"} ``` An instance from `stance_hillary` config: ``` {'label': 1, 'text': "If a man demanded staff to get him an ice tea he'd be called a sexists elitist pig.. Oink oink #Hillary #SemST"} ``` ### Data Fields For `emoji` config: - `text`: a `string` feature containing the tweet. - `label`: an `int` classification label with the following mapping: `0`: ❤ `1`: 😍 `2`: 😂 `3`: 💕 `4`: 🔥 `5`: 😊 `6`: 😎 `7`: ✨ `8`: 💙 `9`: 😘 `10`: 📷 `11`: 🇺🇸 `12`: ☀ `13`: 💜 `14`: 😉 `15`: 💯 `16`: 😁 `17`: 🎄 `18`: 📸 `19`: 😜 For `emotion` config: - `text`: a `string` feature containing the tweet. - `label`: an `int` classification label with the following mapping: `0`: anger `1`: joy `2`: optimism `3`: sadness For `hate` config: - `text`: a `string` feature containing the tweet. - `label`: an `int` classification label with the following mapping: `0`: non-hate `1`: hate For `irony` config: - `text`: a `string` feature containing the tweet. - `label`: an `int` classification label with the following mapping: `0`: non_irony `1`: irony For `offensive` config: - `text`: a `string` feature containing the tweet. - `label`: an `int` classification label with the following mapping: `0`: non-offensive `1`: offensive For `sentiment` config: - `text`: a `string` feature containing the tweet. - `label`: an `int` classification label with the following mapping: `0`: negative `1`: neutral `2`: positive For `stance_abortion` config: - `text`: a `string` feature containing the tweet. - `label`: an `int` classification label with the following mapping: `0`: none `1`: against `2`: favor For `stance_atheism` config: - `text`: a `string` feature containing the tweet. - `label`: an `int` classification label with the following mapping: `0`: none `1`: against `2`: favor For `stance_climate` config: - `text`: a `string` feature containing the tweet. - `label`: an `int` classification label with the following mapping: `0`: none `1`: against `2`: favor For `stance_feminist` config: - `text`: a `string` feature containing the tweet. - `label`: an `int` classification label with the following mapping: `0`: none `1`: against `2`: favor For `stance_hillary` config: - `text`: a `string` feature containing the tweet. - `label`: an `int` classification label with the following mapping: `0`: none `1`: against `2`: favor ### Data Splits | name | train | validation | test | | --------------- | ----- | ---------- | ----- | | emoji | 45000 | 5000 | 50000 | | emotion | 3257 | 374 | 1421 | | hate | 9000 | 1000 | 2970 | | irony | 2862 | 955 | 784 | | offensive | 11916 | 1324 | 860 | | sentiment | 45615 | 2000 | 12284 | | stance_abortion | 587 | 66 | 280 | | stance_atheism | 461 | 52 | 220 | | stance_climate | 355 | 40 | 169 | | stance_feminist | 597 | 67 | 285 | | stance_hillary | 620 | 69 | 295 | ## Dataset Creation ### Curation Rationale [Needs More Information] ### Source Data #### Initial Data Collection and Normalization [Needs More Information] #### Who are the source language producers? [Needs More Information] ### Annotations #### Annotation process [Needs More Information] #### Who are the annotators? [Needs More Information] ### Personal and Sensitive Information [Needs More Information] ## Considerations for Using the Data ### Social Impact of Dataset [Needs More Information] ### Discussion of Biases [Needs More Information] ### Other Known Limitations [Needs More Information] ## Additional Information ### Dataset Curators Francesco Barbieri, Jose Camacho-Collados, Luis Espiinosa-Anke and Leonardo Neves through Cardiff NLP. ### Licensing Information This is not a single dataset, therefore each subset has its own license (the collection itself does not have additional restrictions). All of the datasets require complying with Twitter [Terms Of Service](https://twitter.com/tos) and Twitter API [Terms Of Service](https://developer.twitter.com/en/developer-terms/agreement-and-policy) Additionally the license are: - emoji: Undefined - emotion(EmoInt): Undefined - hate (HateEval): Need permission [here](http://hatespeech.di.unito.it/hateval.html) - irony: Undefined - Offensive: Undefined - Sentiment: [Creative Commons Attribution 3.0 Unported License](https://groups.google.com/g/semevaltweet/c/k5DDcvVb_Vo/m/zEOdECFyBQAJ) - Stance: Undefined ### Citation Information ``` @inproceedings{barbieri2020tweeteval, title={{TweetEval:Unified Benchmark and Comparative Evaluation for Tweet Classification}}, author={Barbieri, Francesco and Camacho-Collados, Jose and Espinosa-Anke, Luis and Neves, Leonardo}, booktitle={Proceedings of Findings of EMNLP}, year={2020} } ``` If you use any of the TweetEval datasets, please cite their original publications: #### Emotion Recognition: ``` @inproceedings{mohammad2018semeval, title={Semeval-2018 task 1: Affect in tweets}, author={Mohammad, Saif and Bravo-Marquez, Felipe and Salameh, Mohammad and Kiritchenko, Svetlana}, booktitle={Proceedings of the 12th international workshop on semantic evaluation}, pages={1--17}, year={2018} } ``` #### Emoji Prediction: ``` @inproceedings{barbieri2018semeval, title={Semeval 2018 task 2: Multilingual emoji prediction}, author={Barbieri, Francesco and Camacho-Collados, Jose and Ronzano, Francesco and Espinosa-Anke, Luis and Ballesteros, Miguel and Basile, Valerio and Patti, Viviana and Saggion, Horacio}, booktitle={Proceedings of The 12th International Workshop on Semantic Evaluation}, pages={24--33}, year={2018} } ``` #### Irony Detection: ``` @inproceedings{van2018semeval, title={Semeval-2018 task 3: Irony detection in english tweets}, author={Van Hee, Cynthia and Lefever, Els and Hoste, V{\'e}ronique}, booktitle={Proceedings of The 12th International Workshop on Semantic Evaluation}, pages={39--50}, year={2018} } ``` #### Hate Speech Detection: ``` @inproceedings{basile-etal-2019-semeval, title = "{S}em{E}val-2019 Task 5: Multilingual Detection of Hate Speech Against Immigrants and Women in {T}witter", author = "Basile, Valerio and Bosco, Cristina and Fersini, Elisabetta and Nozza, Debora and Patti, Viviana and Rangel Pardo, Francisco Manuel and Rosso, Paolo and Sanguinetti, Manuela", booktitle = "Proceedings of the 13th International Workshop on Semantic Evaluation", year = "2019", address = "Minneapolis, Minnesota, USA", publisher = "Association for Computational Linguistics", url = "https://www.aclweb.org/anthology/S19-2007", doi = "10.18653/v1/S19-2007", pages = "54--63" } ``` #### Offensive Language Identification: ``` @inproceedings{zampieri2019semeval, title={SemEval-2019 Task 6: Identifying and Categorizing Offensive Language in Social Media (OffensEval)}, author={Zampieri, Marcos and Malmasi, Shervin and Nakov, Preslav and Rosenthal, Sara and Farra, Noura and Kumar, Ritesh}, booktitle={Proceedings of the 13th International Workshop on Semantic Evaluation}, pages={75--86}, year={2019} } ``` #### Sentiment Analysis: ``` @inproceedings{rosenthal2017semeval, title={SemEval-2017 task 4: Sentiment analysis in Twitter}, author={Rosenthal, Sara and Farra, Noura and Nakov, Preslav}, booktitle={Proceedings of the 11th international workshop on semantic evaluation (SemEval-2017)}, pages={502--518}, year={2017} } ``` #### Stance Detection: ``` @inproceedings{mohammad2016semeval, title={Semeval-2016 task 6: Detecting stance in tweets}, author={Mohammad, Saif and Kiritchenko, Svetlana and Sobhani, Parinaz and Zhu, Xiaodan and Cherry, Colin}, booktitle={Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016)}, pages={31--41}, year={2016} } ``` ### Contributions Thanks to [@gchhablani](https://github.com/gchhablani) and [@abhishekkrthakur](https://github.com/abhishekkrthakur) for adding this dataset.

billion-word-benchmark/lm1b

billion-word-benchmark

--- pretty_name: One Billion Word Language Model Benchmark paperswithcode_id: billion-word-benchmark dataset_info: features: - name: text dtype: string config_name: plain_text splits: - name: train num_bytes: 4238206516 num_examples: 30301028 - name: test num_bytes: 42942045 num_examples: 306688 download_size: 1792209805 dataset_size: 4281148561 task_categories: - text-generation - fill-mask task_ids: - language-modeling - masked-language-modeling language: - en --- # Dataset Card for One Billion Word Language Model Benchmark ## Table of Contents - [Dataset Description](#dataset-description) - [Dataset Summary](#dataset-summary) - [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards) - [Languages](#languages) - [Dataset Structure](#dataset-structure) - [Data Instances](#data-instances) - [Data Fields](#data-fields) - [Data Splits](#data-splits) - [Dataset Creation](#dataset-creation) - [Curation Rationale](#curation-rationale) - [Source Data](#source-data) - [Annotations](#annotations) - [Personal and Sensitive Information](#personal-and-sensitive-information) - [Considerations for Using the Data](#considerations-for-using-the-data) - [Social Impact of Dataset](#social-impact-of-dataset) - [Discussion of Biases](#discussion-of-biases) - [Other Known Limitations](#other-known-limitations) - [Additional Information](#additional-information) - [Dataset Curators](#dataset-curators) - [Licensing Information](#licensing-information) - [Citation Information](#citation-information) - [Contributions](#contributions) ## Dataset Description - **Homepage:** [statmt](http://www.statmt.org/lm-benchmark/) - **Repository:** [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) - **Paper:** [arxiv](https://arxiv.org/pdf/1312.3005v3.pdf) - **Point of Contact:** [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) - **Size of downloaded dataset files:** 1.79 GB - **Size of the generated dataset:** 4.28 GB - **Total amount of disk used:** 6.07 GB ### Dataset Summary A benchmark corpus to be used for measuring progress in statistical language modeling. This has almost one billion words in the training data. ### Supported Tasks and Leaderboards [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Languages [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ## Dataset Structure ### Data Instances #### plain_text - **Size of downloaded dataset files:** 1.79 GB - **Size of the generated dataset:** 4.28 GB - **Total amount of disk used:** 6.07 GB An example of 'train' looks as follows. ``` This example was too long and was cropped: { "text": "While athletes in different professions dealt with doping scandals and other controversies , Woods continued to do what he did best : dominate the field of professional golf and rake in endorsements ." } ``` ### Data Fields The data fields are the same among all splits. #### plain_text - `text`: a `string` feature. ### Data Splits | name | train | test | |------------|----------|--------| | plain_text | 30301028 | 306688 | ## Dataset Creation ### Curation Rationale [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Source Data #### Initial Data Collection and Normalization [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) #### Who are the source language producers? [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Annotations The dataset doesn't contain annotations. ### Personal and Sensitive Information [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ## Considerations for Using the Data ### Social Impact of Dataset [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Discussion of Biases [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Other Known Limitations [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ## Additional Information ### Dataset Curators [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Licensing Information [More Information Needeate this repository accordingly. ### Citation Information ```bibtex @misc{chelba2014billion, title={One Billion Word Benchmark for Measuring Progress in Statistical Language Modeling}, author={Ciprian Chelba and Tomas Mikolov and Mike Schuster and Qi Ge and Thorsten Brants and Phillipp Koehn and Tony Robinson}, year={2014}, eprint={1312.3005}, archivePrefix={arXiv}, primaryClass={cs.CL} } ``` ### Contributions Thanks to [@patrickvonplaten](https://github.com/patrickvonplaten), [@lewtun](https://github.com/lewtun), [@jplu](https://github.com/jplu), [@thomwolf](https://github.com/thomwolf) for adding this dataset.

openslr/librispeech_asr

openslr

--- pretty_name: LibriSpeech annotations_creators: - expert-generated language_creators: - crowdsourced - expert-generated language: - en license: - cc-by-4.0 multilinguality: - monolingual paperswithcode_id: librispeech-1 size_categories: - 100K<n<1M source_datasets: - original task_categories: - automatic-speech-recognition - audio-classification task_ids: - speaker-identification dataset_info: - config_name: clean features: - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: text dtype: string - name: speaker_id dtype: int64 - name: chapter_id dtype: int64 - name: id dtype: string splits: - name: train.100 num_bytes: 6619683041 num_examples: 28539 - name: train.360 num_bytes: 23898214592 num_examples: 104014 - name: validation num_bytes: 359572231 num_examples: 2703 - name: test num_bytes: 367705423 num_examples: 2620 download_size: 30121377654 dataset_size: 31245175287 - config_name: other features: - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: text dtype: string - name: speaker_id dtype: int64 - name: chapter_id dtype: int64 - name: id dtype: string splits: - name: train.500 num_bytes: 31810256902 num_examples: 148688 - name: validation num_bytes: 337283304 num_examples: 2864 - name: test num_bytes: 352396474 num_examples: 2939 download_size: 31236565377 dataset_size: 32499936680 - config_name: all features: - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: text dtype: string - name: speaker_id dtype: int64 - name: chapter_id dtype: int64 - name: id dtype: string splits: - name: train.clean.100 num_bytes: 6627791685 num_examples: 28539 - name: train.clean.360 num_bytes: 23927767570 num_examples: 104014 - name: train.other.500 num_bytes: 31852502880 num_examples: 148688 - name: validation.clean num_bytes: 359505691 num_examples: 2703 - name: validation.other num_bytes: 337213112 num_examples: 2864 - name: test.clean num_bytes: 368449831 num_examples: 2620 - name: test.other num_bytes: 353231518 num_examples: 2939 download_size: 61357943031 dataset_size: 63826462287 --- # Dataset Card for librispeech_asr ## Table of Contents - [Dataset Description](#dataset-description) - [Dataset Summary](#dataset-summary) - [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards) - [Languages](#languages) - [Dataset Structure](#dataset-structure) - [Data Instances](#data-instances) - [Data Fields](#data-fields) - [Data Splits](#data-splits) - [Dataset Creation](#dataset-creation) - [Curation Rationale](#curation-rationale) - [Source Data](#source-data) - [Annotations](#annotations) - [Personal and Sensitive Information](#personal-and-sensitive-information) - [Considerations for Using the Data](#considerations-for-using-the-data) - [Social Impact of Dataset](#social-impact-of-dataset) - [Discussion of Biases](#discussion-of-biases) - [Other Known Limitations](#other-known-limitations) - [Additional Information](#additional-information) - [Dataset Curators](#dataset-curators) - [Licensing Information](#licensing-information) - [Citation Information](#citation-information) - [Contributions](#contributions) ## Dataset Description - **Homepage:** [LibriSpeech ASR corpus](http://www.openslr.org/12) - **Repository:** [Needs More Information] - **Paper:** [LibriSpeech: An ASR Corpus Based On Public Domain Audio Books](https://www.danielpovey.com/files/2015_icassp_librispeech.pdf) - **Leaderboard:** [The 🤗 Speech Bench](https://huggingface.co./spaces/huggingface/hf-speech-bench) - **Point of Contact:** [Daniel Povey](mailto:[email protected]) ### Dataset Summary LibriSpeech is a corpus of approximately 1000 hours of 16kHz read English speech, prepared by Vassil Panayotov with the assistance of Daniel Povey. The data is derived from read audiobooks from the LibriVox project, and has been carefully segmented and aligned. ### Supported Tasks and Leaderboards - `automatic-speech-recognition`, `audio-speaker-identification`: The dataset can be used to train a model for Automatic Speech Recognition (ASR). The model is presented with an audio file and asked to transcribe the audio file to written text. The most common evaluation metric is the word error rate (WER). The task has an active Hugging Face leaderboard which can be found at https://huggingface.co./spaces/huggingface/hf-speech-bench. The leaderboard ranks models uploaded to the Hub based on their WER. An external leaderboard at https://paperswithcode.com/sota/speech-recognition-on-librispeech-test-clean ranks the latest models from research and academia. ### Languages The audio is in English. There are two configurations: `clean` and `other`. The speakers in the corpus were ranked according to the WER of the transcripts of a model trained on a different dataset, and were divided roughly in the middle, with the lower-WER speakers designated as "clean" and the higher WER speakers designated as "other". ## Dataset Structure ### Data Instances A typical data point comprises the path to the audio file, usually called `file` and its transcription, called `text`. Some additional information about the speaker and the passage which contains the transcription is provided. ``` {'chapter_id': 141231, 'file': '/home/patrick/.cache/huggingface/datasets/downloads/extracted/b7ded9969e09942ab65313e691e6fc2e12066192ee8527e21d634aca128afbe2/dev_clean/1272/141231/1272-141231-0000.flac', 'audio': {'path': '/home/patrick/.cache/huggingface/datasets/downloads/extracted/b7ded9969e09942ab65313e691e6fc2e12066192ee8527e21d634aca128afbe2/dev_clean/1272/141231/1272-141231-0000.flac', 'array': array([-0.00048828, -0.00018311, -0.00137329, ..., 0.00079346, 0.00091553, 0.00085449], dtype=float32), 'sampling_rate': 16000}, 'id': '1272-141231-0000', 'speaker_id': 1272, 'text': 'A MAN SAID TO THE UNIVERSE SIR I EXIST'} ``` ### Data Fields - file: A path to the downloaded audio file in .flac format. - audio: A dictionary containing the path to the downloaded audio file, the decoded audio array, and the sampling rate. Note that when accessing the audio column: `dataset[0]["audio"]` the audio file is automatically decoded and resampled to `dataset.features["audio"].sampling_rate`. Decoding and resampling of a large number of audio files might take a significant amount of time. Thus it is important to first query the sample index before the `"audio"` column, *i.e.* `dataset[0]["audio"]` should **always** be preferred over `dataset["audio"][0]`. - text: the transcription of the audio file. - id: unique id of the data sample. - speaker_id: unique id of the speaker. The same speaker id can be found for multiple data samples. - chapter_id: id of the audiobook chapter which includes the transcription. ### Data Splits The size of the corpus makes it impractical, or at least inconvenient for some users, to distribute it as a single large archive. Thus the training portion of the corpus is split into three subsets, with approximate size 100, 360 and 500 hours respectively. A simple automatic procedure was used to select the audio in the first two sets to be, on average, of higher recording quality and with accents closer to US English. An acoustic model was trained on WSJ’s si-84 data subset and was used to recognize the audio in the corpus, using a bigram LM estimated on the text of the respective books. We computed the Word Error Rate (WER) of this automatic transcript relative to our reference transcripts obtained from the book texts. The speakers in the corpus were ranked according to the WER of the WSJ model’s transcripts, and were divided roughly in the middle, with the lower-WER speakers designated as "clean" and the higher-WER speakers designated as "other". For "clean", the data is split into train, validation, and test set. The train set is further split into train.100 and train.360 respectively accounting for 100h and 360h of the training data. For "other", the data is split into train, validation, and test set. The train set contains approximately 500h of recorded speech. | | Train.500 | Train.360 | Train.100 | Valid | Test | | ----- | ------ | ----- | ---- | ---- | ---- | | clean | - | 104014 | 28539 | 2703 | 2620| | other | 148688 | - | - | 2864 | 2939 | ## Dataset Creation ### Curation Rationale [Needs More Information] ### Source Data #### Initial Data Collection and Normalization [Needs More Information] #### Who are the source language producers? [Needs More Information] ### Annotations #### Annotation process [Needs More Information] #### Who are the annotators? [Needs More Information] ### Personal and Sensitive Information The dataset consists of people who have donated their voice online. You agree to not attempt to determine the identity of speakers in this dataset. ## Considerations for Using the Data ### Social Impact of Dataset [More Information Needed] ### Discussion of Biases [More Information Needed] ### Other Known Limitations [Needs More Information] ## Additional Information ### Dataset Curators The dataset was initially created by Vassil Panayotov, Guoguo Chen, Daniel Povey, and Sanjeev Khudanpur. ### Licensing Information [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/) ### Citation Information ``` @inproceedings{panayotov2015librispeech, title={Librispeech: an ASR corpus based on public domain audio books}, author={Panayotov, Vassil and Chen, Guoguo and Povey, Daniel and Khudanpur, Sanjeev}, booktitle={Acoustics, Speech and Signal Processing (ICASSP), 2015 IEEE International Conference on}, pages={5206--5210}, year={2015}, organization={IEEE} } ``` ### Contributions Thanks to [@patrickvonplaten](https://github.com/patrickvonplaten) for adding this dataset.

CohereForAI/Global-MMLU

CohereForAI

--- dataset_info: - config_name: am features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 209505 num_examples: 285 - name: test num_bytes: 12085768 num_examples: 14042 download_size: 10260448 dataset_size: 12295273 - config_name: ar features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 202343 num_examples: 285 - name: test num_bytes: 11621977 num_examples: 14042 download_size: 9817049 dataset_size: 11824320 - config_name: bn features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 301875 num_examples: 285 - name: test num_bytes: 18061158 num_examples: 14042 download_size: 12524784 dataset_size: 18363033 - config_name: cs features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 149807 num_examples: 285 - name: test num_bytes: 8607308 num_examples: 14042 download_size: 8640151 dataset_size: 8757115 - config_name: de features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 162406 num_examples: 285 - name: test num_bytes: 9575360 num_examples: 14042 download_size: 9187953 dataset_size: 9737766 - config_name: el features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 254308 num_examples: 285 - name: test num_bytes: 14502137 num_examples: 14042 download_size: 12288940 dataset_size: 14756445 - config_name: en features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 146364 num_examples: 285 - name: test num_bytes: 8440632 num_examples: 14042 download_size: 7912429 dataset_size: 8586996 - config_name: es features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 160633 num_examples: 285 - name: test num_bytes: 9399724 num_examples: 14042 download_size: 8752720 dataset_size: 9560357 - config_name: fa features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 202609 num_examples: 285 - name: test num_bytes: 11611890 num_examples: 14042 download_size: 9564082 dataset_size: 11814499 - config_name: fil features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 165182 num_examples: 285 - name: test num_bytes: 9510179 num_examples: 14042 download_size: 8564879 dataset_size: 9675361 - config_name: fr features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 166173 num_examples: 285 - name: test num_bytes: 9858873 num_examples: 14042 download_size: 9202595 dataset_size: 10025046 - config_name: ha features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 147406 num_examples: 285 - name: test num_bytes: 8445707 num_examples: 14042 download_size: 7665529 dataset_size: 8593113 - config_name: he features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 178912 num_examples: 285 - name: test num_bytes: 10248592 num_examples: 14042 download_size: 8818618 dataset_size: 10427504 - config_name: hi features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 308254 num_examples: 285 - name: test num_bytes: 17970478 num_examples: 14042 download_size: 12407854 dataset_size: 18278732 - config_name: id features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 154692 num_examples: 285 - name: test num_bytes: 8886643 num_examples: 14042 download_size: 7793365 dataset_size: 9041335 - config_name: ig features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 157376 num_examples: 285 - name: test num_bytes: 9221405 num_examples: 14042 download_size: 7644102 dataset_size: 9378781 - config_name: it features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 157547 num_examples: 285 - name: test num_bytes: 9374481 num_examples: 14042 download_size: 8873034 dataset_size: 9532028 - config_name: ja features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 167646 num_examples: 285 - name: test num_bytes: 9830716 num_examples: 14042 download_size: 8826164 dataset_size: 9998362 - config_name: ko features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 160572 num_examples: 285 - name: test num_bytes: 9454859 num_examples: 14042 download_size: 8640457 dataset_size: 9615431 - config_name: ky features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 235001 num_examples: 285 - name: test num_bytes: 13483934 num_examples: 14042 download_size: 11148813 dataset_size: 13718935 - config_name: lt features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 148917 num_examples: 285 - name: test num_bytes: 8504949 num_examples: 14042 download_size: 8416467 dataset_size: 8653866 - config_name: mg features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 161992 num_examples: 285 - name: test num_bytes: 9337415 num_examples: 14042 download_size: 8011427 dataset_size: 9499407 - config_name: ms features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 152549 num_examples: 285 - name: test num_bytes: 8823844 num_examples: 14042 download_size: 7783581 dataset_size: 8976393 - config_name: ne features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 294790 num_examples: 285 - name: test num_bytes: 16972110 num_examples: 14042 download_size: 11895818 dataset_size: 17266900 - config_name: nl features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 158122 num_examples: 285 - name: test num_bytes: 9099176 num_examples: 14042 download_size: 8565959 dataset_size: 9257298 - config_name: ny features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 151315 num_examples: 285 - name: test num_bytes: 8686819 num_examples: 14042 download_size: 7822699 dataset_size: 8838134 - config_name: pl features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 157290 num_examples: 285 - name: test num_bytes: 8980730 num_examples: 14042 download_size: 8981270 dataset_size: 9138020 - config_name: pt features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 154592 num_examples: 285 - name: test num_bytes: 8983299 num_examples: 14042 download_size: 8517588 dataset_size: 9137891 - config_name: ro features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 158311 num_examples: 285 - name: test num_bytes: 9163189 num_examples: 14042 download_size: 8773232 dataset_size: 9321500 - config_name: ru features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 246059 num_examples: 285 - name: test num_bytes: 14059847 num_examples: 14042 download_size: 11904365 dataset_size: 14305906 - config_name: si features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 297843 num_examples: 285 - name: test num_bytes: 17374939 num_examples: 14042 download_size: 12790098 dataset_size: 17672782 - config_name: sn features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 147355 num_examples: 285 - name: test num_bytes: 8507368 num_examples: 14042 download_size: 7962672 dataset_size: 8654723 - config_name: so features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 156282 num_examples: 285 - name: test num_bytes: 9033243 num_examples: 14042 download_size: 8706693 dataset_size: 9189525 - config_name: sr features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 221580 num_examples: 285 - name: test num_bytes: 12695546 num_examples: 14042 download_size: 10748391 dataset_size: 12917126 - config_name: sv features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 147893 num_examples: 285 - name: test num_bytes: 8549708 num_examples: 14042 download_size: 8181997 dataset_size: 8697601 - config_name: sw features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 147069 num_examples: 285 - name: test num_bytes: 8653210 num_examples: 14042 download_size: 7932986 dataset_size: 8800279 - config_name: te features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 315724 num_examples: 285 - name: test num_bytes: 18170058 num_examples: 14042 download_size: 12631358 dataset_size: 18485782 - config_name: tr features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 153426 num_examples: 285 - name: test num_bytes: 8833244 num_examples: 14042 download_size: 8351339 dataset_size: 8986670 - config_name: uk features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 229888 num_examples: 285 - name: test num_bytes: 13233771 num_examples: 14042 download_size: 11347842 dataset_size: 13463659 - config_name: vi features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 185712 num_examples: 285 - name: test num_bytes: 10604332 num_examples: 14042 download_size: 8971266 dataset_size: 10790044 - config_name: yo features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 153810 num_examples: 285 - name: test num_bytes: 10694916 num_examples: 14042 download_size: 9303668 dataset_size: 10848726 - config_name: zh features: - name: sample_id dtype: string - name: subject dtype: string - name: subject_category dtype: string - name: question dtype: string - name: option_a dtype: string - name: option_b dtype: string - name: option_c dtype: string - name: option_d dtype: string - name: answer dtype: string - name: required_knowledge dtype: string - name: time_sensitive dtype: string - name: reference dtype: string - name: culture dtype: string - name: region dtype: string - name: country dtype: string - name: cultural_sensitivity_label dtype: string - name: is_annotated dtype: bool splits: - name: dev num_bytes: 127577 num_examples: 285 - name: test num_bytes: 7393764 num_examples: 14042 download_size: 7322261 dataset_size: 7521341 configs: - config_name: am data_files: - split: test path: am/test-* - split: dev path: am/dev-* - config_name: ar data_files: - split: test path: ar/test-* - split: dev path: ar/dev-* - config_name: bn data_files: - split: test path: bn/test-* - split: dev path: bn/dev-* - config_name: cs data_files: - split: test path: cs/test-* - split: dev path: cs/dev-* - config_name: de data_files: - split: test path: de/test-* - split: dev path: de/dev-* - config_name: el data_files: - split: test path: el/test-* - split: dev path: el/dev-* - config_name: en data_files: - split: test path: en/test-* - split: dev path: en/dev-* - config_name: es data_files: - split: test path: es/test-* - split: dev path: es/dev-* - config_name: fa data_files: - split: test path: fa/test-* - split: dev path: fa/dev-* - config_name: fil data_files: - split: test path: fil/test-* - split: dev path: fil/dev-* - config_name: fr data_files: - split: test path: fr/test-* - split: dev path: fr/dev-* - config_name: ha data_files: - split: test path: ha/test-* - split: dev path: ha/dev-* - config_name: he data_files: - split: test path: he/test-* - split: dev path: he/dev-* - config_name: hi data_files: - split: test path: hi/test-* - split: dev path: hi/dev-* - config_name: id data_files: - split: test path: id/test-* - split: dev path: id/dev-* - config_name: ig data_files: - split: test path: ig/test-* - split: dev path: ig/dev-* - config_name: it data_files: - split: test path: it/test-* - split: dev path: it/dev-* - config_name: ja data_files: - split: test path: ja/test-* - split: dev path: ja/dev-* - config_name: ko data_files: - split: test path: ko/test-* - split: dev path: ko/dev-* - config_name: ky data_files: - split: test path: ky/test-* - split: dev path: ky/dev-* - config_name: lt data_files: - split: test path: lt/test-* - split: dev path: lt/dev-* - config_name: mg data_files: - split: test path: mg/test-* - split: dev path: mg/dev-* - config_name: ms data_files: - split: test path: ms/test-* - split: dev path: ms/dev-* - config_name: ne data_files: - split: test path: ne/test-* - split: dev path: ne/dev-* - config_name: nl data_files: - split: test path: nl/test-* - split: dev path: nl/dev-* - config_name: ny data_files: - split: test path: ny/test-* - split: dev path: ny/dev-* - config_name: pl data_files: - split: test path: pl/test-* - split: dev path: pl/dev-* - config_name: pt data_files: - split: test path: pt/test-* - split: dev path: pt/dev-* - config_name: ro data_files: - split: test path: ro/test-* - split: dev path: ro/dev-* - config_name: ru data_files: - split: test path: ru/test-* - split: dev path: ru/dev-* - config_name: si data_files: - split: test path: si/test-* - split: dev path: si/dev-* - config_name: sn data_files: - split: test path: sn/test-* - split: dev path: sn/dev-* - config_name: so data_files: - split: test path: so/test-* - split: dev path: so/dev-* - config_name: sr data_files: - split: test path: sr/test-* - split: dev path: sr/dev-* - config_name: sv data_files: - split: test path: sv/test-* - split: dev path: sv/dev-* - config_name: sw data_files: - split: test path: sw/test-* - split: dev path: sw/dev-* - config_name: te data_files: - split: test path: te/test-* - split: dev path: te/dev-* - config_name: tr data_files: - split: test path: tr/test-* - split: dev path: tr/dev-* - config_name: uk data_files: - split: test path: uk/test-* - split: dev path: uk/dev-* - config_name: vi data_files: - split: test path: vi/test-* - split: dev path: vi/dev-* - config_name: yo data_files: - split: test path: yo/test-* - split: dev path: yo/dev-* - config_name: zh data_files: - split: test path: zh/test-* - split: dev path: zh/dev-* tags: - argilla language: - en - ar - bn - es - fr - hi - ru - de - id - it - ja - ko - pt - zh - yo - nl - ro - uk - vi - tr - pl - fa - cs - he - el - ms - fil - te - si - ne - ky - sv - lt - sr - mg - so - ha - am - sn - ig - ny - sw ---  # Dataset Summary [Global-MMLU](https://arxiv.org/abs/2412.03304) 🌍 is a multilingual evaluation set spanning 42 languages, including English. This dataset combines machine translations for [MMLU](https://huggingface.co./datasets/cais/mmlu) questions along with professional translations and crowd-sourced post-edits. It also includes cultural sensitivity annotations for a subset of the questions (2850 questions per language) and classifies them as *Culturally Sensitive* (CS) 🗽 or *Culturally Agnostic* (CA) ⚖️. These annotations were collected as part of an open science initiative led by Cohere For AI in collaboration with many external collaborators from both industry and academia. - **Curated by:** Professional annotators and contributors of [Cohere For AI Community](https://cohere.com/research). - **Language(s):** 42 languages. - **License:** [Apache 2.0](https://opensource.org/license/apache-2-0) **Note:** We also provide a "lite" version of Global MMLU called ["Global-MMLU-Lite"](https://huggingface.co./datasets/CohereForAI/Global-MMLU-Lite). This datatset is more balanced containing 200 samples each for CA and CS subsets for each language. And provides coverage for 15 languages with human translations. ### **Global-MMLU Dataset Family:** | Name | Explanation | |------|--------------| | [Global-MMLU](https://huggingface.co./datasets/CohereForAI/Global-MMLU) | Full Global-MMLU set with translations for all 14K samples including CS and CA subsets| | [Global-MMLU-Lite](https://huggingface.co./datasets/CohereForAI/Global-MMLU-Lite) | Lite version of Global-MMLU with human translated samples in 15 languages and containing 200 samples each for CS and CA subsets per language.| ## Load with Datasets To load this dataset with `datasets`, you'll first need to install it using `pip install datasets` and then use the following code: ```python from datasets import load_dataset # load HF dataset global_mmlu = load_dataset("CohereForAI/Global-MMLU", 'en') # can also be used as pandas dataframe global_mmlu.set_format("pandas") global_mmlu_test = global_mmlu['test'][:] global_mmlu_dev = global_mmlu['dev'][:] ``` <details> <summary> additional details </summary> The columns corresponding to annotations collected from our cultural bias study (i.e. 'required_knowledge', 'time_sensitive', 'reference', 'culture', 'region', 'country') contain a list of values representing annotations from different annotators. However, to avoid conversion issues to HF dataset, these columns are provided as string in the final dataset. You can convert these columns back to list of values for easier manipulation as follows: ```python import ast # convert string values to list global_mmlu_df['required_knowledge'] = global_mmlu_df['required_knowledge'].apply(lamda x: ast.literal_eval(x)) ``` </details> <br> ## Data Fields The data fields are the same among all splits. Brief description of each field is provided below. <details> <summary> data field description </summary> - `sample_id`: A unique identifier for the question. - `subject`: The main topic the question falls under. - `subject_category`: The high-level category the subject falls under i.e. STEM/Humanities/Social Sciences/Medical/Business/Other. - `question`: translated question from MMLU - `option_a`: one of the possible option choices - `option_b`: one of the possible option choices - `option_c`: one of the possible option choices - `option_d`: one of the possible option choices - `answer': the correct answer (A/B/C/D) - `required_knowledge`: annotator votes for knowledge needed to answer the question correctly. Possible values include: "cultural", "regional", "dialect" or "none" - `time_sensitive`: annotator votes indicating if the question's answer is time-dependent. Possible values include: Yes/No - `reference`: annotations for which part of the question contains cultural/regional/dialect references. The different items in the list are annotations from different annotators. - `culture`: annotations for which culture does the question belong to. The different items in the list correspond to annotations from different annotators. - `region`: Geographic region the question is relevant to. Each item in the list correspond to annotations from different annotators. - `country`: Specific country the question pertains to. Each item in the list correspond to annotations from different annotators. - `cultural_sensitivity_label`: Label to indicate if question is culturally sensitive (CS) or culturally agnostic (CA) based on annotator votes. - `is_annotated`: True/False flag to indicate if sample contains any annotations from our cultural bias study. </details> <br> ## Data Splits The following are the splits of the data: | Split | No. of instances | Language Coverage | |-------|------------------|-------------------| | test | 589,764 | 42 | | dev | 11,970 | 42 | ## Data Instances An example from `test` set looks as follows: ```json {'sample_id': 'world_religions/test/170' 'subject': 'world_religions', 'subject_category': 'Humanities', 'question': ' The numen of Augustus referred to which of the following characteristics?', 'option_a': 'Divine power', 'option_b': 'Sexual virility', 'option_c': 'Military acumen', 'option_d': 'Philosophical intellect', 'answer': 'A', 'required_knowledge': "['none', 'cultural', 'cultural', 'cultural']", 'time_sensitive': "['No', 'No', 'No', 'No']", 'reference': "['-', '-', {'end': 22, 'label': 'Cultural', 'score': None, 'start': 5}, {'end': 22, 'label': 'Cultural', 'score': None, 'start': 5}]", 'culture': "['Western Culture', 'Western Culture', 'Western Culture']", 'region': "['North America', 'Europe']", 'country': "['Italy']", 'cultural_sensitivity_label': 'CS', 'is_annotated': True, } ``` ## Statistics ### Annotation Types The following is the breakdown of CS🗽, CA⚖️ and MA📝 samples in the final dataset. | Type of Annotation | Instances per language | No. of languages | Total instances |--------------------|------------------------|------------------|----------------| | Culturally Sensitive 🗽 | 792 | 42 | 33,264 | | Culturally Agnostic ⚖️ | 2058 |42 | 86,436 | | MMLU Annotated 📝| 2850 |42 | 119,700 | ### Languages The dataset covers 42 languages: 20 high-resource, 9 mid-resource, and 13 low-resource languages. The following is details about the languages included in the dataset. <details> <summary> Languages Info </summary> | ISO Code | Language | Resources | |----------|----------|-----------| | `am` | Amharic | Low | | `ar` | Arabic (Standard)| High | | `bn` | Bengali | Mid | | `de` | German | High | | `el` | Greek | Mid | | `en` | English | High | | `fil` | Filipino | Mid | | `fr` | French | High | | `ha` | Hausa | Low | | `he` | Hebrew | Mid | | `hi` | Hindi | High | | `ig` | Igbo | Low | | `id` | Indonesian | Mid | | `it` | Italian | High | | `ja` | Japanese | High | | `ky` | Kyrgyz | Low | | `ko` | Korean | Mid | | `lt` | Lithuanian | Mid | | `mg` | Malagasy | Low | | `ms` | Malay | Mid | | `ne` | Nepali | Low | | `nl` | Dutch | High | | `ny` | Chichewa | Low | | `fa` | Persian | High | | `pl` | Polish | High | | `pt` | Portuguese | High | | `ru` | Russian | High | | `si` | Sinhala | Low | | `sn` | Shona | Low | | `so` | Somali | Low | | `es` | Spanish | High | | `sr` | Serbian | High | | `sw` | Swahili | Low | | `sw` | Swedish | High | | `te` | Telugu | Low | | `tr` | Turkish | High | | `uk` | Ukrainian | Mid | | `vi` | Vietnamese | High | | `yo` | Yorùbá | Low | | `zh` | Chinese (Simplified) | High | </details> <br> # Known Limitations A brief overview of limitations of this dataset is provided below. <details> <summary> show limitations </summary> - **Language and dialect coverage:** Global-MMLU focusses on 42 languages. However, this is still only a tiny fraction of the world’s linguistic diversity. Future work is needed to continue to improve evaluations beyond these 42 languages and take into account how technology serves different dialects. - **Uneven distribution of contributions:** The dataset contains translation post-edits from community volunteers, with a 'long tail' of volunteers making only one or two contributions. Similarly, there is a huge gap between languages with the highest number of contributions and ones with the lowest number of contributions. - **Toxic or offensive speech:** Our annotation process did not focus on flagging for toxic,harmful, or offensive speech, so it is possible that Global-MMLU contains some data that could be considered harmful. We believe this is of relatively low risk because of the nature of the original MMLU and the focus on examination material. - **Region Category Assignment:** For the annotation of geographically sensitive questions, we classified regions into six geographic regions (Africa, Asia, Europe, North America, Oceania,and South America). However, based upon discussions we would going forward recommend switching to the taxonomy proposed by the World Bank which is more granular and includes separate designations for Central America and Sub-Saharan Africa. - **Identifying cultural sensitivity does not guarantee cultural inclusion:** While Global-MMLU highlights important limitations in current datasets by identifying gaps in non-Western cultural representation. Future work must prioritize the integration of diverse culturally grounded knowledge to achieve true inclusivity and fairness in multilingual AI evaluation. </details> <br> # Additional Information ## Provenance - **Methods Used:** Professional annotations as well as crowd-sourced through volunteer annotations. - **Methodology Details:** We collected cultural bias annotations as well as post-edits of translations for different mmlu questions. - [Cultural Sensitivity Annotation Platform](https://huggingface.co./spaces/CohereForAI/MMLU-evaluation) - [Translation Quality Annotation Platform](https://huggingface.co./spaces/CohereForAI/review-mmlu-translations) - Dates of Collection: May 2024 - Aug 2024 ## Dataset Version and Maintenance - **Maintenance Status:** Actively Maintained - **Version Details:** - *Current version:* 1.0 - *Last Update:* 12/2024 - *First Release:* 12/2024 ## Authorship - **Publishing Organization:** [Cohere For AI](https://cohere.com/research) - **Industry Type:** Not-for-profit - Tech ## Licensing Information This dataset can be used for any purpose, under the terms of the [Apache 2.0](https://opensource.org/license/apache-2-0) License. ## Additional Details For any additional details, please check our paper, [Global MMLU: Understanding and Addressing Cultural and Linguistic Biases in Multilingual Evaluation](https://arxiv.org/abs/2412.03304). ## Citation Information ```bibtex @misc{singh2024globalmmluunderstandingaddressing, title={Global MMLU: Understanding and Addressing Cultural and Linguistic Biases in Multilingual Evaluation}, author={Shivalika Singh and Angelika Romanou and Clémentine Fourrier and David I. Adelani and Jian Gang Ngui and Daniel Vila-Suero and Peerat Limkonchotiwat and Kelly Marchisio and Wei Qi Leong and Yosephine Susanto and Raymond Ng and Shayne Longpre and Wei-Yin Ko and Madeline Smith and Antoine Bosselut and Alice Oh and Andre F. T. Martins and Leshem Choshen and Daphne Ippolito and Enzo Ferrante and Marzieh Fadaee and Beyza Ermis and Sara Hooker}, year={2024}, eprint={2412.03304}, archivePrefix={arXiv}, primaryClass={cs.CL}, url={https://arxiv.org/abs/2412.03304}, } ```

Tuxifan/UbuntuIRC

Tuxifan

--- license: cc0-1.0 task_categories: - text-generation pretty_name: Ubuntu IRC channels --- Completely uncurated collection of IRC logs from the Ubuntu IRC channels

mteb/emotion

mteb

--- language: - en --- ** Attention: There appears an overlap in train / test. I trained a model on the train set and achieved 100% acc on test set. With the original emotion dataset this is not the case (92.4% acc)**

laion/strategic_game_chess

laion

--- tags: - game pretty_name: The Chess Dataset license: cc-by-4.0 --- # Chess > Recent advancements in artificial intelligence (AI) underscore the progress of reasoning and planning shown by recent generalist machine learning (ML) models. The progress can be boosted by datasets that can further boost these generic capabilities when used for training foundation models of various kind. This research initiative has generated extensive synthetic datasets from complex games — chess, Rubik's Cube, and mazes — to study facilitation and the advancement of these critical generic skills in AI models. This dataset contains 3.2 billion games, equating to approximately 608 billion individual moves. it is generated through self-play by Stockfish engine using Fugaku and we add initial moves to expand its diversity. Each game has three columns: 'Moves', 'Termination' and 'Result', - 'Move': recorded chess moves of the whole game. - 'Termination': include CHECKMATE, INSUFFICIENT_MATERIAL, ... etc. - Please check this for detail information https://python-chess.readthedocs.io/en/latest/core.html#chess.Outcome.termination - 'Result': result of this game, 1-0, 1/2-1/2, 0-1. ### Call for Collaboration We invite interested researchers and ML practitioners to explore these datasets' potential. Whether training GPT models from scratch or fine-tuning pre-existing models, we encourage the exploration of various pre-training and fine-tuning strategies using these game-based datasets standalone or as enhancement of other already composed large-scale data. Our team is prepared to assist in securing necessary GPU resources for these explorations. We are particularly interested in collaborators eager to pre-train models of small to medium scale on our game data, subsequently transition to standard text-based training, and then perform comparative analyses against models of similar architecture trained exclusively on text data. Conclusively, this initiative marks a significant stride toward intricate problem-solving and strategic planning in AI, extending an open invitation to the research community for collaborative advancement in this domain.

japanese-asr/whisper_transcriptions.mls.wer_10.0.vectorized

japanese-asr

--- dataset_info: - config_name: subset_0 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95550219596 num_examples: 62101 download_size: 43092578892 dataset_size: 95550219596 - config_name: subset_1 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95892233884 num_examples: 62323 download_size: 43217224829 dataset_size: 95892233884 - config_name: subset_10 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95659534424 num_examples: 62172 download_size: 43197712726 dataset_size: 95659534424 - config_name: subset_100 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95570234896 num_examples: 62114 download_size: 43084233453 dataset_size: 95570234896 - config_name: subset_101 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95741000524 num_examples: 62225 download_size: 43183665345 dataset_size: 95741000524 - config_name: subset_102 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95732487892 num_examples: 62219 download_size: 43229537725 dataset_size: 95732487892 - config_name: subset_103 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95776664816 num_examples: 62248 download_size: 43187441638 dataset_size: 95776664816 - config_name: subset_104 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95930500816 num_examples: 62348 download_size: 43294625977 dataset_size: 95930500816 - config_name: subset_105 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95836868972 num_examples: 62287 download_size: 43251807028 dataset_size: 95836868972 - config_name: subset_106 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95940716900 num_examples: 62355 download_size: 43289304103 dataset_size: 95940716900 - config_name: subset_107 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95782476488 num_examples: 62252 download_size: 43209137820 dataset_size: 95782476488 - config_name: subset_108 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 96007104792 num_examples: 62398 download_size: 43221018658 dataset_size: 96007104792 - config_name: subset_109 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95764776944 num_examples: 62240 download_size: 43162176171 dataset_size: 95764776944 - config_name: subset_11 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95749669360 num_examples: 62230 download_size: 43193067430 dataset_size: 95749669360 - config_name: subset_110 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95826353540 num_examples: 62281 download_size: 43217482451 dataset_size: 95826353540 - config_name: subset_111 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95910493660 num_examples: 62335 download_size: 43268379463 dataset_size: 95910493660 - config_name: subset_112 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95782539616 num_examples: 62252 download_size: 43198507530 dataset_size: 95782539616 - config_name: subset_113 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95496693376 num_examples: 62066 download_size: 43106662052 dataset_size: 95496693376 - config_name: subset_114 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 16920876 num_examples: 11 download_size: 7573002 dataset_size: 16920876 - config_name: subset_115 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95639177564 num_examples: 62159 download_size: 43180784518 dataset_size: 95639177564 - config_name: subset_116 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95625267448 num_examples: 62150 download_size: 43124129761 dataset_size: 95625267448 - config_name: subset_117 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95545048296 num_examples: 62098 download_size: 43082968259 dataset_size: 95545048296 - config_name: subset_118 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95866827908 num_examples: 62307 download_size: 43167164098 dataset_size: 95866827908 - config_name: subset_119 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 96068332252 num_examples: 62437 download_size: 43339136980 dataset_size: 96068332252 - config_name: subset_12 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95728691164 num_examples: 62217 download_size: 43198747627 dataset_size: 95728691164 - config_name: subset_120 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95722632700 num_examples: 62213 download_size: 43167373358 dataset_size: 95722632700 - config_name: subset_121 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95732191100 num_examples: 62219 download_size: 43221505796 dataset_size: 95732191100 - config_name: subset_122 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95699024432 num_examples: 62198 download_size: 43219580053 dataset_size: 95699024432 - config_name: subset_123 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95713523564 num_examples: 62207 download_size: 43177149081 dataset_size: 95713523564 - config_name: subset_124 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95463256840 num_examples: 62044 download_size: 43081995426 dataset_size: 95463256840 - config_name: subset_125 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95597812312 num_examples: 62132 download_size: 43093919552 dataset_size: 95597812312 - config_name: subset_126 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95798796016 num_examples: 62262 download_size: 43254288601 dataset_size: 95798796016 - config_name: subset_127 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95674872576 num_examples: 62182 download_size: 43251503801 dataset_size: 95674872576 - config_name: subset_128 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95741950380 num_examples: 62225 download_size: 43150675085 dataset_size: 95741950380 - config_name: subset_129 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95902821264 num_examples: 62330 download_size: 43266797081 dataset_size: 95902821264 - config_name: subset_13 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95706484544 num_examples: 62202 download_size: 43194357797 dataset_size: 95706484544 - config_name: subset_130 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 13845812 num_examples: 9 download_size: 6597728 dataset_size: 13845812 - config_name: subset_131 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95385820008 num_examples: 61994 download_size: 43049793791 dataset_size: 95385820008 - config_name: subset_132 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95718111696 num_examples: 62210 download_size: 43160367467 dataset_size: 95718111696 - config_name: subset_133 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95642427284 num_examples: 62161 download_size: 43145455128 dataset_size: 95642427284 - config_name: subset_134 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95783162736 num_examples: 62252 download_size: 43157288094 dataset_size: 95783162736 - config_name: subset_135 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95905643680 num_examples: 62332 download_size: 43211878248 dataset_size: 95905643680 - config_name: subset_136 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95602572980 num_examples: 62135 download_size: 43148250609 dataset_size: 95602572980 - config_name: subset_137 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95742569912 num_examples: 62226 download_size: 43196126465 dataset_size: 95742569912 - config_name: subset_138 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95784277468 num_examples: 62253 download_size: 43213036863 dataset_size: 95784277468 - config_name: subset_14 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95484035440 num_examples: 62058 download_size: 43038787620 dataset_size: 95484035440 - config_name: subset_15 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95847923004 num_examples: 62295 download_size: 43269622880 dataset_size: 95847923004 - config_name: subset_16 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143676345616 num_examples: 93380 download_size: 64763101794 dataset_size: 143676345616 - config_name: subset_17 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143218562076 num_examples: 93081 download_size: 64543519703 dataset_size: 143218562076 - config_name: subset_18 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 1538508 num_examples: 1 download_size: 888657 dataset_size: 1538508 - config_name: subset_19 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143234313008 num_examples: 93092 download_size: 64590945738 dataset_size: 143234313008 - config_name: subset_2 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95692976304 num_examples: 62194 download_size: 43156432229 dataset_size: 95692976304 - config_name: subset_20 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143387469416 num_examples: 93192 download_size: 64657130955 dataset_size: 143387469416 - config_name: subset_21 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143761745188 num_examples: 93435 download_size: 64848639452 dataset_size: 143761745188 - config_name: subset_22 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143510788288 num_examples: 93272 download_size: 64664207735 dataset_size: 143510788288 - config_name: subset_23 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143745597332 num_examples: 93425 download_size: 64881327829 dataset_size: 143745597332 - config_name: subset_24 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143524148912 num_examples: 93280 download_size: 64658212505 dataset_size: 143524148912 - config_name: subset_25 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143893466228 num_examples: 93521 download_size: 64887011756 dataset_size: 143893466228 - config_name: subset_26 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143679361468 num_examples: 93381 download_size: 64845399473 dataset_size: 143679361468 - config_name: subset_27 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143578388120 num_examples: 93316 download_size: 64733082218 dataset_size: 143578388120 - config_name: subset_28 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143336154232 num_examples: 93158 download_size: 64663766459 dataset_size: 143336154232 - config_name: subset_29 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 7691452 num_examples: 5 download_size: 3459998 dataset_size: 7691452 - config_name: subset_3 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95679747492 num_examples: 62185 download_size: 43162138038 dataset_size: 95679747492 - config_name: subset_30 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143445434128 num_examples: 93230 download_size: 64632174781 dataset_size: 143445434128 - config_name: subset_31 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143557489496 num_examples: 93302 download_size: 64701593443 dataset_size: 143557489496 - config_name: subset_32 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143480746600 num_examples: 93252 download_size: 64739797925 dataset_size: 143480746600 - config_name: subset_33 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143804688340 num_examples: 93463 download_size: 64883427549 dataset_size: 143804688340 - config_name: subset_34 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143763133852 num_examples: 93435 download_size: 64878027444 dataset_size: 143763133852 - config_name: subset_35 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143471499924 num_examples: 93247 download_size: 64668279919 dataset_size: 143471499924 - config_name: subset_36 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143578658920 num_examples: 93316 download_size: 64771308961 dataset_size: 143578658920 - config_name: subset_37 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143421843384 num_examples: 93214 download_size: 64702071071 dataset_size: 143421843384 - config_name: subset_38 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143684196348 num_examples: 93385 download_size: 64784473635 dataset_size: 143684196348 - config_name: subset_39 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143680679576 num_examples: 93382 download_size: 64742283095 dataset_size: 143680679576 - config_name: subset_4 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95688480364 num_examples: 62191 download_size: 43186075154 dataset_size: 95688480364 - config_name: subset_40 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 12306560 num_examples: 8 download_size: 5824713 dataset_size: 12306560 - config_name: subset_41 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143692662464 num_examples: 93390 download_size: 64709902673 dataset_size: 143692662464 - config_name: subset_42 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143203990624 num_examples: 93072 download_size: 64613043749 dataset_size: 143203990624 - config_name: subset_43 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143423685888 num_examples: 93216 download_size: 64706208398 dataset_size: 143423685888 - config_name: subset_44 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143599898184 num_examples: 93330 download_size: 64731002218 dataset_size: 143599898184 - config_name: subset_45 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143523564744 num_examples: 93280 download_size: 64697514930 dataset_size: 143523564744 - config_name: subset_46 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143657253604 num_examples: 93367 download_size: 64832235795 dataset_size: 143657253604 - config_name: subset_47 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143635083108 num_examples: 93353 download_size: 64816566584 dataset_size: 143635083108 - config_name: subset_48 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143498198048 num_examples: 93264 download_size: 64761835832 dataset_size: 143498198048 - config_name: subset_49 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95628254736 num_examples: 62152 download_size: 43114668093 dataset_size: 95628254736 - config_name: subset_5 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95761408264 num_examples: 62238 download_size: 43098449131 dataset_size: 95761408264 - config_name: subset_50 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95710114492 num_examples: 62205 download_size: 43145722727 dataset_size: 95710114492 - config_name: subset_51 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95718176136 num_examples: 62210 download_size: 43219455050 dataset_size: 95718176136 - config_name: subset_52 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95945517480 num_examples: 62358 download_size: 43266431091 dataset_size: 95945517480 - config_name: subset_53 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95659331056 num_examples: 62172 download_size: 43159537104 dataset_size: 95659331056 - config_name: subset_54 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95733778168 num_examples: 62220 download_size: 43168252529 dataset_size: 95733778168 - config_name: subset_55 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95529164348 num_examples: 62087 download_size: 43137593293 dataset_size: 95529164348 - config_name: subset_56 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 12308272 num_examples: 8 download_size: 6100142 dataset_size: 12308272 - config_name: subset_57 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95725368820 num_examples: 62215 download_size: 43172851860 dataset_size: 95725368820 - config_name: subset_58 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95675366136 num_examples: 62182 download_size: 43119589688 dataset_size: 95675366136 - config_name: subset_59 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95757684168 num_examples: 62236 download_size: 43189671985 dataset_size: 95757684168 - config_name: subset_6 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95578098092 num_examples: 62119 download_size: 43139859949 dataset_size: 95578098092 - config_name: subset_60 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95700890356 num_examples: 62199 download_size: 43168843386 dataset_size: 95700890356 - config_name: subset_61 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95730743624 num_examples: 62218 download_size: 43225423665 dataset_size: 95730743624 - config_name: subset_62 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95939249240 num_examples: 62354 download_size: 43194512512 dataset_size: 95939249240 - config_name: subset_63 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95771529340 num_examples: 62245 download_size: 43196958015 dataset_size: 95771529340 - config_name: subset_64 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95848159444 num_examples: 62295 download_size: 43215788957 dataset_size: 95848159444 - config_name: subset_65 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95882062420 num_examples: 62317 download_size: 43207070631 dataset_size: 95882062420 - config_name: subset_66 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95871828072 num_examples: 62310 download_size: 43225588983 dataset_size: 95871828072 - config_name: subset_67 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95709466896 num_examples: 62204 download_size: 43120587410 dataset_size: 95709466896 - config_name: subset_68 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95761289000 num_examples: 62238 download_size: 43168961328 dataset_size: 95761289000 - config_name: subset_69 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95724204184 num_examples: 62214 download_size: 43179130241 dataset_size: 95724204184 - config_name: subset_7 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 1538156 num_examples: 1 download_size: 820398 dataset_size: 1538156 - config_name: subset_70 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95609034668 num_examples: 62139 download_size: 43117847437 dataset_size: 95609034668 - config_name: subset_71 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95387596792 num_examples: 61996 download_size: 43021151166 dataset_size: 95387596792 - config_name: subset_72 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 4615244 num_examples: 3 download_size: 2452533 dataset_size: 4615244 - config_name: subset_73 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95846947264 num_examples: 62294 download_size: 43209608729 dataset_size: 95846947264 - config_name: subset_74 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95818688740 num_examples: 62275 download_size: 43205934001 dataset_size: 95818688740 - config_name: subset_75 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95775232460 num_examples: 62247 download_size: 43190536605 dataset_size: 95775232460 - config_name: subset_76 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95665581880 num_examples: 62176 download_size: 43152943289 dataset_size: 95665581880 - config_name: subset_77 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95538306996 num_examples: 62093 download_size: 43186488482 dataset_size: 95538306996 - config_name: subset_78 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95653366336 num_examples: 62168 download_size: 43143452346 dataset_size: 95653366336 - config_name: subset_79 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95676339900 num_examples: 62183 download_size: 43128557833 dataset_size: 95676339900 - config_name: subset_8 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95715343992 num_examples: 62208 download_size: 43164885461 dataset_size: 95715343992 - config_name: subset_80 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95766599296 num_examples: 62242 download_size: 43239930128 dataset_size: 95766599296 - config_name: subset_81 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143321630332 num_examples: 93149 download_size: 64626209893 dataset_size: 143321630332 - config_name: subset_82 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143413608572 num_examples: 93209 download_size: 64621538517 dataset_size: 143413608572 - config_name: subset_83 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143531418364 num_examples: 93285 download_size: 64801287818 dataset_size: 143531418364 - config_name: subset_84 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143436760360 num_examples: 93224 download_size: 64683558260 dataset_size: 143436760360 - config_name: subset_85 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143693790772 num_examples: 93391 download_size: 64884349404 dataset_size: 143693790772 - config_name: subset_86 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143485525272 num_examples: 93256 download_size: 64696999488 dataset_size: 143485525272 - config_name: subset_87 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143365510504 num_examples: 93178 download_size: 64633922570 dataset_size: 143365510504 - config_name: subset_88 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143459907372 num_examples: 93239 download_size: 64646778148 dataset_size: 143459907372 - config_name: subset_89 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143713229680 num_examples: 93404 download_size: 64788831986 dataset_size: 143713229680 - config_name: subset_9 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95562629284 num_examples: 62109 download_size: 43123134026 dataset_size: 95562629284 - config_name: subset_90 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 143379593708 num_examples: 93187 download_size: 64733038170 dataset_size: 143379593708 - config_name: subset_91 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95696250128 num_examples: 62196 download_size: 43134085960 dataset_size: 95696250128 - config_name: subset_92 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95934407652 num_examples: 62351 download_size: 43224929875 dataset_size: 95934407652 - config_name: subset_93 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95753580284 num_examples: 62233 download_size: 43222236201 dataset_size: 95753580284 - config_name: subset_94 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95891874916 num_examples: 62323 download_size: 43252770071 dataset_size: 95891874916 - config_name: subset_95 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95659464728 num_examples: 62172 download_size: 43086228614 dataset_size: 95659464728 - config_name: subset_96 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95794821896 num_examples: 62260 download_size: 43179370699 dataset_size: 95794821896 - config_name: subset_97 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95622506640 num_examples: 62148 download_size: 43156846644 dataset_size: 95622506640 - config_name: subset_98 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 13845628 num_examples: 9 download_size: 6713409 dataset_size: 13845628 - config_name: subset_99 features: - name: transcription sequence: int64 - name: transcription/ja_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/ja_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 95636401316 num_examples: 62157 download_size: 43147436863 dataset_size: 95636401316 configs: - config_name: subset_0 data_files: - split: train path: subset_0/train-* - config_name: subset_1 data_files: - split: train path: subset_1/train-* - config_name: subset_10 data_files: - split: train path: subset_10/train-* - config_name: subset_100 data_files: - split: train path: subset_100/train-* - config_name: subset_101 data_files: - split: train path: subset_101/train-* - config_name: subset_102 data_files: - split: train path: subset_102/train-* - config_name: subset_103 data_files: - split: train path: subset_103/train-* - config_name: subset_104 data_files: - split: train path: subset_104/train-* - config_name: subset_105 data_files: - split: train path: subset_105/train-* - config_name: subset_106 data_files: - split: train path: subset_106/train-* - config_name: subset_107 data_files: - split: train path: subset_107/train-* - config_name: subset_108 data_files: - split: train path: subset_108/train-* - config_name: subset_109 data_files: - split: train path: subset_109/train-* - config_name: subset_11 data_files: - split: train path: subset_11/train-* - config_name: subset_110 data_files: - split: train path: subset_110/train-* - config_name: subset_111 data_files: - split: train path: subset_111/train-* - config_name: subset_112 data_files: - split: train path: subset_112/train-* - config_name: subset_113 data_files: - split: train path: subset_113/train-* - config_name: subset_114 data_files: - split: train path: subset_114/train-* - config_name: subset_115 data_files: - split: train path: subset_115/train-* - config_name: subset_116 data_files: - split: train path: subset_116/train-* - config_name: subset_117 data_files: - split: train path: subset_117/train-* - config_name: subset_118 data_files: - split: train path: subset_118/train-* - config_name: subset_119 data_files: - split: train path: subset_119/train-* - config_name: subset_12 data_files: - split: train path: subset_12/train-* - config_name: subset_120 data_files: - split: train path: subset_120/train-* - config_name: subset_121 data_files: - split: train path: subset_121/train-* - config_name: subset_122 data_files: - split: train path: subset_122/train-* - config_name: subset_123 data_files: - split: train path: subset_123/train-* - config_name: subset_124 data_files: - split: train path: subset_124/train-* - config_name: subset_125 data_files: - split: train path: subset_125/train-* - config_name: subset_126 data_files: - split: train path: subset_126/train-* - config_name: subset_127 data_files: - split: train path: subset_127/train-* - config_name: subset_128 data_files: - split: train path: subset_128/train-* - config_name: subset_129 data_files: - split: train path: subset_129/train-* - config_name: subset_13 data_files: - split: train path: subset_13/train-* - config_name: subset_130 data_files: - split: train path: subset_130/train-* - config_name: subset_131 data_files: - split: train path: subset_131/train-* - config_name: subset_132 data_files: - split: train path: subset_132/train-* - config_name: subset_133 data_files: - split: train path: subset_133/train-* - config_name: subset_134 data_files: - split: train path: subset_134/train-* - config_name: subset_135 data_files: - split: train path: subset_135/train-* - config_name: subset_136 data_files: - split: train path: subset_136/train-* - config_name: subset_137 data_files: - split: train path: subset_137/train-* - config_name: subset_138 data_files: - split: train path: subset_138/train-* - config_name: subset_14 data_files: - split: train path: subset_14/train-* - config_name: subset_15 data_files: - split: train path: subset_15/train-* - config_name: subset_16 data_files: - split: train path: subset_16/train-* - config_name: subset_17 data_files: - split: train path: subset_17/train-* - config_name: subset_18 data_files: - split: train path: subset_18/train-* - config_name: subset_19 data_files: - split: train path: subset_19/train-* - config_name: subset_2 data_files: - split: train path: subset_2/train-* - config_name: subset_20 data_files: - split: train path: subset_20/train-* - config_name: subset_21 data_files: - split: train path: subset_21/train-* - config_name: subset_22 data_files: - split: train path: subset_22/train-* - config_name: subset_23 data_files: - split: train path: subset_23/train-* - config_name: subset_24 data_files: - split: train path: subset_24/train-* - config_name: subset_25 data_files: - split: train path: subset_25/train-* - config_name: subset_26 data_files: - split: train path: subset_26/train-* - config_name: subset_27 data_files: - split: train path: subset_27/train-* - config_name: subset_28 data_files: - split: train path: subset_28/train-* - config_name: subset_29 data_files: - split: train path: subset_29/train-* - config_name: subset_3 data_files: - split: train path: subset_3/train-* - config_name: subset_30 data_files: - split: train path: subset_30/train-* - config_name: subset_31 data_files: - split: train path: subset_31/train-* - config_name: subset_32 data_files: - split: train path: subset_32/train-* - config_name: subset_33 data_files: - split: train path: subset_33/train-* - config_name: subset_34 data_files: - split: train path: subset_34/train-* - config_name: subset_35 data_files: - split: train path: subset_35/train-* - config_name: subset_36 data_files: - split: train path: subset_36/train-* - config_name: subset_37 data_files: - split: train path: subset_37/train-* - config_name: subset_38 data_files: - split: train path: subset_38/train-* - config_name: subset_39 data_files: - split: train path: subset_39/train-* - config_name: subset_4 data_files: - split: train path: subset_4/train-* - config_name: subset_40 data_files: - split: train path: subset_40/train-* - config_name: subset_41 data_files: - split: train path: subset_41/train-* - config_name: subset_42 data_files: - split: train path: subset_42/train-* - config_name: subset_43 data_files: - split: train path: subset_43/train-* - config_name: subset_44 data_files: - split: train path: subset_44/train-* - config_name: subset_45 data_files: - split: train path: subset_45/train-* - config_name: subset_46 data_files: - split: train path: subset_46/train-* - config_name: subset_47 data_files: - split: train path: subset_47/train-* - config_name: subset_48 data_files: - split: train path: subset_48/train-* - config_name: subset_49 data_files: - split: train path: subset_49/train-* - config_name: subset_5 data_files: - split: train path: subset_5/train-* - config_name: subset_50 data_files: - split: train path: subset_50/train-* - config_name: subset_51 data_files: - split: train path: subset_51/train-* - config_name: subset_52 data_files: - split: train path: subset_52/train-* - config_name: subset_53 data_files: - split: train path: subset_53/train-* - config_name: subset_54 data_files: - split: train path: subset_54/train-* - config_name: subset_55 data_files: - split: train path: subset_55/train-* - config_name: subset_56 data_files: - split: train path: subset_56/train-* - config_name: subset_57 data_files: - split: train path: subset_57/train-* - config_name: subset_58 data_files: - split: train path: subset_58/train-* - config_name: subset_59 data_files: - split: train path: subset_59/train-* - config_name: subset_6 data_files: - split: train path: subset_6/train-* - config_name: subset_60 data_files: - split: train path: subset_60/train-* - config_name: subset_61 data_files: - split: train path: subset_61/train-* - config_name: subset_62 data_files: - split: train path: subset_62/train-* - config_name: subset_63 data_files: - split: train path: subset_63/train-* - config_name: subset_64 data_files: - split: train path: subset_64/train-* - config_name: subset_65 data_files: - split: train path: subset_65/train-* - config_name: subset_66 data_files: - split: train path: subset_66/train-* - config_name: subset_67 data_files: - split: train path: subset_67/train-* - config_name: subset_68 data_files: - split: train path: subset_68/train-* - config_name: subset_69 data_files: - split: train path: subset_69/train-* - config_name: subset_7 data_files: - split: train path: subset_7/train-* - config_name: subset_70 data_files: - split: train path: subset_70/train-* - config_name: subset_71 data_files: - split: train path: subset_71/train-* - config_name: subset_72 data_files: - split: train path: subset_72/train-* - config_name: subset_73 data_files: - split: train path: subset_73/train-* - config_name: subset_74 data_files: - split: train path: subset_74/train-* - config_name: subset_75 data_files: - split: train path: subset_75/train-* - config_name: subset_76 data_files: - split: train path: subset_76/train-* - config_name: subset_77 data_files: - split: train path: subset_77/train-* - config_name: subset_78 data_files: - split: train path: subset_78/train-* - config_name: subset_79 data_files: - split: train path: subset_79/train-* - config_name: subset_8 data_files: - split: train path: subset_8/train-* - config_name: subset_80 data_files: - split: train path: subset_80/train-* - config_name: subset_81 data_files: - split: train path: subset_81/train-* - config_name: subset_82 data_files: - split: train path: subset_82/train-* - config_name: subset_83 data_files: - split: train path: subset_83/train-* - config_name: subset_84 data_files: - split: train path: subset_84/train-* - config_name: subset_85 data_files: - split: train path: subset_85/train-* - config_name: subset_86 data_files: - split: train path: subset_86/train-* - config_name: subset_87 data_files: - split: train path: subset_87/train-* - config_name: subset_88 data_files: - split: train path: subset_88/train-* - config_name: subset_89 data_files: - split: train path: subset_89/train-* - config_name: subset_9 data_files: - split: train path: subset_9/train-* - config_name: subset_90 data_files: - split: train path: subset_90/train-* - config_name: subset_91 data_files: - split: train path: subset_91/train-* - config_name: subset_92 data_files: - split: train path: subset_92/train-* - config_name: subset_93 data_files: - split: train path: subset_93/train-* - config_name: subset_94 data_files: - split: train path: subset_94/train-* - config_name: subset_95 data_files: - split: train path: subset_95/train-* - config_name: subset_96 data_files: - split: train path: subset_96/train-* - config_name: subset_97 data_files: - split: train path: subset_97/train-* - config_name: subset_98 data_files: - split: train path: subset_98/train-* - config_name: subset_99 data_files: - split: train path: subset_99/train-* ---

EdinburghNLP/xsum

EdinburghNLP

--- annotations_creators: - found language_creators: - found language: - en license: - unknown multilinguality: - monolingual pretty_name: Extreme Summarization (XSum) paperswithcode_id: xsum size_categories: - 100K<n<1M source_datasets: - original task_categories: - summarization task_ids: - news-articles-summarization train-eval-index: - config: default task: summarization task_id: summarization splits: train_split: train eval_split: test col_mapping: document: text summary: target metrics: - type: rouge name: Rouge dataset_info: features: - name: document dtype: string - name: summary dtype: string - name: id dtype: string splits: - name: train num_bytes: 479206608 num_examples: 204045 - name: validation num_bytes: 26292901 num_examples: 11332 - name: test num_bytes: 26756165 num_examples: 11334 download_size: 257302866 dataset_size: 532255674 --- # Dataset Card for "xsum" ## Table of Contents - [Dataset Description](#dataset-description) - [Dataset Summary](#dataset-summary) - [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards) - [Languages](#languages) - [Dataset Structure](#dataset-structure) - [Data Instances](#data-instances) - [Data Fields](#data-fields) - [Data Splits](#data-splits) - [Dataset Creation](#dataset-creation) - [Curation Rationale](#curation-rationale) - [Source Data](#source-data) - [Annotations](#annotations) - [Personal and Sensitive Information](#personal-and-sensitive-information) - [Considerations for Using the Data](#considerations-for-using-the-data) - [Social Impact of Dataset](#social-impact-of-dataset) - [Discussion of Biases](#discussion-of-biases) - [Other Known Limitations](#other-known-limitations) - [Additional Information](#additional-information) - [Dataset Curators](#dataset-curators) - [Licensing Information](#licensing-information) - [Citation Information](#citation-information) - [Contributions](#contributions) ## Dataset Description - **Homepage:** - **Repository:** https://github.com/EdinburghNLP/XSum - **Paper:** [Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization](https://arxiv.org/abs/1808.08745) - **Point of Contact:** [Shashi Narayan](mailto:[email protected]) - **Size of downloaded dataset files:** 257.30 MB - **Size of the generated dataset:** 532.26 MB - **Total amount of disk used:** 789.56 MB ### Dataset Summary Extreme Summarization (XSum) Dataset. There are three features: - document: Input news article. - summary: One sentence summary of the article. - id: BBC ID of the article. ### Supported Tasks and Leaderboards [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Languages [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ## Dataset Structure ### Data Instances #### default - **Size of downloaded dataset files:** 257.30 MB - **Size of the generated dataset:** 532.26 MB - **Total amount of disk used:** 789.56 MB An example of 'validation' looks as follows. ``` { "document": "some-body", "id": "29750031", "summary": "some-sentence" } ``` ### Data Fields The data fields are the same among all splits. #### default - `document`: a `string` feature. - `summary`: a `string` feature. - `id`: a `string` feature. ### Data Splits | name |train |validation|test | |-------|-----:|---------:|----:| |default|204045| 11332|11334| ## Dataset Creation ### Curation Rationale [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Source Data #### Initial Data Collection and Normalization [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) #### Who are the source language producers? [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Annotations #### Annotation process [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) #### Who are the annotators? [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Personal and Sensitive Information [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ## Considerations for Using the Data ### Social Impact of Dataset [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Discussion of Biases [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Other Known Limitations [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ## Additional Information ### Dataset Curators [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Licensing Information [More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) ### Citation Information ``` @article{Narayan2018DontGM, title={Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization}, author={Shashi Narayan and Shay B. Cohen and Mirella Lapata}, journal={ArXiv}, year={2018}, volume={abs/1808.08745} } ``` ### Contributions Thanks to [@thomwolf](https://github.com/thomwolf), [@lewtun](https://github.com/lewtun), [@mariamabarham](https://github.com/mariamabarham), [@jbragg](https://github.com/jbragg), [@lhoestq](https://github.com/lhoestq), [@patrickvonplaten](https://github.com/patrickvonplaten) for adding this dataset.

mshah1/speech_robust_bench

mshah1

--- dataset_info: - config_name: accented_cv features: - name: audio dtype: audio: sampling_rate: 16000 - name: text dtype: string - name: age dtype: string - name: gender dtype: string - name: accents dtype: string - name: locale dtype: string - name: id dtype: int64 splits: - name: test num_bytes: 55407854.085 num_examples: 1355 - name: test.clean num_bytes: 25593824.0 num_examples: 640 download_size: 78598662 dataset_size: 81001678.08500001 - config_name: accented_cv_es features: - name: audio dtype: audio - name: accent dtype: string - name: text dtype: string - name: gender dtype: string - name: age dtype: string - name: locale dtype: string - name: id dtype: int64 splits: - name: test num_bytes: 65868440.963 num_examples: 1483 download_size: 60557913 dataset_size: 65868440.963 - config_name: accented_cv_fr features: - name: file_name dtype: string - name: accent dtype: string - name: text dtype: string - name: gender dtype: string - name: age dtype: string - name: locale dtype: string - name: id dtype: int64 splits: - name: test num_bytes: 337528 num_examples: 2171 download_size: 148493 dataset_size: 337528 - config_name: chime features: - name: audio dtype: audio - name: end_time dtype: string - name: start_time dtype: string - name: speaker dtype: string - name: ref dtype: string - name: location dtype: string - name: session_id dtype: string - name: text dtype: string splits: - name: farfield num_bytes: 521160936.31 num_examples: 6535 - name: nearfield num_bytes: 1072274621.0799999 num_examples: 6535 download_size: 1532887016 dataset_size: 1593435557.3899999 - config_name: in-the-wild features: - name: audio dtype: audio - name: end_time dtype: string - name: start_time dtype: string - name: speaker dtype: string - name: ref dtype: string - name: location dtype: string - name: session_id dtype: string - name: id dtype: string - name: text dtype: string splits: - name: farfield num_bytes: 521363521.31 num_examples: 6535 - name: nearfield num_bytes: 1072477206.0799999 num_examples: 6535 download_size: 1533124839 dataset_size: 1593840727.3899999 - config_name: in-the-wild-AMI features: - name: meeting_id dtype: string - name: id dtype: string - name: text dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: begin_time dtype: float32 - name: end_time dtype: float32 - name: microphone_id dtype: string - name: speaker_id dtype: string splits: - name: nearfield num_bytes: 1382749390.9785259 num_examples: 6584 - name: farfield num_bytes: 1040706691.1008185 num_examples: 6584 download_size: 2164898498 dataset_size: 2423456082.0793443 - config_name: in-the-wild-ami features: - name: meeting_id dtype: string - name: audio_id dtype: string - name: text dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: begin_time dtype: float32 - name: end_time dtype: float32 - name: microphone_id dtype: string - name: speaker_id dtype: string splits: - name: nearfield num_bytes: 1382749390.9785259 num_examples: 6584 - name: farfield num_bytes: 1040706691.1008185 num_examples: 6584 download_size: 2164900274 dataset_size: 2423456082.0793443 - config_name: librispeech_asr-test.clean features: - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: text dtype: string - name: speaker_id dtype: int64 - name: chapter_id dtype: int64 - name: id dtype: string splits: - name: speedup.1 num_bytes: 498896619.34 num_examples: 2620 - name: speedup.2 num_bytes: 415901075.34 num_examples: 2620 - name: speedup.3 num_bytes: 356617835.34 num_examples: 2620 - name: speedup.4 num_bytes: 312152811.34 num_examples: 2620 - name: slowdown.1 num_bytes: 712320343.34 num_examples: 2620 - name: slowdown.2 num_bytes: 830887339.34 num_examples: 2620 - name: slowdown.3 num_bytes: 996880127.34 num_examples: 2620 - name: slowdown.4 num_bytes: 1245871847.34 num_examples: 2620 - name: pitch_up.3 num_bytes: 623392467.34 num_examples: 2620 - name: pitch_up.4 num_bytes: 623392467.34 num_examples: 2620 - name: pitch_down.1 num_bytes: 623392467.34 num_examples: 2620 - name: pitch_down.2 num_bytes: 623392467.34 num_examples: 2620 - name: pitch_down.3 num_bytes: 623392467.34 num_examples: 2620 - name: pitch_down.4 num_bytes: 623392467.34 num_examples: 2620 - name: pitch_up.1 num_bytes: 623392458.5 num_examples: 2620 - name: pitch_up.2 num_bytes: 623392458.5 num_examples: 2620 - name: resample.1 num_bytes: 623392535.34 num_examples: 2620 - name: resample.2 num_bytes: 623392535.34 num_examples: 2620 - name: resample.3 num_bytes: 623392579.34 num_examples: 2620 - name: resample.4 num_bytes: 623392623.34 num_examples: 2620 - name: voice_conversion.4 num_bytes: 799852214.5 num_examples: 2620 - name: voice_conversion.3 num_bytes: 580185782.5 num_examples: 2620 - name: voice_conversion.1 num_bytes: 589259446.5 num_examples: 2620 - name: voice_conversion.2 num_bytes: 571175606.5 num_examples: 2620 - name: gain.1 num_bytes: 623392467.34 num_examples: 2620 - name: gain.2 num_bytes: 623392467.34 num_examples: 2620 - name: gain.3 num_bytes: 623392467.34 num_examples: 2620 - name: echo.1 num_bytes: 633872467.34 num_examples: 2620 - name: echo.2 num_bytes: 644352467.34 num_examples: 2620 - name: echo.3 num_bytes: 665312467.34 num_examples: 2620 - name: echo.4 num_bytes: 707232467.34 num_examples: 2620 - name: phaser.1 num_bytes: 623392467.34 num_examples: 2620 - name: phaser.2 num_bytes: 623392467.34 num_examples: 2620 - name: phaser.3 num_bytes: 623392467.34 num_examples: 2620 - name: tempo_up.1 num_bytes: 498896595.34 num_examples: 2620 - name: tempo_up.2 num_bytes: 415899351.34 num_examples: 2620 - name: tempo_up.3 num_bytes: 356615595.34 num_examples: 2620 - name: tempo_up.4 num_bytes: 312152811.34 num_examples: 2620 - name: tempo_down.1 num_bytes: 712318083.34 num_examples: 2620 - name: tempo_down.2 num_bytes: 830885583.34 num_examples: 2620 - name: tempo_down.3 num_bytes: 996880103.34 num_examples: 2620 - name: tempo_down.4 num_bytes: 1245871847.34 num_examples: 2620 - name: gain.4 num_bytes: 623392467.34 num_examples: 2620 - name: phaser.4 num_bytes: 623392467.34 num_examples: 2620 - name: lowpass.1 num_bytes: 623392467.34 num_examples: 2620 - name: lowpass.2 num_bytes: 623392467.34 num_examples: 2620 - name: lowpass.3 num_bytes: 623392467.34 num_examples: 2620 - name: lowpass.4 num_bytes: 623392467.34 num_examples: 2620 - name: highpass.1 num_bytes: 623392467.34 num_examples: 2620 - name: highpass.2 num_bytes: 623392467.34 num_examples: 2620 - name: highpass.3 num_bytes: 623392467.34 num_examples: 2620 - name: highpass.4 num_bytes: 623392467.34 num_examples: 2620 - name: voice_conversion_vctk.1 num_bytes: 495165825.88 num_examples: 2620 - name: universal_adv.1 num_bytes: 623392467.34 num_examples: 2620 - name: rir.1 num_bytes: 705636818.5 num_examples: 2620 - name: rir.2 num_bytes: 744484818.5 num_examples: 2620 - name: rir.3 num_bytes: 758740818.5 num_examples: 2620 - name: rir.4 num_bytes: 776116818.5 num_examples: 2620 - name: gnoise.1 num_bytes: 623392455.88 num_examples: 2620 - name: gnoise.2 num_bytes: 623392455.88 num_examples: 2620 - name: gnoise.3 num_bytes: 623392455.88 num_examples: 2620 - name: gnoise.4 num_bytes: 623392455.88 num_examples: 2620 - name: env_noise_esc50.1 num_bytes: 623392455.88 num_examples: 2620 - name: env_noise_esc50.2 num_bytes: 623392455.88 num_examples: 2620 - name: env_noise_esc50.3 num_bytes: 623392455.88 num_examples: 2620 - name: env_noise_esc50.4 num_bytes: 623392455.88 num_examples: 2620 - name: music.1 num_bytes: 623392455.88 num_examples: 2620 - name: music.2 num_bytes: 623392455.88 num_examples: 2620 - name: music.3 num_bytes: 623392455.88 num_examples: 2620 - name: music.4 num_bytes: 623392455.88 num_examples: 2620 - name: crosstalk.1 num_bytes: 623392455.88 num_examples: 2620 - name: crosstalk.2 num_bytes: 623392455.88 num_examples: 2620 - name: crosstalk.3 num_bytes: 623392455.88 num_examples: 2620 - name: crosstalk.4 num_bytes: 623392455.88 num_examples: 2620 - name: env_noise_musan.1 num_bytes: 623392455.88 num_examples: 2620 - name: env_noise_musan.2 num_bytes: 623392455.88 num_examples: 2620 - name: env_noise_musan.3 num_bytes: 623392455.88 num_examples: 2620 - name: env_noise_musan.4 num_bytes: 623392455.88 num_examples: 2620 - name: real_rir.1 num_bytes: 638169615.88 num_examples: 2620 - name: real_rir.2 num_bytes: 694281819.88 num_examples: 2620 - name: real_rir.3 num_bytes: 713200537.88 num_examples: 2620 - name: real_rir.4 num_bytes: 1515177725.88 num_examples: 2620 - name: env_noise.1 num_bytes: 623392455.88 num_examples: 2620 - name: env_noise.2 num_bytes: 623392455.88 num_examples: 2620 - name: env_noise.3 num_bytes: 623392455.88 num_examples: 2620 - name: env_noise.4 num_bytes: 623392455.88 num_examples: 2620 - name: env_noise_wham.1 num_bytes: 623392455.88 num_examples: 2620 - name: env_noise_wham.2 num_bytes: 623392455.88 num_examples: 2620 - name: env_noise_wham.3 num_bytes: 623392455.88 num_examples: 2620 - name: env_noise_wham.4 num_bytes: 623392455.88 num_examples: 2620 - name: tremolo.1 num_bytes: 623392455.88 num_examples: 2620 - name: tremolo.2 num_bytes: 623392455.88 num_examples: 2620 - name: tremolo.3 num_bytes: 623392455.88 num_examples: 2620 - name: tremolo.4 num_bytes: 623392455.88 num_examples: 2620 - name: treble.1 num_bytes: 623392455.88 num_examples: 2620 - name: treble.2 num_bytes: 623392455.88 num_examples: 2620 - name: treble.3 num_bytes: 623392455.88 num_examples: 2620 - name: treble.4 num_bytes: 623392455.88 num_examples: 2620 - name: bass.1 num_bytes: 623392455.88 num_examples: 2620 - name: bass.2 num_bytes: 623392455.88 num_examples: 2620 - name: bass.3 num_bytes: 623392455.88 num_examples: 2620 - name: bass.4 num_bytes: 623392455.88 num_examples: 2620 - name: chorus.1 num_bytes: 626913735.88 num_examples: 2620 - name: chorus.2 num_bytes: 628590535.88 num_examples: 2620 - name: chorus.3 num_bytes: 630267335.88 num_examples: 2620 - name: chorus.4 num_bytes: 631944135.88 num_examples: 2620 - name: None.0 num_bytes: 367982506.42 num_examples: 2620 download_size: 67547733720 dataset_size: 68871044112.51988 - config_name: librispeech_asr-test.clean_pertEval_500_30 features: - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: text dtype: string - name: speaker_id dtype: int64 - name: chapter_id dtype: int64 - name: id dtype: string - name: pert_idx dtype: int64 splits: - name: gnoise.1 num_bytes: 3592401090.0 num_examples: 15000 - name: env_noise_esc50.1 num_bytes: 3592401090.0 num_examples: 15000 download_size: 7170899040 dataset_size: 7184802180.0 - config_name: multilingual_librispeech-french_test features: - name: audio dtype: audio: sampling_rate: 16000 - name: original_path dtype: string - name: begin_time dtype: float64 - name: end_time dtype: float64 - name: audio_duration dtype: float64 - name: speaker_id dtype: string - name: chapter_id dtype: string - name: file dtype: string - name: id dtype: string - name: text dtype: string splits: - name: gnoise.1 num_bytes: 1160858614.324 num_examples: 2426 - name: gnoise.2 num_bytes: 1160858614.324 num_examples: 2426 - name: gnoise.3 num_bytes: 1160858614.324 num_examples: 2426 - name: speedup.1 num_bytes: 928910526.324 num_examples: 2426 - name: speedup.3 num_bytes: 663829084.324 num_examples: 2426 - name: pitch_up.1 num_bytes: 1160858614.324 num_examples: 2426 - name: pitch_up.2 num_bytes: 1160858614.324 num_examples: 2426 - name: pitch_up.3 num_bytes: 1160858614.324 num_examples: 2426 - name: pitch_down.1 num_bytes: 1160858614.324 num_examples: 2426 - name: pitch_down.2 num_bytes: 1160858614.324 num_examples: 2426 - name: env_noise.1 num_bytes: 1160858614.324 num_examples: 2426 - name: env_noise.3 num_bytes: 1160858614.324 num_examples: 2426 - name: env_noise_wham.1 num_bytes: 1160858614.324 num_examples: 2426 - name: slowdown.2 num_bytes: 1547440398.324 num_examples: 2426 - name: real_rir.3 num_bytes: 1241772582.324 num_examples: 2426 - name: env_noise.2 num_bytes: 1160858614.324 num_examples: 2426 - name: env_noise_wham.2 num_bytes: 1160858614.324 num_examples: 2426 - name: speedup.2 num_bytes: 774280064.324 num_examples: 2426 - name: slowdown.1 num_bytes: 1326537936.324 num_examples: 2426 - name: slowdown.3 num_bytes: 1856702974.324 num_examples: 2426 - name: env_noise_esc50.1 num_bytes: 1160858614.324 num_examples: 2426 - name: env_noise_esc50.2 num_bytes: 1160858614.324 num_examples: 2426 - name: env_noise_esc50.3 num_bytes: 1160858614.324 num_examples: 2426 - name: env_noise_musan.1 num_bytes: 1160858614.324 num_examples: 2426 - name: env_noise_musan.2 num_bytes: 1160858614.324 num_examples: 2426 - name: env_noise_musan.3 num_bytes: 1160858614.324 num_examples: 2426 - name: env_noise_wham.3 num_bytes: 1160858614.324 num_examples: 2426 - name: pitch_down.3 num_bytes: 1160858614.324 num_examples: 2426 - name: rir.1 num_bytes: 1235965442.324 num_examples: 2426 - name: rir.2 num_bytes: 1273085442.324 num_examples: 2426 - name: rir.3 num_bytes: 1284653442.324 num_examples: 2426 - name: real_rir.1 num_bytes: 1174422106.324 num_examples: 2426 - name: real_rir.2 num_bytes: 1226129514.324 num_examples: 2426 - name: resample.1 num_bytes: 1160858656.324 num_examples: 2426 - name: resample.2 num_bytes: 1160858642.324 num_examples: 2426 - name: resample.3 num_bytes: 1160858694.324 num_examples: 2426 - name: gain.1 num_bytes: 1160858614.324 num_examples: 2426 - name: gain.2 num_bytes: 1160858614.324 num_examples: 2426 - name: gain.3 num_bytes: 1160858614.324 num_examples: 2426 - name: echo.1 num_bytes: 1170562614.324 num_examples: 2426 - name: echo.2 num_bytes: 1180266614.324 num_examples: 2426 - name: echo.3 num_bytes: 1199674614.324 num_examples: 2426 - name: phaser.1 num_bytes: 1160858614.324 num_examples: 2426 - name: phaser.2 num_bytes: 1160858614.324 num_examples: 2426 - name: phaser.3 num_bytes: 1160858614.324 num_examples: 2426 - name: tempo_up.1 num_bytes: 928910510.324 num_examples: 2426 - name: tempo_up.2 num_bytes: 774278396.324 num_examples: 2426 - name: tempo_up.3 num_bytes: 663826914.324 num_examples: 2426 - name: tempo_down.1 num_bytes: 1326535834.324 num_examples: 2426 - name: tempo_down.2 num_bytes: 1547438832.324 num_examples: 2426 - name: tempo_down.3 num_bytes: 1856702944.324 num_examples: 2426 - name: lowpass.1 num_bytes: 1160858614.324 num_examples: 2426 - name: lowpass.2 num_bytes: 1160858614.324 num_examples: 2426 - name: lowpass.3 num_bytes: 1160858614.324 num_examples: 2426 - name: highpass.1 num_bytes: 1160858614.324 num_examples: 2426 - name: highpass.2 num_bytes: 1160858614.324 num_examples: 2426 - name: highpass.3 num_bytes: 1160858614.324 num_examples: 2426 - name: music.1 num_bytes: 1160858614.324 num_examples: 2426 - name: music.2 num_bytes: 1160858614.324 num_examples: 2426 - name: music.3 num_bytes: 1160858614.324 num_examples: 2426 - name: crosstalk.1 num_bytes: 1160858614.324 num_examples: 2426 - name: crosstalk.2 num_bytes: 1160858614.324 num_examples: 2426 - name: crosstalk.3 num_bytes: 1160858614.324 num_examples: 2426 - name: tremolo.1 num_bytes: 1160858614.324 num_examples: 2426 - name: tremolo.2 num_bytes: 1160858614.324 num_examples: 2426 - name: tremolo.3 num_bytes: 1160858614.324 num_examples: 2426 - name: treble.1 num_bytes: 1160858614.324 num_examples: 2426 - name: treble.2 num_bytes: 1160858614.324 num_examples: 2426 - name: treble.3 num_bytes: 1160858614.324 num_examples: 2426 - name: bass.1 num_bytes: 1160858614.324 num_examples: 2426 - name: bass.2 num_bytes: 1160858614.324 num_examples: 2426 - name: bass.3 num_bytes: 1160858614.324 num_examples: 2426 - name: chorus.1 num_bytes: 1164119158.324 num_examples: 2426 - name: chorus.2 num_bytes: 1165671798.324 num_examples: 2426 - name: chorus.3 num_bytes: 1167224438.324 num_examples: 2426 - name: gnoise.4 num_bytes: 1160858614.324 num_examples: 2426 - name: env_noise.4 num_bytes: 1160858614.324 num_examples: 2426 - name: env_noise_esc50.4 num_bytes: 1160858614.324 num_examples: 2426 - name: env_noise_musan.4 num_bytes: 1160858614.324 num_examples: 2426 - name: env_noise_wham.4 num_bytes: 1160858614.324 num_examples: 2426 - name: speedup.4 num_bytes: 580988352.324 num_examples: 2426 - name: slowdown.4 num_bytes: 2320599166.324 num_examples: 2426 - name: pitch_up.4 num_bytes: 1160858614.324 num_examples: 2426 - name: pitch_down.4 num_bytes: 1160858614.324 num_examples: 2426 - name: rir.4 num_bytes: 1302669442.324 num_examples: 2426 - name: real_rir.4 num_bytes: 2020765820.324 num_examples: 2426 - name: resample.4 num_bytes: 1160858814.324 num_examples: 2426 - name: gain.4 num_bytes: 1160858614.324 num_examples: 2426 - name: echo.4 num_bytes: 1238490614.324 num_examples: 2426 - name: phaser.4 num_bytes: 1160858614.324 num_examples: 2426 - name: tempo_up.4 num_bytes: 580988352.324 num_examples: 2426 - name: tempo_down.4 num_bytes: 2320599166.324 num_examples: 2426 - name: lowpass.4 num_bytes: 1160858614.324 num_examples: 2426 - name: highpass.4 num_bytes: 1160858614.324 num_examples: 2426 - name: music.4 num_bytes: 1160858614.324 num_examples: 2426 - name: crosstalk.4 num_bytes: 1160858614.324 num_examples: 2426 - name: tremolo.4 num_bytes: 1160858614.324 num_examples: 2426 - name: treble.4 num_bytes: 1160858614.324 num_examples: 2426 - name: bass.4 num_bytes: 1160858614.324 num_examples: 2426 - name: chorus.4 num_bytes: 1168777078.324 num_examples: 2426 download_size: 121459263523 dataset_size: 119151206300.40016 - config_name: multilingual_librispeech-german_test features: - name: audio dtype: audio: sampling_rate: 16000 - name: original_path dtype: string - name: begin_time dtype: float64 - name: end_time dtype: float64 - name: audio_duration dtype: float64 - name: speaker_id dtype: string - name: chapter_id dtype: string - name: file dtype: string - name: id dtype: string - name: text dtype: string splits: - name: gnoise.1 num_bytes: 1648113341.356 num_examples: 3394 - name: gnoise.2 num_bytes: 1648113341.356 num_examples: 3394 - name: gnoise.3 num_bytes: 1648113341.356 num_examples: 3394 - name: env_noise.1 num_bytes: 1648113341.356 num_examples: 3394 - name: env_noise.2 num_bytes: 1648113341.356 num_examples: 3394 - name: env_noise.3 num_bytes: 1648113341.356 num_examples: 3394 - name: env_noise_esc50.1 num_bytes: 1648113341.356 num_examples: 3394 - name: env_noise_esc50.2 num_bytes: 1648113341.356 num_examples: 3394 - name: env_noise_esc50.3 num_bytes: 1648113341.356 num_examples: 3394 - name: env_noise_musan.1 num_bytes: 1648113341.356 num_examples: 3394 - name: env_noise_musan.2 num_bytes: 1648113341.356 num_examples: 3394 - name: env_noise_musan.3 num_bytes: 1648113341.356 num_examples: 3394 - name: env_noise_wham.1 num_bytes: 1648113341.356 num_examples: 3394 - name: env_noise_wham.2 num_bytes: 1648113341.356 num_examples: 3394 - name: env_noise_wham.3 num_bytes: 1648113341.356 num_examples: 3394 - name: speedup.1 num_bytes: 1318802109.356 num_examples: 3394 - name: speedup.2 num_bytes: 1099263673.356 num_examples: 3394 - name: speedup.3 num_bytes: 942449495.356 num_examples: 3394 - name: slowdown.1 num_bytes: 1883338719.356 num_examples: 3394 - name: slowdown.2 num_bytes: 2196967643.356 num_examples: 3394 - name: slowdown.3 num_bytes: 2636047081.356 num_examples: 3394 - name: pitch_up.1 num_bytes: 1648113341.356 num_examples: 3394 - name: pitch_up.2 num_bytes: 1648113341.356 num_examples: 3394 - name: pitch_up.3 num_bytes: 1648113341.356 num_examples: 3394 - name: pitch_down.1 num_bytes: 1648113341.356 num_examples: 3394 - name: pitch_down.2 num_bytes: 1648113341.356 num_examples: 3394 - name: pitch_down.3 num_bytes: 1648113341.356 num_examples: 3394 - name: rir.1 num_bytes: 1755612473.356 num_examples: 3394 - name: rir.2 num_bytes: 1806508473.356 num_examples: 3394 - name: rir.3 num_bytes: 1821740473.356 num_examples: 3394 - name: real_rir.1 num_bytes: 1666887689.356 num_examples: 3394 - name: real_rir.2 num_bytes: 1738836201.356 num_examples: 3394 - name: real_rir.3 num_bytes: 1764380853.356 num_examples: 3394 - name: resample.1 num_bytes: 1648113369.356 num_examples: 3394 - name: resample.2 num_bytes: 1648113363.356 num_examples: 3394 - name: resample.3 num_bytes: 1648113411.356 num_examples: 3394 - name: gain.1 num_bytes: 1648113341.356 num_examples: 3394 - name: gain.2 num_bytes: 1648113341.356 num_examples: 3394 - name: gain.3 num_bytes: 1648113341.356 num_examples: 3394 - name: echo.1 num_bytes: 1661689341.356 num_examples: 3394 - name: echo.2 num_bytes: 1675265341.356 num_examples: 3394 - name: echo.3 num_bytes: 1702417341.356 num_examples: 3394 - name: phaser.1 num_bytes: 1648113341.356 num_examples: 3394 - name: phaser.2 num_bytes: 1648113341.356 num_examples: 3394 - name: phaser.3 num_bytes: 1648113341.356 num_examples: 3394 - name: tempo_up.1 num_bytes: 1318802103.356 num_examples: 3394 - name: tempo_up.2 num_bytes: 1099261101.356 num_examples: 3394 - name: tempo_up.3 num_bytes: 942446355.356 num_examples: 3394 - name: tempo_down.1 num_bytes: 1883335523.356 num_examples: 3394 - name: tempo_down.2 num_bytes: 2196965581.356 num_examples: 3394 - name: tempo_down.3 num_bytes: 2636047065.356 num_examples: 3394 - name: lowpass.1 num_bytes: 1648113341.356 num_examples: 3394 - name: lowpass.2 num_bytes: 1648113341.356 num_examples: 3394 - name: lowpass.3 num_bytes: 1648113341.356 num_examples: 3394 - name: highpass.1 num_bytes: 1648113341.356 num_examples: 3394 - name: highpass.2 num_bytes: 1648113341.356 num_examples: 3394 - name: highpass.3 num_bytes: 1648113341.356 num_examples: 3394 - name: music.1 num_bytes: 1648113341.356 num_examples: 3394 - name: music.2 num_bytes: 1648113341.356 num_examples: 3394 - name: music.3 num_bytes: 1648113341.356 num_examples: 3394 - name: crosstalk.1 num_bytes: 1648113341.356 num_examples: 3394 - name: crosstalk.2 num_bytes: 1648113341.356 num_examples: 3394 - name: crosstalk.3 num_bytes: 1648113341.356 num_examples: 3394 - name: tremolo.1 num_bytes: 1648113341.356 num_examples: 3394 - name: tremolo.2 num_bytes: 1648113341.356 num_examples: 3394 - name: tremolo.3 num_bytes: 1648113341.356 num_examples: 3394 - name: treble.1 num_bytes: 1648113341.356 num_examples: 3394 - name: treble.2 num_bytes: 1648113341.356 num_examples: 3394 - name: treble.3 num_bytes: 1648113341.356 num_examples: 3394 - name: bass.1 num_bytes: 1648113341.356 num_examples: 3394 - name: bass.2 num_bytes: 1648113341.356 num_examples: 3394 - name: bass.3 num_bytes: 1648113341.356 num_examples: 3394 - name: chorus.1 num_bytes: 1652674877.356 num_examples: 3394 - name: chorus.2 num_bytes: 1654847037.356 num_examples: 3394 - name: chorus.3 num_bytes: 1657019197.356 num_examples: 3394 - name: gnoise.4 num_bytes: 1648113341.356 num_examples: 3394 - name: env_noise.4 num_bytes: 1648113341.356 num_examples: 3394 - name: env_noise_esc50.4 num_bytes: 1648113341.356 num_examples: 3394 - name: env_noise_musan.4 num_bytes: 1648113341.356 num_examples: 3394 - name: env_noise_wham.4 num_bytes: 1648113341.356 num_examples: 3394 - name: speedup.4 num_bytes: 824835247.356 num_examples: 3394 - name: slowdown.4 num_bytes: 3294669551.356 num_examples: 3394 - name: pitch_up.4 num_bytes: 1648113341.356 num_examples: 3394 - name: pitch_down.4 num_bytes: 1648113341.356 num_examples: 3394 - name: rir.4 num_bytes: 1846956473.356 num_examples: 3394 - name: real_rir.4 num_bytes: 2846504095.356 num_examples: 3394 - name: resample.4 num_bytes: 1648113451.356 num_examples: 3394 - name: gain.4 num_bytes: 1648113341.356 num_examples: 3394 - name: echo.4 num_bytes: 1756721341.356 num_examples: 3394 - name: phaser.4 num_bytes: 1648113341.356 num_examples: 3394 - name: tempo_up.4 num_bytes: 824835247.356 num_examples: 3394 - name: tempo_down.4 num_bytes: 3294669551.356 num_examples: 3394 - name: lowpass.4 num_bytes: 1648113341.356 num_examples: 3394 - name: highpass.4 num_bytes: 1648113341.356 num_examples: 3394 - name: music.4 num_bytes: 1648113341.356 num_examples: 3394 - name: crosstalk.4 num_bytes: 1648113341.356 num_examples: 3394 - name: tremolo.4 num_bytes: 1648113341.356 num_examples: 3394 - name: treble.4 num_bytes: 1648113341.356 num_examples: 3394 - name: bass.4 num_bytes: 1648113341.356 num_examples: 3394 - name: chorus.4 num_bytes: 1659191357.356 num_examples: 3394 download_size: 163104340817 dataset_size: 169131696059.59995 - config_name: multilingual_librispeech-spanish_test features: - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: text dtype: string - name: speaker_id dtype: int64 - name: chapter_id dtype: int64 - name: id dtype: string splits: - name: None.0 num_bytes: 596762288.01 num_examples: 2385 - name: env_noise.1 num_bytes: 1153485830.17 num_examples: 2385 - name: env_noise.2 num_bytes: 1153485830.17 num_examples: 2385 - name: env_noise.3 num_bytes: 1153485830.17 num_examples: 2385 - name: env_noise.4 num_bytes: 1153485830.17 num_examples: 2385 - name: rir.1 num_bytes: 1268493860.17 num_examples: 2385 - name: rir.2 num_bytes: 1252109860.17 num_examples: 2385 - name: rir.3 num_bytes: 1249517860.17 num_examples: 2385 - name: rir.4 num_bytes: 1222893860.17 num_examples: 2385 - name: speedup.1 num_bytes: 923001764.17 num_examples: 2385 - name: speedup.2 num_bytes: 769347364.17 num_examples: 2385 - name: speedup.3 num_bytes: 659593516.17 num_examples: 2385 - name: speedup.4 num_bytes: 577275652.17 num_examples: 2385 - name: slowdown.1 num_bytes: 1318119422.17 num_examples: 2385 - name: slowdown.2 num_bytes: 1537627530.17 num_examples: 2385 - name: slowdown.3 num_bytes: 1844938056.17 num_examples: 2385 - name: slowdown.4 num_bytes: 2305906194.17 num_examples: 2385 - name: pitch_up.3 num_bytes: 1153485830.17 num_examples: 2385 - name: pitch_up.4 num_bytes: 1153485830.17 num_examples: 2385 - name: pitch_down.1 num_bytes: 1153485830.17 num_examples: 2385 - name: pitch_down.2 num_bytes: 1153485830.17 num_examples: 2385 - name: pitch_down.3 num_bytes: 1153485830.17 num_examples: 2385 - name: pitch_down.4 num_bytes: 1153485830.17 num_examples: 2385 - name: pitch_up.1 num_bytes: 1153485821.72 num_examples: 2385 - name: pitch_up.2 num_bytes: 1153485821.72 num_examples: 2385 - name: resample.2 num_bytes: 1153485842.17 num_examples: 2385 - name: gain.1 num_bytes: 1153485830.17 num_examples: 2385 - name: gain.2 num_bytes: 1153485830.17 num_examples: 2385 - name: gain.3 num_bytes: 1153485830.17 num_examples: 2385 - name: gain.4 num_bytes: 1153485830.17 num_examples: 2385 - name: echo.1 num_bytes: 1163025830.17 num_examples: 2385 - name: echo.2 num_bytes: 1172565830.17 num_examples: 2385 - name: echo.3 num_bytes: 1191645830.17 num_examples: 2385 - name: echo.4 num_bytes: 1229805830.17 num_examples: 2385 - name: tempo_up.1 num_bytes: 923001758.17 num_examples: 2385 - name: tempo_up.2 num_bytes: 769345632.17 num_examples: 2385 - name: tempo_up.3 num_bytes: 659591372.17 num_examples: 2385 - name: tempo_up.4 num_bytes: 577275652.17 num_examples: 2385 - name: tempo_down.1 num_bytes: 1318117252.17 num_examples: 2385 - name: tempo_down.2 num_bytes: 1537626028.17 num_examples: 2385 - name: tempo_down.3 num_bytes: 1844938048.17 num_examples: 2385 - name: tempo_down.4 num_bytes: 2305906194.17 num_examples: 2385 - name: phaser.1 num_bytes: 1153485830.17 num_examples: 2385 - name: phaser.2 num_bytes: 1153485830.17 num_examples: 2385 - name: phaser.3 num_bytes: 1153485830.17 num_examples: 2385 - name: phaser.4 num_bytes: 1153485830.17 num_examples: 2385 - name: resample.1 num_bytes: 1153485840.17 num_examples: 2385 - name: resample.3 num_bytes: 1153485850.17 num_examples: 2385 - name: resample.4 num_bytes: 1153485882.17 num_examples: 2385 - name: lowpass.1 num_bytes: 1153485830.17 num_examples: 2385 - name: lowpass.2 num_bytes: 1153485830.17 num_examples: 2385 - name: lowpass.3 num_bytes: 1153485830.17 num_examples: 2385 - name: lowpass.4 num_bytes: 1153485830.17 num_examples: 2385 - name: highpass.1 num_bytes: 1153485830.17 num_examples: 2385 - name: highpass.2 num_bytes: 1153485830.17 num_examples: 2385 - name: highpass.3 num_bytes: 1153485830.17 num_examples: 2385 - name: highpass.4 num_bytes: 1153485830.17 num_examples: 2385 - name: gnoise.1 num_bytes: 1153485822.49 num_examples: 2385 - name: gnoise.2 num_bytes: 1153485822.49 num_examples: 2385 - name: gnoise.3 num_bytes: 1153485822.49 num_examples: 2385 - name: gnoise.4 num_bytes: 1153485822.49 num_examples: 2385 - name: env_noise_esc50.1 num_bytes: 1153485822.49 num_examples: 2385 - name: env_noise_esc50.2 num_bytes: 1153485822.49 num_examples: 2385 - name: env_noise_esc50.3 num_bytes: 1153485822.49 num_examples: 2385 - name: env_noise_esc50.4 num_bytes: 1153485822.49 num_examples: 2385 - name: env_noise_musan.1 num_bytes: 1153485822.49 num_examples: 2385 - name: env_noise_musan.2 num_bytes: 1153485822.49 num_examples: 2385 - name: env_noise_musan.3 num_bytes: 1153485822.49 num_examples: 2385 - name: env_noise_musan.4 num_bytes: 1153485822.49 num_examples: 2385 - name: music.1 num_bytes: 1153485822.49 num_examples: 2385 - name: music.2 num_bytes: 1153485822.49 num_examples: 2385 - name: music.3 num_bytes: 1153485822.49 num_examples: 2385 - name: music.4 num_bytes: 1153485822.49 num_examples: 2385 - name: crosstalk.1 num_bytes: 1153485822.49 num_examples: 2385 - name: crosstalk.2 num_bytes: 1153485822.49 num_examples: 2385 - name: crosstalk.3 num_bytes: 1153485822.49 num_examples: 2385 - name: crosstalk.4 num_bytes: 1153485822.49 num_examples: 2385 - name: env_noise_wham.1 num_bytes: 1153485822.49 num_examples: 2385 - name: env_noise_wham.2 num_bytes: 1153485822.49 num_examples: 2385 - name: env_noise_wham.3 num_bytes: 1153485822.49 num_examples: 2385 - name: env_noise_wham.4 num_bytes: 1153485822.49 num_examples: 2385 - name: tremolo.1 num_bytes: 1153485822.49 num_examples: 2385 - name: tremolo.2 num_bytes: 1153485822.49 num_examples: 2385 - name: tremolo.4 num_bytes: 1153485822.49 num_examples: 2385 - name: treble.1 num_bytes: 1153485822.49 num_examples: 2385 - name: treble.2 num_bytes: 1153485822.49 num_examples: 2385 - name: treble.3 num_bytes: 1153485822.49 num_examples: 2385 - name: treble.4 num_bytes: 1153485822.49 num_examples: 2385 - name: bass.1 num_bytes: 1153485822.49 num_examples: 2385 - name: bass.2 num_bytes: 1153485822.49 num_examples: 2385 - name: bass.3 num_bytes: 1153485822.49 num_examples: 2385 - name: bass.4 num_bytes: 1153485822.49 num_examples: 2385 - name: chorus.1 num_bytes: 1156691262.49 num_examples: 2385 - name: chorus.2 num_bytes: 1158217662.49 num_examples: 2385 - name: chorus.3 num_bytes: 1159744062.49 num_examples: 2385 - name: chorus.4 num_bytes: 1161270462.49 num_examples: 2385 - name: tremolo.3 num_bytes: 1153485822.49 num_examples: 2385 - name: voice_conversion_bark.1 num_bytes: 1457427139.875 num_examples: 2385 download_size: 119056891470 dataset_size: 114748819328.10516 - config_name: multilingual_librispeech-spanish_test_pertEval_500_30 features: - name: file dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: text dtype: string - name: speaker_id dtype: int64 - name: chapter_id dtype: int64 - name: id dtype: string - name: pert_idx dtype: int64 splits: - name: gnoise.1 num_bytes: 7341021960.0 num_examples: 15000 - name: env_noise_esc50.1 num_bytes: 7341021960.0 num_examples: 15000 download_size: 14645523867 dataset_size: 14682043920.0 - config_name: tedlium-release3_test features: - name: audio dtype: audio: sampling_rate: 16000 - name: text dtype: string - name: speaker_id dtype: string - name: gender dtype: class_label: names: '0': unknown '1': female '2': male - name: file dtype: string - name: id dtype: string splits: - name: None.0 num_bytes: 277376247.9680054 num_examples: 1155 - name: speedup.1 num_bytes: 221990159.49965963 num_examples: 1155 - name: speedup.2 num_bytes: 185066240.47311097 num_examples: 1155 - name: speedup.3 num_bytes: 158691929.4792376 num_examples: 1155 - name: slowdown.1 num_bytes: 316938966.95371 num_examples: 1155 - name: slowdown.2 num_bytes: 369687787.0762423 num_examples: 1155 - name: slowdown.3 num_bytes: 443535996.23893803 num_examples: 1155 - name: pitch_up.1 num_bytes: 277376247.9680054 num_examples: 1155 - name: pitch_up.2 num_bytes: 277376247.9680054 num_examples: 1155 - name: pitch_up.3 num_bytes: 277376247.9680054 num_examples: 1155 - name: pitch_down.1 num_bytes: 277376247.9680054 num_examples: 1155 - name: pitch_down.2 num_bytes: 277376247.9680054 num_examples: 1155 - name: pitch_down.3 num_bytes: 277376247.9680054 num_examples: 1155 - name: rir.1 num_bytes: 313788218.1586113 num_examples: 1155 - name: rir.2 num_bytes: 330268000.32334924 num_examples: 1155 - name: rir.3 num_bytes: 336608313.46153843 num_examples: 1155 - name: voice_conversion_vctk.1 num_bytes: 216990920.87134105 num_examples: 1155 - name: resample.1 num_bytes: 277376301.4329476 num_examples: 1155 - name: resample.2 num_bytes: 277376301.4329476 num_examples: 1155 - name: resample.3 num_bytes: 277376354.89788973 num_examples: 1155 - name: gain.1 num_bytes: 277376247.9680054 num_examples: 1155 - name: gain.2 num_bytes: 277376247.9680054 num_examples: 1155 - name: gain.3 num_bytes: 277376247.9680054 num_examples: 1155 - name: echo.1 num_bytes: 281996247.9680054 num_examples: 1155 - name: echo.2 num_bytes: 286616247.9680054 num_examples: 1155 - name: echo.3 num_bytes: 295856247.9680054 num_examples: 1155 - name: phaser.1 num_bytes: 277376247.9680054 num_examples: 1155 - name: phaser.2 num_bytes: 277376247.9680054 num_examples: 1155 - name: phaser.3 num_bytes: 277376247.9680054 num_examples: 1155 - name: tempo_up.1 num_bytes: 221989786.81756297 num_examples: 1155 - name: tempo_up.2 num_bytes: 185065496.68141592 num_examples: 1155 - name: tempo_up.3 num_bytes: 158690987.55275697 num_examples: 1155 - name: tempo_down.1 num_bytes: 316938020.3097345 num_examples: 1155 - name: tempo_down.2 num_bytes: 369686999.254595 num_examples: 1155 - name: tempo_down.3 num_bytes: 443535631.41933286 num_examples: 1155 - name: lowpass.1 num_bytes: 277376247.9680054 num_examples: 1155 - name: lowpass.2 num_bytes: 277376247.9680054 num_examples: 1155 - name: lowpass.3 num_bytes: 277376247.9680054 num_examples: 1155 - name: highpass.1 num_bytes: 277376247.9680054 num_examples: 1155 - name: highpass.2 num_bytes: 277376247.9680054 num_examples: 1155 - name: highpass.3 num_bytes: 277376247.9680054 num_examples: 1155 - name: speedup.4 num_bytes: 138910125.75561607 num_examples: 1155 - name: slowdown.4 num_bytes: 554308545.8577263 num_examples: 1155 - name: pitch_up.4 num_bytes: 277376247.9680054 num_examples: 1155 - name: pitch_down.4 num_bytes: 277376247.9680054 num_examples: 1155 - name: rir.4 num_bytes: 345514943.8223281 num_examples: 1155 - name: resample.4 num_bytes: 277376474.4077604 num_examples: 1155 - name: gain.4 num_bytes: 277376247.9680054 num_examples: 1155 - name: echo.4 num_bytes: 314336247.9680054 num_examples: 1155 - name: phaser.4 num_bytes: 277376247.9680054 num_examples: 1155 - name: tempo_up.4 num_bytes: 138910125.75561607 num_examples: 1155 - name: tempo_down.4 num_bytes: 554308545.8577263 num_examples: 1155 - name: lowpass.4 num_bytes: 277376247.9680054 num_examples: 1155 - name: highpass.4 num_bytes: 277376247.9680054 num_examples: 1155 - name: gnoise.1 num_bytes: 277376247.9680054 num_examples: 1155 - name: gnoise.2 num_bytes: 277376247.9680054 num_examples: 1155 - name: gnoise.3 num_bytes: 277376247.9680054 num_examples: 1155 - name: music.1 num_bytes: 301958728.16 num_examples: 1155 - name: music.2 num_bytes: 301958728.16 num_examples: 1155 - name: music.3 num_bytes: 301958728.16 num_examples: 1155 - name: music.4 num_bytes: 301958728.16 num_examples: 1155 - name: crosstalk.1 num_bytes: 301958728.16 num_examples: 1155 - name: env_noise_esc50.1 num_bytes: 277376247.9680054 num_examples: 1155 - name: env_noise_esc50.2 num_bytes: 277376247.9680054 num_examples: 1155 - name: env_noise_esc50.3 num_bytes: 277376247.9680054 num_examples: 1155 - name: gnoise.4 num_bytes: 277376247.9680054 num_examples: 1155 - name: crosstalk.2 num_bytes: 301958728.16 num_examples: 1155 - name: env_noise_esc50.4 num_bytes: 277376247.9680054 num_examples: 1155 - name: crosstalk.3 num_bytes: 301958728.16 num_examples: 1155 - name: crosstalk.4 num_bytes: 301958728.16 num_examples: 1155 - name: env_noise_musan.1 num_bytes: 301958728.16 num_examples: 1155 - name: env_noise_musan.2 num_bytes: 301958728.16 num_examples: 1155 - name: env_noise_musan.3 num_bytes: 301958728.16 num_examples: 1155 - name: env_noise_musan.4 num_bytes: 301958728.16 num_examples: 1155 - name: real_rir.1 num_bytes: 308750878.16 num_examples: 1155 - name: real_rir.2 num_bytes: 333286988.16 num_examples: 1155 - name: real_rir.3 num_bytes: 341205738.16 num_examples: 1155 - name: real_rir.4 num_bytes: 715155314.16 num_examples: 1155 - name: env_noise.1 num_bytes: 301958728.16 num_examples: 1155 - name: env_noise.2 num_bytes: 301958728.16 num_examples: 1155 - name: env_noise.3 num_bytes: 301958728.16 num_examples: 1155 - name: env_noise.4 num_bytes: 301958728.16 num_examples: 1155 - name: env_noise_wham.1 num_bytes: 301958728.16 num_examples: 1155 - name: env_noise_wham.2 num_bytes: 301958728.16 num_examples: 1155 - name: env_noise_wham.3 num_bytes: 301958728.16 num_examples: 1155 - name: env_noise_wham.4 num_bytes: 301958728.16 num_examples: 1155 - name: tremolo.1 num_bytes: 301958728.16 num_examples: 1155 - name: tremolo.2 num_bytes: 301958728.16 num_examples: 1155 - name: tremolo.3 num_bytes: 301958728.16 num_examples: 1155 - name: tremolo.4 num_bytes: 301958728.16 num_examples: 1155 - name: treble.1 num_bytes: 301958728.16 num_examples: 1155 - name: treble.2 num_bytes: 301958728.16 num_examples: 1155 - name: treble.3 num_bytes: 301958728.16 num_examples: 1155 - name: treble.4 num_bytes: 301958728.16 num_examples: 1155 - name: bass.1 num_bytes: 301958728.16 num_examples: 1155 - name: bass.2 num_bytes: 301958728.16 num_examples: 1155 - name: bass.3 num_bytes: 301958728.16 num_examples: 1155 - name: bass.4 num_bytes: 301958728.16 num_examples: 1155 - name: chorus.1 num_bytes: 303511048.16 num_examples: 1155 - name: chorus.2 num_bytes: 304250248.16 num_examples: 1155 - name: chorus.4 num_bytes: 305728648.16 num_examples: 1155 - name: chorus.3 num_bytes: 304989448.16 num_examples: 1155 download_size: 58723208514 dataset_size: 30342709961.007984 configs: - config_name: accented_cv data_files: - split: test path: accented_cv/test-* - split: test.clean path: accented_cv/test.clean-* - config_name: accented_cv_es data_files: - split: test path: accented_cv_es/test-* - config_name: accented_cv_fr data_files: - split: test path: accented_cv_fr/test-* - config_name: chime data_files: - split: farfield path: chime/farfield-* - split: nearfield path: chime/nearfield-* - config_name: in-the-wild data_files: - split: farfield path: in-the-wild/farfield-* - split: nearfield path: in-the-wild/nearfield-* - config_name: in-the-wild-AMI data_files: - split: nearfield path: in-the-wild-AMI/nearfield-* - split: farfield path: in-the-wild-AMI/farfield-* - config_name: in-the-wild-ami data_files: - split: nearfield path: in-the-wild-ami/nearfield-* - split: farfield path: in-the-wild-ami/farfield-* - config_name: librispeech_asr-test.clean data_files: - split: None.0 path: librispeech_asr-test.clean/None.0-* - split: gnoise.1 path: librispeech_asr-test.clean/gnoise.1-* - split: gnoise.2 path: librispeech_asr-test.clean/gnoise.2-* - split: gnoise.3 path: librispeech_asr-test.clean/gnoise.3-* - split: gnoise.4 path: librispeech_asr-test.clean/gnoise.4-* - split: env_noise.1 path: librispeech_asr-test.clean/env_noise.1-* - split: env_noise.2 path: librispeech_asr-test.clean/env_noise.2-* - split: env_noise.3 path: librispeech_asr-test.clean/env_noise.3-* - split: env_noise.4 path: librispeech_asr-test.clean/env_noise.4-* - split: rir.1 path: librispeech_asr-test.clean/rir.1-* - split: rir.2 path: librispeech_asr-test.clean/rir.2-* - split: rir.3 path: librispeech_asr-test.clean/rir.3-* - split: rir.4 path: librispeech_asr-test.clean/rir.4-* - split: speedup.1 path: librispeech_asr-test.clean/speedup.1-* - split: speedup.2 path: librispeech_asr-test.clean/speedup.2-* - split: speedup.3 path: librispeech_asr-test.clean/speedup.3-* - split: speedup.4 path: librispeech_asr-test.clean/speedup.4-* - split: slowdown.1 path: librispeech_asr-test.clean/slowdown.1-* - split: slowdown.2 path: librispeech_asr-test.clean/slowdown.2-* - split: slowdown.3 path: librispeech_asr-test.clean/slowdown.3-* - split: slowdown.4 path: librispeech_asr-test.clean/slowdown.4-* - split: pitch_up.3 path: librispeech_asr-test.clean/pitch_up.3-* - split: pitch_up.4 path: librispeech_asr-test.clean/pitch_up.4-* - split: pitch_down.1 path: librispeech_asr-test.clean/pitch_down.1-* - split: pitch_down.2 path: librispeech_asr-test.clean/pitch_down.2-* - split: pitch_down.3 path: librispeech_asr-test.clean/pitch_down.3-* - split: pitch_down.4 path: librispeech_asr-test.clean/pitch_down.4-* - split: pitch_up.1 path: librispeech_asr-test.clean/pitch_up.1-* - split: pitch_up.2 path: librispeech_asr-test.clean/pitch_up.2-* - split: resample.1 path: librispeech_asr-test.clean/resample.1-* - split: resample.2 path: librispeech_asr-test.clean/resample.2-* - split: resample.3 path: librispeech_asr-test.clean/resample.3-* - split: resample.4 path: librispeech_asr-test.clean/resample.4-* - split: env_noise_esc50.1 path: librispeech_asr-test.clean/env_noise_esc50.1-* - split: env_noise_esc50.2 path: librispeech_asr-test.clean/env_noise_esc50.2-* - split: env_noise_esc50.3 path: librispeech_asr-test.clean/env_noise_esc50.3-* - split: env_noise_esc50.4 path: librispeech_asr-test.clean/env_noise_esc50.4-* - split: voice_conversion.4 path: librispeech_asr-test.clean/voice_conversion.4-* - split: voice_conversion.3 path: librispeech_asr-test.clean/voice_conversion.3-* - split: voice_conversion.1 path: librispeech_asr-test.clean/voice_conversion.1-* - split: voice_conversion.2 path: librispeech_asr-test.clean/voice_conversion.2-* - split: gain.1 path: librispeech_asr-test.clean/gain.1-* - split: gain.2 path: librispeech_asr-test.clean/gain.2-* - split: gain.3 path: librispeech_asr-test.clean/gain.3-* - split: echo.1 path: librispeech_asr-test.clean/echo.1-* - split: echo.2 path: librispeech_asr-test.clean/echo.2-* - split: echo.3 path: librispeech_asr-test.clean/echo.3-* - split: echo.4 path: librispeech_asr-test.clean/echo.4-* - split: phaser.1 path: librispeech_asr-test.clean/phaser.1-* - split: phaser.2 path: librispeech_asr-test.clean/phaser.2-* - split: phaser.3 path: librispeech_asr-test.clean/phaser.3-* - split: tempo_up.1 path: librispeech_asr-test.clean/tempo_up.1-* - split: tempo_up.2 path: librispeech_asr-test.clean/tempo_up.2-* - split: tempo_up.3 path: librispeech_asr-test.clean/tempo_up.3-* - split: tempo_up.4 path: librispeech_asr-test.clean/tempo_up.4-* - split: tempo_down.1 path: librispeech_asr-test.clean/tempo_down.1-* - split: tempo_down.2 path: librispeech_asr-test.clean/tempo_down.2-* - split: tempo_down.3 path: librispeech_asr-test.clean/tempo_down.3-* - split: tempo_down.4 path: librispeech_asr-test.clean/tempo_down.4-* - split: gain.4 path: librispeech_asr-test.clean/gain.4-* - split: lowpass.1 path: librispeech_asr-test.clean/lowpass.1-* - split: lowpass.2 path: librispeech_asr-test.clean/lowpass.2-* - split: lowpass.3 path: librispeech_asr-test.clean/lowpass.3-* - split: lowpass.4 path: librispeech_asr-test.clean/lowpass.4-* - split: highpass.1 path: librispeech_asr-test.clean/highpass.1-* - split: highpass.2 path: librispeech_asr-test.clean/highpass.2-* - split: highpass.3 path: librispeech_asr-test.clean/highpass.3-* - split: highpass.4 path: librispeech_asr-test.clean/highpass.4-* - split: phaser.4 path: librispeech_asr-test.clean/phaser.4-* - split: voice_conversion_vctk.1 path: librispeech_asr-test.clean/voice_conversion_vctk.1-* - split: universal_adv.1 path: librispeech_asr-test.clean/universal_adv.1-* - split: music.1 path: librispeech_asr-test.clean/music.1-* - split: music.2 path: librispeech_asr-test.clean/music.2-* - split: music.3 path: librispeech_asr-test.clean/music.3-* - split: music.4 path: librispeech_asr-test.clean/music.4-* - split: crosstalk.1 path: librispeech_asr-test.clean/crosstalk.1-* - split: crosstalk.2 path: librispeech_asr-test.clean/crosstalk.2-* - split: crosstalk.3 path: librispeech_asr-test.clean/crosstalk.3-* - split: crosstalk.4 path: librispeech_asr-test.clean/crosstalk.4-* - split: env_noise_musan.1 path: librispeech_asr-test.clean/env_noise_musan.1-* - split: env_noise_musan.2 path: librispeech_asr-test.clean/env_noise_musan.2-* - split: env_noise_musan.3 path: librispeech_asr-test.clean/env_noise_musan.3-* - split: env_noise_musan.4 path: librispeech_asr-test.clean/env_noise_musan.4-* - split: real_rir.1 path: librispeech_asr-test.clean/real_rir.1-* - split: real_rir.2 path: librispeech_asr-test.clean/real_rir.2-* - split: real_rir.3 path: librispeech_asr-test.clean/real_rir.3-* - split: real_rir.4 path: librispeech_asr-test.clean/real_rir.4-* - split: env_noise_wham.1 path: librispeech_asr-test.clean/env_noise_wham.1-* - split: env_noise_wham.2 path: librispeech_asr-test.clean/env_noise_wham.2-* - split: env_noise_wham.3 path: librispeech_asr-test.clean/env_noise_wham.3-* - split: env_noise_wham.4 path: librispeech_asr-test.clean/env_noise_wham.4-* - split: tremolo.1 path: librispeech_asr-test.clean/tremolo.1-* - split: tremolo.2 path: librispeech_asr-test.clean/tremolo.2-* - split: tremolo.3 path: librispeech_asr-test.clean/tremolo.3-* - split: tremolo.4 path: librispeech_asr-test.clean/tremolo.4-* - split: treble.1 path: librispeech_asr-test.clean/treble.1-* - split: treble.2 path: librispeech_asr-test.clean/treble.2-* - split: treble.3 path: librispeech_asr-test.clean/treble.3-* - split: treble.4 path: librispeech_asr-test.clean/treble.4-* - split: bass.1 path: librispeech_asr-test.clean/bass.1-* - split: bass.2 path: librispeech_asr-test.clean/bass.2-* - split: bass.3 path: librispeech_asr-test.clean/bass.3-* - split: bass.4 path: librispeech_asr-test.clean/bass.4-* - split: chorus.1 path: librispeech_asr-test.clean/chorus.1-* - split: chorus.2 path: librispeech_asr-test.clean/chorus.2-* - split: chorus.3 path: librispeech_asr-test.clean/chorus.3-* - split: chorus.4 path: librispeech_asr-test.clean/chorus.4-* - config_name: librispeech_asr-test.clean_pertEval_500_30 data_files: - split: gnoise.1 path: librispeech_asr-test.clean_pertEval_500_30/gnoise.1-* - split: env_noise_esc50.1 path: librispeech_asr-test.clean_pertEval_500_30/env_noise_esc50.1-* - config_name: multilingual_librispeech-french_test data_files: - split: gnoise.1 path: multilingual_librispeech-french_test/gnoise.1-* - split: gnoise.2 path: multilingual_librispeech-french_test/gnoise.2-* - split: gnoise.3 path: multilingual_librispeech-french_test/gnoise.3-* - split: speedup.1 path: multilingual_librispeech-french_test/speedup.1-* - split: speedup.2 path: multilingual_librispeech-french_test/speedup.2-* - split: speedup.3 path: multilingual_librispeech-french_test/speedup.3-* - split: slowdown.1 path: multilingual_librispeech-french_test/slowdown.1-* - split: slowdown.2 path: multilingual_librispeech-french_test/slowdown.2-* - split: slowdown.3 path: multilingual_librispeech-french_test/slowdown.3-* - split: pitch_up.1 path: multilingual_librispeech-french_test/pitch_up.1-* - split: pitch_up.2 path: multilingual_librispeech-french_test/pitch_up.2-* - split: pitch_up.3 path: multilingual_librispeech-french_test/pitch_up.3-* - split: pitch_down.1 path: multilingual_librispeech-french_test/pitch_down.1-* - split: pitch_down.2 path: multilingual_librispeech-french_test/pitch_down.2-* - split: env_noise.1 path: multilingual_librispeech-french_test/env_noise.1-* - split: env_noise.3 path: multilingual_librispeech-french_test/env_noise.3-* - split: env_noise_wham.1 path: multilingual_librispeech-french_test/env_noise_wham.1-* - split: env_noise_wham.2 path: multilingual_librispeech-french_test/env_noise_wham.2-* - split: real_rir.3 path: multilingual_librispeech-french_test/real_rir.3-* - split: env_noise.2 path: multilingual_librispeech-french_test/env_noise.2-* - split: env_noise_esc50.1 path: multilingual_librispeech-french_test/env_noise_esc50.1-* - split: env_noise_esc50.2 path: multilingual_librispeech-french_test/env_noise_esc50.2-* - split: env_noise_esc50.3 path: multilingual_librispeech-french_test/env_noise_esc50.3-* - split: env_noise_musan.1 path: multilingual_librispeech-french_test/env_noise_musan.1-* - split: env_noise_musan.2 path: multilingual_librispeech-french_test/env_noise_musan.2-* - split: env_noise_musan.3 path: multilingual_librispeech-french_test/env_noise_musan.3-* - split: env_noise_wham.3 path: multilingual_librispeech-french_test/env_noise_wham.3-* - split: pitch_down.3 path: multilingual_librispeech-french_test/pitch_down.3-* - split: rir.1 path: multilingual_librispeech-french_test/rir.1-* - split: rir.2 path: multilingual_librispeech-french_test/rir.2-* - split: rir.3 path: multilingual_librispeech-french_test/rir.3-* - split: real_rir.1 path: multilingual_librispeech-french_test/real_rir.1-* - split: real_rir.2 path: multilingual_librispeech-french_test/real_rir.2-* - split: resample.1 path: multilingual_librispeech-french_test/resample.1-* - split: resample.2 path: multilingual_librispeech-french_test/resample.2-* - split: resample.3 path: multilingual_librispeech-french_test/resample.3-* - split: gain.1 path: multilingual_librispeech-french_test/gain.1-* - split: gain.2 path: multilingual_librispeech-french_test/gain.2-* - split: gain.3 path: multilingual_librispeech-french_test/gain.3-* - split: echo.1 path: multilingual_librispeech-french_test/echo.1-* - split: echo.2 path: multilingual_librispeech-french_test/echo.2-* - split: echo.3 path: multilingual_librispeech-french_test/echo.3-* - split: phaser.1 path: multilingual_librispeech-french_test/phaser.1-* - split: phaser.2 path: multilingual_librispeech-french_test/phaser.2-* - split: phaser.3 path: multilingual_librispeech-french_test/phaser.3-* - split: tempo_up.1 path: multilingual_librispeech-french_test/tempo_up.1-* - split: tempo_up.2 path: multilingual_librispeech-french_test/tempo_up.2-* - split: tempo_up.3 path: multilingual_librispeech-french_test/tempo_up.3-* - split: tempo_down.1 path: multilingual_librispeech-french_test/tempo_down.1-* - split: tempo_down.2 path: multilingual_librispeech-french_test/tempo_down.2-* - split: tempo_down.3 path: multilingual_librispeech-french_test/tempo_down.3-* - split: lowpass.1 path: multilingual_librispeech-french_test/lowpass.1-* - split: lowpass.2 path: multilingual_librispeech-french_test/lowpass.2-* - split: lowpass.3 path: multilingual_librispeech-french_test/lowpass.3-* - split: highpass.1 path: multilingual_librispeech-french_test/highpass.1-* - split: highpass.2 path: multilingual_librispeech-french_test/highpass.2-* - split: highpass.3 path: multilingual_librispeech-french_test/highpass.3-* - split: music.1 path: multilingual_librispeech-french_test/music.1-* - split: music.2 path: multilingual_librispeech-french_test/music.2-* - split: music.3 path: multilingual_librispeech-french_test/music.3-* - split: crosstalk.1 path: multilingual_librispeech-french_test/crosstalk.1-* - split: crosstalk.2 path: multilingual_librispeech-french_test/crosstalk.2-* - split: crosstalk.3 path: multilingual_librispeech-french_test/crosstalk.3-* - split: tremolo.1 path: multilingual_librispeech-french_test/tremolo.1-* - split: tremolo.2 path: multilingual_librispeech-french_test/tremolo.2-* - split: tremolo.3 path: multilingual_librispeech-french_test/tremolo.3-* - split: treble.1 path: multilingual_librispeech-french_test/treble.1-* - split: treble.2 path: multilingual_librispeech-french_test/treble.2-* - split: treble.3 path: multilingual_librispeech-french_test/treble.3-* - split: bass.1 path: multilingual_librispeech-french_test/bass.1-* - split: bass.2 path: multilingual_librispeech-french_test/bass.2-* - split: bass.3 path: multilingual_librispeech-french_test/bass.3-* - split: chorus.1 path: multilingual_librispeech-french_test/chorus.1-* - split: chorus.2 path: multilingual_librispeech-french_test/chorus.2-* - split: chorus.3 path: multilingual_librispeech-french_test/chorus.3-* - split: gnoise.4 path: multilingual_librispeech-french_test/gnoise.4-* - split: env_noise.4 path: multilingual_librispeech-french_test/env_noise.4-* - split: env_noise_esc50.4 path: multilingual_librispeech-french_test/env_noise_esc50.4-* - split: env_noise_musan.4 path: multilingual_librispeech-french_test/env_noise_musan.4-* - split: env_noise_wham.4 path: multilingual_librispeech-french_test/env_noise_wham.4-* - split: speedup.4 path: multilingual_librispeech-french_test/speedup.4-* - split: slowdown.4 path: multilingual_librispeech-french_test/slowdown.4-* - split: pitch_up.4 path: multilingual_librispeech-french_test/pitch_up.4-* - split: pitch_down.4 path: multilingual_librispeech-french_test/pitch_down.4-* - split: rir.4 path: multilingual_librispeech-french_test/rir.4-* - split: real_rir.4 path: multilingual_librispeech-french_test/real_rir.4-* - split: resample.4 path: multilingual_librispeech-french_test/resample.4-* - split: gain.4 path: multilingual_librispeech-french_test/gain.4-* - split: echo.4 path: multilingual_librispeech-french_test/echo.4-* - split: phaser.4 path: multilingual_librispeech-french_test/phaser.4-* - split: tempo_up.4 path: multilingual_librispeech-french_test/tempo_up.4-* - split: tempo_down.4 path: multilingual_librispeech-french_test/tempo_down.4-* - split: lowpass.4 path: multilingual_librispeech-french_test/lowpass.4-* - split: highpass.4 path: multilingual_librispeech-french_test/highpass.4-* - split: music.4 path: multilingual_librispeech-french_test/music.4-* - split: crosstalk.4 path: multilingual_librispeech-french_test/crosstalk.4-* - split: tremolo.4 path: multilingual_librispeech-french_test/tremolo.4-* - split: treble.4 path: multilingual_librispeech-french_test/treble.4-* - split: bass.4 path: multilingual_librispeech-french_test/bass.4-* - split: chorus.4 path: multilingual_librispeech-french_test/chorus.4-* - config_name: multilingual_librispeech-german_test data_files: - split: gnoise.1 path: multilingual_librispeech-german_test/gnoise.1-* - split: gnoise.2 path: multilingual_librispeech-german_test/gnoise.2-* - split: gnoise.3 path: multilingual_librispeech-german_test/gnoise.3-* - split: env_noise.1 path: multilingual_librispeech-german_test/env_noise.1-* - split: env_noise.2 path: multilingual_librispeech-german_test/env_noise.2-* - split: env_noise.3 path: multilingual_librispeech-german_test/env_noise.3-* - split: env_noise_esc50.1 path: multilingual_librispeech-german_test/env_noise_esc50.1-* - split: env_noise_esc50.2 path: multilingual_librispeech-german_test/env_noise_esc50.2-* - split: env_noise_esc50.3 path: multilingual_librispeech-german_test/env_noise_esc50.3-* - split: env_noise_musan.1 path: multilingual_librispeech-german_test/env_noise_musan.1-* - split: env_noise_musan.2 path: multilingual_librispeech-german_test/env_noise_musan.2-* - split: env_noise_musan.3 path: multilingual_librispeech-german_test/env_noise_musan.3-* - split: env_noise_wham.1 path: multilingual_librispeech-german_test/env_noise_wham.1-* - split: env_noise_wham.2 path: multilingual_librispeech-german_test/env_noise_wham.2-* - split: env_noise_wham.3 path: multilingual_librispeech-german_test/env_noise_wham.3-* - split: speedup.1 path: multilingual_librispeech-german_test/speedup.1-* - split: speedup.2 path: multilingual_librispeech-german_test/speedup.2-* - split: speedup.3 path: multilingual_librispeech-german_test/speedup.3-* - split: slowdown.1 path: multilingual_librispeech-german_test/slowdown.1-* - split: slowdown.2 path: multilingual_librispeech-german_test/slowdown.2-* - split: slowdown.3 path: multilingual_librispeech-german_test/slowdown.3-* - split: pitch_up.1 path: multilingual_librispeech-german_test/pitch_up.1-* - split: pitch_up.2 path: multilingual_librispeech-german_test/pitch_up.2-* - split: pitch_up.3 path: multilingual_librispeech-german_test/pitch_up.3-* - split: pitch_down.1 path: multilingual_librispeech-german_test/pitch_down.1-* - split: pitch_down.2 path: multilingual_librispeech-german_test/pitch_down.2-* - split: pitch_down.3 path: multilingual_librispeech-german_test/pitch_down.3-* - split: rir.1 path: multilingual_librispeech-german_test/rir.1-* - split: rir.2 path: multilingual_librispeech-german_test/rir.2-* - split: rir.3 path: multilingual_librispeech-german_test/rir.3-* - split: real_rir.1 path: multilingual_librispeech-german_test/real_rir.1-* - split: real_rir.2 path: multilingual_librispeech-german_test/real_rir.2-* - split: real_rir.3 path: multilingual_librispeech-german_test/real_rir.3-* - split: resample.1 path: multilingual_librispeech-german_test/resample.1-* - split: resample.2 path: multilingual_librispeech-german_test/resample.2-* - split: resample.3 path: multilingual_librispeech-german_test/resample.3-* - split: gain.1 path: multilingual_librispeech-german_test/gain.1-* - split: gain.2 path: multilingual_librispeech-german_test/gain.2-* - split: gain.3 path: multilingual_librispeech-german_test/gain.3-* - split: echo.1 path: multilingual_librispeech-german_test/echo.1-* - split: echo.2 path: multilingual_librispeech-german_test/echo.2-* - split: echo.3 path: multilingual_librispeech-german_test/echo.3-* - split: phaser.1 path: multilingual_librispeech-german_test/phaser.1-* - split: phaser.2 path: multilingual_librispeech-german_test/phaser.2-* - split: phaser.3 path: multilingual_librispeech-german_test/phaser.3-* - split: tempo_up.1 path: multilingual_librispeech-german_test/tempo_up.1-* - split: tempo_up.2 path: multilingual_librispeech-german_test/tempo_up.2-* - split: tempo_up.3 path: multilingual_librispeech-german_test/tempo_up.3-* - split: tempo_down.1 path: multilingual_librispeech-german_test/tempo_down.1-* - split: tempo_down.2 path: multilingual_librispeech-german_test/tempo_down.2-* - split: tempo_down.3 path: multilingual_librispeech-german_test/tempo_down.3-* - split: lowpass.1 path: multilingual_librispeech-german_test/lowpass.1-* - split: lowpass.2 path: multilingual_librispeech-german_test/lowpass.2-* - split: lowpass.3 path: multilingual_librispeech-german_test/lowpass.3-* - split: highpass.1 path: multilingual_librispeech-german_test/highpass.1-* - split: highpass.2 path: multilingual_librispeech-german_test/highpass.2-* - split: highpass.3 path: multilingual_librispeech-german_test/highpass.3-* - split: music.1 path: multilingual_librispeech-german_test/music.1-* - split: music.2 path: multilingual_librispeech-german_test/music.2-* - split: music.3 path: multilingual_librispeech-german_test/music.3-* - split: crosstalk.1 path: multilingual_librispeech-german_test/crosstalk.1-* - split: crosstalk.2 path: multilingual_librispeech-german_test/crosstalk.2-* - split: crosstalk.3 path: multilingual_librispeech-german_test/crosstalk.3-* - split: tremolo.1 path: multilingual_librispeech-german_test/tremolo.1-* - split: tremolo.2 path: multilingual_librispeech-german_test/tremolo.2-* - split: tremolo.3 path: multilingual_librispeech-german_test/tremolo.3-* - split: treble.1 path: multilingual_librispeech-german_test/treble.1-* - split: treble.2 path: multilingual_librispeech-german_test/treble.2-* - split: treble.3 path: multilingual_librispeech-german_test/treble.3-* - split: bass.1 path: multilingual_librispeech-german_test/bass.1-* - split: bass.2 path: multilingual_librispeech-german_test/bass.2-* - split: bass.3 path: multilingual_librispeech-german_test/bass.3-* - split: chorus.1 path: multilingual_librispeech-german_test/chorus.1-* - split: chorus.2 path: multilingual_librispeech-german_test/chorus.2-* - split: chorus.3 path: multilingual_librispeech-german_test/chorus.3-* - split: gnoise.4 path: multilingual_librispeech-german_test/gnoise.4-* - split: env_noise.4 path: multilingual_librispeech-german_test/env_noise.4-* - split: env_noise_esc50.4 path: multilingual_librispeech-german_test/env_noise_esc50.4-* - split: env_noise_musan.4 path: multilingual_librispeech-german_test/env_noise_musan.4-* - split: env_noise_wham.4 path: multilingual_librispeech-german_test/env_noise_wham.4-* - split: speedup.4 path: multilingual_librispeech-german_test/speedup.4-* - split: slowdown.4 path: multilingual_librispeech-german_test/slowdown.4-* - split: pitch_up.4 path: multilingual_librispeech-german_test/pitch_up.4-* - split: pitch_down.4 path: multilingual_librispeech-german_test/pitch_down.4-* - split: rir.4 path: multilingual_librispeech-german_test/rir.4-* - split: real_rir.4 path: multilingual_librispeech-german_test/real_rir.4-* - split: resample.4 path: multilingual_librispeech-german_test/resample.4-* - split: gain.4 path: multilingual_librispeech-german_test/gain.4-* - split: echo.4 path: multilingual_librispeech-german_test/echo.4-* - split: phaser.4 path: multilingual_librispeech-german_test/phaser.4-* - split: tempo_up.4 path: multilingual_librispeech-german_test/tempo_up.4-* - split: tempo_down.4 path: multilingual_librispeech-german_test/tempo_down.4-* - split: lowpass.4 path: multilingual_librispeech-german_test/lowpass.4-* - split: highpass.4 path: multilingual_librispeech-german_test/highpass.4-* - split: music.4 path: multilingual_librispeech-german_test/music.4-* - split: crosstalk.4 path: multilingual_librispeech-german_test/crosstalk.4-* - split: tremolo.4 path: multilingual_librispeech-german_test/tremolo.4-* - split: treble.4 path: multilingual_librispeech-german_test/treble.4-* - split: bass.4 path: multilingual_librispeech-german_test/bass.4-* - split: chorus.4 path: multilingual_librispeech-german_test/chorus.4-* - config_name: multilingual_librispeech-spanish_test data_files: - split: None.0 path: multilingual_librispeech-spanish_test/None.0-* - split: gnoise.1 path: multilingual_librispeech-spanish_test/gnoise.1-* - split: gnoise.2 path: multilingual_librispeech-spanish_test/gnoise.2-* - split: gnoise.3 path: multilingual_librispeech-spanish_test/gnoise.3-* - split: gnoise.4 path: multilingual_librispeech-spanish_test/gnoise.4-* - split: env_noise.1 path: multilingual_librispeech-spanish_test/env_noise.1-* - split: env_noise.2 path: multilingual_librispeech-spanish_test/env_noise.2-* - split: env_noise.3 path: multilingual_librispeech-spanish_test/env_noise.3-* - split: env_noise.4 path: multilingual_librispeech-spanish_test/env_noise.4-* - split: rir.1 path: multilingual_librispeech-spanish_test/rir.1-* - split: rir.2 path: multilingual_librispeech-spanish_test/rir.2-* - split: rir.3 path: multilingual_librispeech-spanish_test/rir.3-* - split: rir.4 path: multilingual_librispeech-spanish_test/rir.4-* - split: speedup.1 path: multilingual_librispeech-spanish_test/speedup.1-* - split: speedup.2 path: multilingual_librispeech-spanish_test/speedup.2-* - split: speedup.3 path: multilingual_librispeech-spanish_test/speedup.3-* - split: speedup.4 path: multilingual_librispeech-spanish_test/speedup.4-* - split: slowdown.1 path: multilingual_librispeech-spanish_test/slowdown.1-* - split: slowdown.2 path: multilingual_librispeech-spanish_test/slowdown.2-* - split: slowdown.3 path: multilingual_librispeech-spanish_test/slowdown.3-* - split: slowdown.4 path: multilingual_librispeech-spanish_test/slowdown.4-* - split: pitch_up.3 path: multilingual_librispeech-spanish_test/pitch_up.3-* - split: pitch_up.4 path: multilingual_librispeech-spanish_test/pitch_up.4-* - split: pitch_down.1 path: multilingual_librispeech-spanish_test/pitch_down.1-* - split: pitch_down.2 path: multilingual_librispeech-spanish_test/pitch_down.2-* - split: pitch_down.3 path: multilingual_librispeech-spanish_test/pitch_down.3-* - split: pitch_down.4 path: multilingual_librispeech-spanish_test/pitch_down.4-* - split: pitch_up.1 path: multilingual_librispeech-spanish_test/pitch_up.1-* - split: pitch_up.2 path: multilingual_librispeech-spanish_test/pitch_up.2-* - split: resample.2 path: multilingual_librispeech-spanish_test/resample.2-* - split: resample.3 path: multilingual_librispeech-spanish_test/resample.3-* - split: resample.4 path: multilingual_librispeech-spanish_test/resample.4-* - split: env_noise_esc50.1 path: multilingual_librispeech-spanish_test/env_noise_esc50.1-* - split: env_noise_esc50.2 path: multilingual_librispeech-spanish_test/env_noise_esc50.2-* - split: env_noise_esc50.3 path: multilingual_librispeech-spanish_test/env_noise_esc50.3-* - split: env_noise_esc50.4 path: multilingual_librispeech-spanish_test/env_noise_esc50.4-* - split: resample.1 path: multilingual_librispeech-spanish_test/resample.1-* - split: gain.1 path: multilingual_librispeech-spanish_test/gain.1-* - split: gain.2 path: multilingual_librispeech-spanish_test/gain.2-* - split: gain.3 path: multilingual_librispeech-spanish_test/gain.3-* - split: gain.4 path: multilingual_librispeech-spanish_test/gain.4-* - split: echo.4 path: multilingual_librispeech-spanish_test/echo.4-* - split: echo.1 path: multilingual_librispeech-spanish_test/echo.1-* - split: echo.2 path: multilingual_librispeech-spanish_test/echo.2-* - split: echo.3 path: multilingual_librispeech-spanish_test/echo.3-* - split: tempo_up.1 path: multilingual_librispeech-spanish_test/tempo_up.1-* - split: tempo_up.2 path: multilingual_librispeech-spanish_test/tempo_up.2-* - split: tempo_up.3 path: multilingual_librispeech-spanish_test/tempo_up.3-* - split: tempo_up.4 path: multilingual_librispeech-spanish_test/tempo_up.4-* - split: tempo_down.1 path: multilingual_librispeech-spanish_test/tempo_down.1-* - split: tempo_down.2 path: multilingual_librispeech-spanish_test/tempo_down.2-* - split: tempo_down.3 path: multilingual_librispeech-spanish_test/tempo_down.3-* - split: tempo_down.4 path: multilingual_librispeech-spanish_test/tempo_down.4-* - split: lowpass.1 path: multilingual_librispeech-spanish_test/lowpass.1-* - split: lowpass.2 path: multilingual_librispeech-spanish_test/lowpass.2-* - split: lowpass.3 path: multilingual_librispeech-spanish_test/lowpass.3-* - split: lowpass.4 path: multilingual_librispeech-spanish_test/lowpass.4-* - split: highpass.1 path: multilingual_librispeech-spanish_test/highpass.1-* - split: highpass.2 path: multilingual_librispeech-spanish_test/highpass.2-* - split: highpass.3 path: multilingual_librispeech-spanish_test/highpass.3-* - split: highpass.4 path: multilingual_librispeech-spanish_test/highpass.4-* - split: phaser.1 path: multilingual_librispeech-spanish_test/phaser.1-* - split: phaser.2 path: multilingual_librispeech-spanish_test/phaser.2-* - split: phaser.3 path: multilingual_librispeech-spanish_test/phaser.3-* - split: phaser.4 path: multilingual_librispeech-spanish_test/phaser.4-* - split: env_noise_musan.1 path: multilingual_librispeech-spanish_test/env_noise_musan.1-* - split: env_noise_musan.2 path: multilingual_librispeech-spanish_test/env_noise_musan.2-* - split: env_noise_musan.3 path: multilingual_librispeech-spanish_test/env_noise_musan.3-* - split: env_noise_musan.4 path: multilingual_librispeech-spanish_test/env_noise_musan.4-* - split: music.1 path: multilingual_librispeech-spanish_test/music.1-* - split: music.2 path: multilingual_librispeech-spanish_test/music.2-* - split: music.3 path: multilingual_librispeech-spanish_test/music.3-* - split: music.4 path: multilingual_librispeech-spanish_test/music.4-* - split: crosstalk.1 path: multilingual_librispeech-spanish_test/crosstalk.1-* - split: crosstalk.2 path: multilingual_librispeech-spanish_test/crosstalk.2-* - split: crosstalk.3 path: multilingual_librispeech-spanish_test/crosstalk.3-* - split: crosstalk.4 path: multilingual_librispeech-spanish_test/crosstalk.4-* - split: env_noise_wham.1 path: multilingual_librispeech-spanish_test/env_noise_wham.1-* - split: env_noise_wham.2 path: multilingual_librispeech-spanish_test/env_noise_wham.2-* - split: env_noise_wham.3 path: multilingual_librispeech-spanish_test/env_noise_wham.3-* - split: env_noise_wham.4 path: multilingual_librispeech-spanish_test/env_noise_wham.4-* - split: tremolo.1 path: multilingual_librispeech-spanish_test/tremolo.1-* - split: tremolo.2 path: multilingual_librispeech-spanish_test/tremolo.2-* - split: tremolo.4 path: multilingual_librispeech-spanish_test/tremolo.4-* - split: treble.1 path: multilingual_librispeech-spanish_test/treble.1-* - split: treble.2 path: multilingual_librispeech-spanish_test/treble.2-* - split: treble.3 path: multilingual_librispeech-spanish_test/treble.3-* - split: treble.4 path: multilingual_librispeech-spanish_test/treble.4-* - split: bass.1 path: multilingual_librispeech-spanish_test/bass.1-* - split: bass.2 path: multilingual_librispeech-spanish_test/bass.2-* - split: bass.3 path: multilingual_librispeech-spanish_test/bass.3-* - split: bass.4 path: multilingual_librispeech-spanish_test/bass.4-* - split: chorus.1 path: multilingual_librispeech-spanish_test/chorus.1-* - split: chorus.2 path: multilingual_librispeech-spanish_test/chorus.2-* - split: chorus.3 path: multilingual_librispeech-spanish_test/chorus.3-* - split: chorus.4 path: multilingual_librispeech-spanish_test/chorus.4-* - split: tremolo.3 path: multilingual_librispeech-spanish_test/tremolo.3-* - split: voice_conversion_bark.1 path: multilingual_librispeech-spanish_test/voice_conversion_bark.1-* - config_name: multilingual_librispeech-spanish_test_pertEval_500_30 data_files: - split: gnoise.1 path: multilingual_librispeech-spanish_test_pertEval_500_30/gnoise.1-* - split: env_noise_esc50.1 path: multilingual_librispeech-spanish_test_pertEval_500_30/env_noise_esc50.1-* - config_name: tedlium-release3_test data_files: - split: gnoise.1 path: tedlium-release3_test/gnoise.1-* - split: gnoise.2 path: tedlium-release3_test/gnoise.2-* - split: gnoise.3 path: tedlium-release3_test/gnoise.3-* - split: env_noise_esc50.1 path: tedlium-release3_test/env_noise_esc50.1-* - split: env_noise_esc50.2 path: tedlium-release3_test/env_noise_esc50.2-* - split: env_noise_esc50.3 path: tedlium-release3_test/env_noise_esc50.3-* - split: speedup.1 path: tedlium-release3_test/speedup.1-* - split: speedup.2 path: tedlium-release3_test/speedup.2-* - split: speedup.3 path: tedlium-release3_test/speedup.3-* - split: slowdown.1 path: tedlium-release3_test/slowdown.1-* - split: slowdown.2 path: tedlium-release3_test/slowdown.2-* - split: slowdown.3 path: tedlium-release3_test/slowdown.3-* - split: pitch_up.1 path: tedlium-release3_test/pitch_up.1-* - split: pitch_up.2 path: tedlium-release3_test/pitch_up.2-* - split: pitch_up.3 path: tedlium-release3_test/pitch_up.3-* - split: pitch_down.1 path: tedlium-release3_test/pitch_down.1-* - split: pitch_down.2 path: tedlium-release3_test/pitch_down.2-* - split: pitch_down.3 path: tedlium-release3_test/pitch_down.3-* - split: rir.1 path: tedlium-release3_test/rir.1-* - split: rir.2 path: tedlium-release3_test/rir.2-* - split: rir.3 path: tedlium-release3_test/rir.3-* - split: voice_conversion_vctk.1 path: tedlium-release3_test/voice_conversion_vctk.1-* - split: resample.1 path: tedlium-release3_test/resample.1-* - split: resample.2 path: tedlium-release3_test/resample.2-* - split: resample.3 path: tedlium-release3_test/resample.3-* - split: gain.1 path: tedlium-release3_test/gain.1-* - split: gain.2 path: tedlium-release3_test/gain.2-* - split: gain.3 path: tedlium-release3_test/gain.3-* - split: echo.1 path: tedlium-release3_test/echo.1-* - split: echo.2 path: tedlium-release3_test/echo.2-* - split: echo.3 path: tedlium-release3_test/echo.3-* - split: phaser.1 path: tedlium-release3_test/phaser.1-* - split: phaser.2 path: tedlium-release3_test/phaser.2-* - split: phaser.3 path: tedlium-release3_test/phaser.3-* - split: tempo_up.1 path: tedlium-release3_test/tempo_up.1-* - split: tempo_up.2 path: tedlium-release3_test/tempo_up.2-* - split: tempo_up.3 path: tedlium-release3_test/tempo_up.3-* - split: tempo_down.1 path: tedlium-release3_test/tempo_down.1-* - split: tempo_down.2 path: tedlium-release3_test/tempo_down.2-* - split: tempo_down.3 path: tedlium-release3_test/tempo_down.3-* - split: lowpass.1 path: tedlium-release3_test/lowpass.1-* - split: lowpass.2 path: tedlium-release3_test/lowpass.2-* - split: lowpass.3 path: tedlium-release3_test/lowpass.3-* - split: highpass.1 path: tedlium-release3_test/highpass.1-* - split: highpass.2 path: tedlium-release3_test/highpass.2-* - split: highpass.3 path: tedlium-release3_test/highpass.3-* - split: gnoise.4 path: tedlium-release3_test/gnoise.4-* - split: env_noise_esc50.4 path: tedlium-release3_test/env_noise_esc50.4-* - split: speedup.4 path: tedlium-release3_test/speedup.4-* - split: slowdown.4 path: tedlium-release3_test/slowdown.4-* - split: pitch_up.4 path: tedlium-release3_test/pitch_up.4-* - split: pitch_down.4 path: tedlium-release3_test/pitch_down.4-* - split: rir.4 path: tedlium-release3_test/rir.4-* - split: resample.4 path: tedlium-release3_test/resample.4-* - split: gain.4 path: tedlium-release3_test/gain.4-* - split: echo.4 path: tedlium-release3_test/echo.4-* - split: phaser.4 path: tedlium-release3_test/phaser.4-* - split: tempo_up.4 path: tedlium-release3_test/tempo_up.4-* - split: tempo_down.4 path: tedlium-release3_test/tempo_down.4-* - split: lowpass.4 path: tedlium-release3_test/lowpass.4-* - split: highpass.4 path: tedlium-release3_test/highpass.4-* - split: None.0 path: tedlium-release3_test/None.0-* - split: music.1 path: tedlium-release3_test/music.1-* - split: music.2 path: tedlium-release3_test/music.2-* - split: music.3 path: tedlium-release3_test/music.3-* - split: music.4 path: tedlium-release3_test/music.4-* - split: crosstalk.1 path: tedlium-release3_test/crosstalk.1-* - split: crosstalk.2 path: tedlium-release3_test/crosstalk.2-* - split: crosstalk.3 path: tedlium-release3_test/crosstalk.3-* - split: crosstalk.4 path: tedlium-release3_test/crosstalk.4-* - split: env_noise_musan.1 path: tedlium-release3_test/env_noise_musan.1-* - split: env_noise_musan.2 path: tedlium-release3_test/env_noise_musan.2-* - split: env_noise_musan.3 path: tedlium-release3_test/env_noise_musan.3-* - split: env_noise_musan.4 path: tedlium-release3_test/env_noise_musan.4-* - split: real_rir.1 path: tedlium-release3_test/real_rir.1-* - split: real_rir.2 path: tedlium-release3_test/real_rir.2-* - split: real_rir.3 path: tedlium-release3_test/real_rir.3-* - split: real_rir.4 path: tedlium-release3_test/real_rir.4-* - split: env_noise.1 path: tedlium-release3_test/env_noise.1-* - split: env_noise.2 path: tedlium-release3_test/env_noise.2-* - split: env_noise.3 path: tedlium-release3_test/env_noise.3-* - split: env_noise.4 path: tedlium-release3_test/env_noise.4-* - split: env_noise_wham.1 path: tedlium-release3_test/env_noise_wham.1-* - split: env_noise_wham.2 path: tedlium-release3_test/env_noise_wham.2-* - split: env_noise_wham.3 path: tedlium-release3_test/env_noise_wham.3-* - split: env_noise_wham.4 path: tedlium-release3_test/env_noise_wham.4-* - split: tremolo.1 path: tedlium-release3_test/tremolo.1-* - split: tremolo.2 path: tedlium-release3_test/tremolo.2-* - split: tremolo.3 path: tedlium-release3_test/tremolo.3-* - split: tremolo.4 path: tedlium-release3_test/tremolo.4-* - split: treble.1 path: tedlium-release3_test/treble.1-* - split: treble.2 path: tedlium-release3_test/treble.2-* - split: treble.3 path: tedlium-release3_test/treble.3-* - split: treble.4 path: tedlium-release3_test/treble.4-* - split: bass.1 path: tedlium-release3_test/bass.1-* - split: bass.2 path: tedlium-release3_test/bass.2-* - split: bass.3 path: tedlium-release3_test/bass.3-* - split: bass.4 path: tedlium-release3_test/bass.4-* - split: chorus.1 path: tedlium-release3_test/chorus.1-* - split: chorus.2 path: tedlium-release3_test/chorus.2-* - split: chorus.4 path: tedlium-release3_test/chorus.4-* - split: chorus.3 path: tedlium-release3_test/chorus.3-* --- # Dataset Card for "speech_robust_bench" [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)

lukaemon/bbh

lukaemon

--- dataset_info: - config_name: boolean_expressions features: - name: input dtype: string - name: target dtype: string splits: - name: test num_bytes: 11790 num_examples: 250 download_size: 17172 dataset_size: 11790 - config_name: causal_judgement features: - name: input dtype: string - name: target dtype: string splits: - name: test num_bytes: 198021 num_examples: 187 download_size: 202943 dataset_size: 198021 - config_name: date_understanding features: - name: input dtype: string - name: target dtype: string splits: - name: test num_bytes: 54666 num_examples: 250 download_size: 61760 dataset_size: 54666 - config_name: disambiguation_qa features: - name: input dtype: string - name: target dtype: string splits: - name: test num_bytes: 78620 num_examples: 250 download_size: 85255 dataset_size: 78620 - config_name: dyck_languages features: - name: input dtype: string - name: target dtype: string splits: - name: test num_bytes: 38432 num_examples: 250 download_size: 43814 dataset_size: 38432 - config_name: formal_fallacies features: - name: input dtype: string - name: target dtype: string splits: - name: test num_bytes: 138224 num_examples: 250 download_size: 145562 dataset_size: 138224 - config_name: geometric_shapes features: - name: input dtype: string - name: target dtype: string splits: - name: test num_bytes: 68560 num_examples: 250 download_size: 77242 dataset_size: 68560 - config_name: hyperbaton features: - name: input dtype: string - name: target dtype: string splits: - name: test num_bytes: 38574 num_examples: 250 download_size: 44706 dataset_size: 38574 - config_name: logical_deduction_five_objects features: - name: input dtype: string - name: target dtype: string splits: - name: test num_bytes: 148595 num_examples: 250 download_size: 155477 dataset_size: 148595 - config_name: logical_deduction_seven_objects features: - name: input dtype: string - name: target dtype: string splits: - name: test num_bytes: 191022 num_examples: 250 download_size: 198404 dataset_size: 191022 - config_name: logical_deduction_three_objects features: - name: input dtype: string - name: target dtype: string splits: - name: test num_bytes: 105831 num_examples: 250 download_size: 112213 dataset_size: 105831 - config_name: movie_recommendation features: - name: input dtype: string - name: target dtype: string splits: - name: test num_bytes: 50985 num_examples: 250 download_size: 57684 dataset_size: 50985 - config_name: multistep_arithmetic_two features: - name: input dtype: string - name: target dtype: string splits: - name: test num_bytes: 12943 num_examples: 250 download_size: 18325 dataset_size: 12943 - config_name: navigate features: - name: input dtype: string - name: target dtype: string splits: - name: test num_bytes: 49031 num_examples: 250 download_size: 55163 dataset_size: 49031 - config_name: object_counting features: - name: input dtype: string - name: target dtype: string splits: - name: test num_bytes: 30508 num_examples: 250 download_size: 35890 dataset_size: 30508 - config_name: penguins_in_a_table features: - name: input dtype: string - name: target dtype: string splits: - name: test num_bytes: 70062 num_examples: 146 download_size: 74516 dataset_size: 70062 - config_name: reasoning_about_colored_objects features: - name: input dtype: string - name: target dtype: string splits: - name: test num_bytes: 89579 num_examples: 250 download_size: 98694 dataset_size: 89579 - config_name: ruin_names features: - name: input dtype: string - name: target dtype: string splits: - name: test num_bytes: 46537 num_examples: 250 download_size: 53178 dataset_size: 46537 - config_name: salient_translation_error_detection features: - name: input dtype: string - name: target dtype: string splits: - name: test num_bytes: 277110 num_examples: 250 download_size: 286443 dataset_size: 277110 - config_name: snarks features: - name: input dtype: string - name: target dtype: string splits: - name: test num_bytes: 38223 num_examples: 178 download_size: 42646 dataset_size: 38223 - config_name: sports_understanding features: - name: input dtype: string - name: target dtype: string splits: - name: test num_bytes: 22723 num_examples: 250 download_size: 28617 dataset_size: 22723 - config_name: temporal_sequences features: - name: input dtype: string - name: target dtype: string splits: - name: test num_bytes: 139546 num_examples: 250 download_size: 148176 dataset_size: 139546 - config_name: tracking_shuffled_objects_five_objects features: - name: input dtype: string - name: target dtype: string splits: - name: test num_bytes: 162590 num_examples: 250 download_size: 169722 dataset_size: 162590 - config_name: tracking_shuffled_objects_seven_objects features: - name: input dtype: string - name: target dtype: string splits: - name: test num_bytes: 207274 num_examples: 250 download_size: 214906 dataset_size: 207274 - config_name: tracking_shuffled_objects_three_objects features: - name: input dtype: string - name: target dtype: string splits: - name: test num_bytes: 122104 num_examples: 250 download_size: 128736 dataset_size: 122104 - config_name: web_of_lies features: - name: input dtype: string - name: target dtype: string splits: - name: test num_bytes: 47582 num_examples: 250 download_size: 52964 dataset_size: 47582 - config_name: word_sorting features: - name: input dtype: string - name: target dtype: string splits: - name: test num_bytes: 60918 num_examples: 250 download_size: 66300 dataset_size: 60918 --- # BIG-bench Hard dataset homepage: https://github.com/suzgunmirac/BIG-Bench-Hard ``` @article{suzgun2022challenging, title={Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them}, author={Suzgun, Mirac and Scales, Nathan and Sch{\"a}rli, Nathanael and Gehrmann, Sebastian and Tay, Yi and Chung, Hyung Won and Chowdhery, Aakanksha and Le, Quoc V and Chi, Ed H and Zhou, Denny and and Wei, Jason}, journal={arXiv preprint arXiv:2210.09261}, year={2022} } ```

liwu/MNBVC

liwu

--- annotations_creators: - other language: - zh language_creators: - other license: - mit multilinguality: - monolingual pretty_name: MNBVC size_categories: - unknown source_datasets: - original task_categories: - text-generation - fill-mask task_ids: - language-modeling - masked-language-modeling --- # Dataset Card for MNBVC ## Table of Contents - [Dataset Card for MNBVC](#dataset-card-for-mnbvc) - [Table of Contents](#table-of-contents) - [Dataset Description](#dataset-description) - [数据集介绍](#数据集介绍) - [数据子集](#数据子集) - [数据格式](#数据格式) - [文本数据](#文本数据) - [问答数据](#问答数据) - [Contributions](#contributions) ## Dataset Description - **Homepage:** http://mnbvc.253874.net/ - **Repository:** https://github.com/esbatmop/MNBVC - **Paper:** N/A - **Leaderboard:** N/A - **Point of Contact:** N/A ### 数据集介绍 中文互联网上最古老最神秘(没有之一)的里屋社区于2023.1.1庄重宣布: 在英明神武的里屋管子带领下，决心发挥社区所长(哪都长)，帮助开源社区长期更新一份最大的中文互联网语料集。 Huggingface上的MNBVC数据集在逐渐更新中，请到[https://github.com/esbatmop/MNBVC](https://github.com/esbatmop/MNBVC) 获取未完成清洗的更多数据。 可以使用如下脚本加载： ```python from datasets import load_dataset dataset = load_dataset("liwu/MNBVC", 'law_judgement', split='train', streaming=True) next(iter(dataset)) # get the first line ``` ## 数据子集 MNBVC数据集包含数个子集： - `law_judgement`: 来自法律文书的文本。 - `gov_xuexiqiangguo`: 来自学习强国的文本。 - `gov_report`: 来自政府工作报告的文本。 - `co_ann_report`: 企业年报文本。 - `code_metadata`: 代码元数据。 - `qa_zhihu`: 来自[知乎](https://huggingface.co./datasets/wangrui6/Zhihu-KOL)的问答数据。 - `qa_wikihow`: 来自wikihow的问答数据。 - `qa_mfa`: 外交部问答数据。 - `news_peoples_daily`: 来自人民日报的文本数据。 - `wikipedia`: 来自维基百科的文本数据。 - `qa_stackexchange`: 来自StackExchange的问答数据。 - `qa_chatgpt`: 使用ChatGPT构造的问答语料，感谢[genggui001](https://github.com/genggui001)贡献语料。 - `math`: - `math_qa `: 和数学领域有关的问答数据。 - `emath` :中国数学爱好者论坛语料数据 - `math_chat`: 和数学领域有关的对话数据数据，可以提升模型Chain of Thought的能力。 - `crawler_oscar`: 从CommonCrawl中清洗出来的通用文本数据。 - `game` : 一些游戏的平行语料数据。 - `Hogwarts_legacy` : 霍格沃茨指遗 - `The_Wither_3` : 巫师三 ## 数据格式 目前MNBVC数据集包含如下几类数据： - 通用文本 - 问答语料 - 代码语料 - 多轮对话 - 论坛语料 - 平行语料 可以在[MNBVC的wiki页面](https://wiki.mnbvc.org/doku.php/%E7%8E%B0%E6%9C%89%E8%AF%AD%E6%96%99%E6%A0%BC%E5%BC%8F)上查看这几类数据的具体格式。 项目早期所上传的数据使用如下格式，以后这一格式会被废弃，相应数据也会重新上传： ```json { "text": datasets.Value("string"), "meta": datasets.Value("string") } ``` ### Contributions Thanks to the [Liwu community](http://mnbvc.253874.net/) for constructing this dataset. Thanks to [silver](https://github.com/silverriver) and [jiaming](https://huggingface.co./Yjiaming) for adding and uploading this dataset to Huggingface. ### Citation Please cite the repo if you use the data or code in this repo. ``` @misc{mnbvc, author = {{MOP-LIWU Community} and {MNBVC Team}}, title = {MNBVC: Massive Never-ending BT Vast Chinese corpus}, year = {2023}, publisher = {GitHub}, journal = {GitHub repository}, howpublished = {\url{https://github.com/esbatmop/MNBVC}}, } ```

OpenGVLab/OmniCorpus-CC

OpenGVLab

--- language: - en license: cc-by-4.0 size_categories: - 100M<n<1B task_categories: - image-to-text - visual-question-answering dataset_info: - config_name: CC-MAIN-2013-20 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 19908676196 num_examples: 3878063 download_size: 9303464923 dataset_size: 19908676196 - config_name: CC-MAIN-2013-48 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 15282078925 num_examples: 3091537 download_size: 6965036866 dataset_size: 15282078925 - config_name: CC-MAIN-2014-10 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 7227087609 num_examples: 1390034 download_size: 3259239561 dataset_size: 7227087609 - config_name: CC-MAIN-2014-15 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 10106913108 num_examples: 1968361 download_size: 4567738362 dataset_size: 10106913108 - config_name: CC-MAIN-2014-23 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 7997621043 num_examples: 1455331 download_size: 3468852905 dataset_size: 7997621043 - config_name: CC-MAIN-2014-35 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 6228103779 num_examples: 1219200 download_size: 2849584613 dataset_size: 6228103779 - config_name: CC-MAIN-2014-41 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 8321822952 num_examples: 1573955 download_size: 3775989970 dataset_size: 8321822952 - config_name: CC-MAIN-2014-42 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 7732679416 num_examples: 1511931 download_size: 3505766162 dataset_size: 7732679416 - config_name: CC-MAIN-2014-49 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 4473311810 num_examples: 837735 download_size: 1982728919 dataset_size: 4473311810 - config_name: CC-MAIN-2014-52 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 7292722888 num_examples: 1304730 download_size: 2957626766 dataset_size: 7292722888 - config_name: CC-MAIN-2015-06 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 5775826679 num_examples: 1061940 download_size: 2462379667 dataset_size: 5775826679 - config_name: CC-MAIN-2015-11 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 6263650452 num_examples: 1129411 download_size: 2528026633 dataset_size: 6263650452 - config_name: CC-MAIN-2015-14 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 4524425019 num_examples: 885221 download_size: 1939222111 dataset_size: 4524425019 - config_name: CC-MAIN-2015-18 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 6195227565 num_examples: 1104115 download_size: 2634204322 dataset_size: 6195227565 - config_name: CC-MAIN-2015-22 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 7008276790 num_examples: 1290530 download_size: 2913627974 dataset_size: 7008276790 - config_name: CC-MAIN-2015-27 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 4320140953 num_examples: 784496 download_size: 1828575226 dataset_size: 4320140953 - config_name: CC-MAIN-2015-32 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 4952806590 num_examples: 875601 download_size: 2065207099 dataset_size: 4952806590 - config_name: CC-MAIN-2015-35 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 6053257306 num_examples: 1086470 download_size: 2632032769 dataset_size: 6053257306 - config_name: CC-MAIN-2015-40 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 5206096790 num_examples: 924036 download_size: 2203603087 dataset_size: 5206096790 - config_name: CC-MAIN-2015-48 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 8343050753 num_examples: 1537468 download_size: 3489600630 dataset_size: 8343050753 - config_name: CC-MAIN-2016-07 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 9329220105 num_examples: 1738650 download_size: 4005599785 dataset_size: 9329220105 - config_name: CC-MAIN-2016-18 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 3897220786 num_examples: 747570 download_size: 1675500816 dataset_size: 3897220786 - config_name: CC-MAIN-2016-22 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 4623903344 num_examples: 857060 download_size: 2000624854 dataset_size: 4623903344 - config_name: CC-MAIN-2016-26 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 3414418701 num_examples: 627995 download_size: 1403890884 dataset_size: 3414418701 - config_name: CC-MAIN-2016-30 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 7244342539 num_examples: 1183776 download_size: 2913394840 dataset_size: 7244342539 - config_name: CC-MAIN-2016-36 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 5402565529 num_examples: 915878 download_size: 2248454753 dataset_size: 5402565529 - config_name: CC-MAIN-2016-40 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 5938544915 num_examples: 1113534 download_size: 2530904625 dataset_size: 5938544915 - config_name: CC-MAIN-2016-44 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 15819536321 num_examples: 3528637 download_size: 6516546200 dataset_size: 15819536321 - config_name: CC-MAIN-2016-50 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 10822695594 num_examples: 2215939 download_size: 4439728574 dataset_size: 10822695594 - config_name: CC-MAIN-2017-04 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 11949732148 num_examples: 2441316 download_size: 5045763620 dataset_size: 11949732148 - config_name: CC-MAIN-2017-09 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 12473370126 num_examples: 2561539 download_size: 5398993614 dataset_size: 12473370126 - config_name: CC-MAIN-2017-13 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 12209904783 num_examples: 2458486 download_size: 5422393873 dataset_size: 12209904783 - config_name: CC-MAIN-2017-17 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 13763109013 num_examples: 2615558 download_size: 6025106556 dataset_size: 13763109013 - config_name: CC-MAIN-2017-22 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 14456991831 num_examples: 2775332 download_size: 6258001465 dataset_size: 14456991831 - config_name: CC-MAIN-2017-26 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 15036103558 num_examples: 2973499 download_size: 6813218532 dataset_size: 15036103558 - config_name: CC-MAIN-2017-30 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 18833639414 num_examples: 3870197 download_size: 8464443468 dataset_size: 18833639414 - config_name: CC-MAIN-2017-34 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 25828116836 num_examples: 4848154 download_size: 11599137919 dataset_size: 25828116836 - config_name: CC-MAIN-2017-39 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 29432150311 num_examples: 4840435 download_size: 13172655761 dataset_size: 29432150311 - config_name: CC-MAIN-2017-43 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 32672966840 num_examples: 5724493 download_size: 15041820212 dataset_size: 32672966840 - config_name: CC-MAIN-2017-47 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 34301891443 num_examples: 5291581 download_size: 15593452226 dataset_size: 34301891443 - config_name: CC-MAIN-2017-51 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 30012533603 num_examples: 5466672 download_size: 14005518471 dataset_size: 30012533603 - config_name: CC-MAIN-2018-05 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 47738703452 num_examples: 8053879 download_size: 22533983733 dataset_size: 47738703452 - config_name: CC-MAIN-2018-09 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 45503126107 num_examples: 8045410 download_size: 21900491411 dataset_size: 45503126107 - config_name: CC-MAIN-2018-13 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 43904789090 num_examples: 7980931 download_size: 21178075620 dataset_size: 43904789090 - config_name: CC-MAIN-2018-17 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 44481167440 num_examples: 8699878 download_size: 21623780968 dataset_size: 44481167440 - config_name: CC-MAIN-2018-22 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 64369136465 num_examples: 13332059 download_size: 32293951649 dataset_size: 64369136465 - config_name: CC-MAIN-2018-26 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 81232597180 num_examples: 16249638 download_size: 41007491366 dataset_size: 81232597180 - config_name: CC-MAIN-2018-30 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 151537007358 num_examples: 32535697 download_size: 77517210537 dataset_size: 151537007358 - config_name: CC-MAIN-2018-34 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 39026071869 num_examples: 6347230 download_size: 19285382621 dataset_size: 39026071869 - config_name: CC-MAIN-2018-39 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 35948493161 num_examples: 6372711 download_size: 17597722170 dataset_size: 35948493161 - config_name: CC-MAIN-2018-43 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 50928918805 num_examples: 8758225 download_size: 25291022646 dataset_size: 50928918805 - config_name: CC-MAIN-2018-47 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 43961213014 num_examples: 7270815 download_size: 22024998684 dataset_size: 43961213014 - config_name: CC-MAIN-2018-51 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 58902353921 num_examples: 10215384 download_size: 29497256483 dataset_size: 58902353921 - config_name: CC-MAIN-2019-04 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 54814836003 num_examples: 9930553 download_size: 27458854931 dataset_size: 54814836003 - config_name: CC-MAIN-2019-09 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 54426174385 num_examples: 8897510 download_size: 28125345656 dataset_size: 54426174385 - config_name: CC-MAIN-2019-13 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 48712051219 num_examples: 7803004 download_size: 25156014252 dataset_size: 48712051219 - config_name: CC-MAIN-2019-18 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 48203751852 num_examples: 7532171 download_size: 24844412087 dataset_size: 48203751852 - config_name: CC-MAIN-2019-22 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 51674379059 num_examples: 8339842 download_size: 26257475492 dataset_size: 51674379059 - config_name: CC-MAIN-2019-26 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 43336967638 num_examples: 7320268 download_size: 21900316910 dataset_size: 43336967638 - config_name: CC-MAIN-2019-30 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 46313133200 num_examples: 7682281 download_size: 23262218065 dataset_size: 46313133200 - config_name: CC-MAIN-2019-35 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 49570657315 num_examples: 8098108 download_size: 24938729240 dataset_size: 49570657315 - config_name: CC-MAIN-2019-39 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 43538081906 num_examples: 7102645 download_size: 21728983014 dataset_size: 43538081906 - config_name: CC-MAIN-2019-43 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 52817470138 num_examples: 8567061 download_size: 26105523209 dataset_size: 52817470138 - config_name: CC-MAIN-2019-47 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 42252827792 num_examples: 6775943 download_size: 21228532199 dataset_size: 42252827792 - config_name: CC-MAIN-2019-51 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 38926356094 num_examples: 6415558 download_size: 19510339598 dataset_size: 38926356094 - config_name: CC-MAIN-2020-05 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 48189844491 num_examples: 7921372 download_size: 24235687030 dataset_size: 48189844491 - config_name: CC-MAIN-2020-10 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 48904133840 num_examples: 8211791 download_size: 24576159189 dataset_size: 48904133840 - config_name: CC-MAIN-2020-16 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 51243682770 num_examples: 8578633 download_size: 25485035979 dataset_size: 51243682770 - config_name: CC-MAIN-2020-24 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 59424939072 num_examples: 10438139 download_size: 29827361603 dataset_size: 59424939072 - config_name: CC-MAIN-2020-29 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 66229730938 num_examples: 11475631 download_size: 33030161773 dataset_size: 66229730938 - config_name: CC-MAIN-2020-34 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 54287690582 num_examples: 9495610 download_size: 27018821467 dataset_size: 54287690582 - config_name: CC-MAIN-2020-40 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 71587907978 num_examples: 12058149 download_size: 35795677487 dataset_size: 71587907978 - config_name: CC-MAIN-2020-45 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 59172857400 num_examples: 9694734 download_size: 29495814784 dataset_size: 59172857400 - config_name: CC-MAIN-2020-50 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 58557861606 num_examples: 9539918 download_size: 29083801775 dataset_size: 58557861606 - config_name: CC-MAIN-2021-04 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 74507336015 num_examples: 12273028 download_size: 36874887518 dataset_size: 74507336015 - config_name: CC-MAIN-2021-10 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 60802783945 num_examples: 10176190 download_size: 30326513365 dataset_size: 60802783945 - config_name: CC-MAIN-2021-17 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 75061494488 num_examples: 12343366 download_size: 37345114890 dataset_size: 75061494488 - config_name: CC-MAIN-2021-21 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 70036417178 num_examples: 11584034 download_size: 34806730527 dataset_size: 70036417178 - config_name: CC-MAIN-2021-25 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 73653674063 num_examples: 12065281 download_size: 36581310312 dataset_size: 73653674063 - config_name: CC-MAIN-2021-31 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 79535885182 num_examples: 13383552 download_size: 39702500971 dataset_size: 79535885182 - config_name: CC-MAIN-2021-39 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 90302065651 num_examples: 14794773 download_size: 45211764750 dataset_size: 90302065651 - config_name: CC-MAIN-2021-43 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 108356023335 num_examples: 17698206 download_size: 54292215300 dataset_size: 108356023335 - config_name: CC-MAIN-2021-49 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 95867022229 num_examples: 15643875 download_size: 47902433321 dataset_size: 95867022229 - config_name: CC-MAIN-2022-05 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 97602903488 num_examples: 15772898 download_size: 48711364812 dataset_size: 97602903488 - config_name: CC-MAIN-2022-21 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 127495492928 num_examples: 21745889 download_size: 63379692210 dataset_size: 127495492928 - config_name: CC-MAIN-2022-27 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 128061655541 num_examples: 21580054 download_size: 63763936007 dataset_size: 128061655541 - config_name: CC-MAIN-2022-33 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 126436062118 num_examples: 21495687 download_size: 63067252044 dataset_size: 126436062118 - config_name: CC-MAIN-2022-40 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 123806739937 num_examples: 20206120 download_size: 61929035270 dataset_size: 123806739937 - config_name: CC-MAIN-2022-49 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 152577158166 num_examples: 24634059 download_size: 76529854484 dataset_size: 152577158166 - config_name: CC-MAIN-2023-06 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 174815301023 num_examples: 28962355 download_size: 87301203013 dataset_size: 174815301023 - config_name: CC-MAIN-2023-14 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 227631152876 num_examples: 37223376 download_size: 114188282465 dataset_size: 227631152876 - config_name: CC-MAIN-2023-23 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 321036722459 num_examples: 52119692 download_size: 161491274249 dataset_size: 321036722459 - config_name: CC-MAIN-2023-40 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 648032999611 num_examples: 101292016 download_size: 317965522325 dataset_size: 648032999611 - config_name: CC-MAIN-2023-50 features: - name: general_metadata struct: - name: domain sequence: string - name: fluency_prob dtype: float64 - name: id dtype: string - name: non_advertisement_prob dtype: float64 - name: politics_prob dtype: float64 - name: porn_prob dtype: float64 - name: toxic_prob dtype: float64 - name: url dtype: string - name: images sequence: string - name: texts sequence: string - name: metadata list: - name: aesthetic_prob dtype: float64 - name: bytes dtype: int64 - name: d_hash dtype: string - name: d_hash_dup_count dtype: int64 - name: height dtype: int64 - name: img_url_sha dtype: string - name: p_hash dtype: string - name: p_hash_dup_count dtype: int64 - name: unsafe_prob dtype: float64 - name: width dtype: int64 splits: - name: train num_bytes: 744768384551 num_examples: 117073004 download_size: 365332295606 dataset_size: 744768384551 configs: - config_name: CC-MAIN-2013-20 data_files: - split: train path: CC-MAIN-2013-20/train-* - config_name: CC-MAIN-2013-48 data_files: - split: train path: CC-MAIN-2013-48/train-* - config_name: CC-MAIN-2014-10 data_files: - split: train path: CC-MAIN-2014-10/train-* - config_name: CC-MAIN-2014-15 data_files: - split: train path: CC-MAIN-2014-15/train-* - config_name: CC-MAIN-2014-23 data_files: - split: train path: CC-MAIN-2014-23/train-* - config_name: CC-MAIN-2014-35 data_files: - split: train path: CC-MAIN-2014-35/train-* - config_name: CC-MAIN-2014-41 data_files: - split: train path: CC-MAIN-2014-41/train-* - config_name: CC-MAIN-2014-42 data_files: - split: train path: CC-MAIN-2014-42/train-* - config_name: CC-MAIN-2014-49 data_files: - split: train path: CC-MAIN-2014-49/train-* - config_name: CC-MAIN-2014-52 data_files: - split: train path: CC-MAIN-2014-52/train-* - config_name: CC-MAIN-2015-06 data_files: - split: train path: CC-MAIN-2015-06/train-* - config_name: CC-MAIN-2015-11 data_files: - split: train path: CC-MAIN-2015-11/train-* - config_name: CC-MAIN-2015-14 data_files: - split: train path: CC-MAIN-2015-14/train-* - config_name: CC-MAIN-2015-18 data_files: - split: train path: CC-MAIN-2015-18/train-* - config_name: CC-MAIN-2015-22 data_files: - split: train path: CC-MAIN-2015-22/train-* - config_name: CC-MAIN-2015-27 data_files: - split: train path: CC-MAIN-2015-27/train-* - config_name: CC-MAIN-2015-32 data_files: - split: train path: CC-MAIN-2015-32/train-* - config_name: CC-MAIN-2015-35 data_files: - split: train path: CC-MAIN-2015-35/train-* - config_name: CC-MAIN-2015-40 data_files: - split: train path: CC-MAIN-2015-40/train-* - config_name: CC-MAIN-2015-48 data_files: - split: train path: CC-MAIN-2015-48/train-* - config_name: CC-MAIN-2016-07 data_files: - split: train path: CC-MAIN-2016-07/train-* - config_name: CC-MAIN-2016-18 data_files: - split: train path: CC-MAIN-2016-18/train-* - config_name: CC-MAIN-2016-22 data_files: - split: train path: CC-MAIN-2016-22/train-* - config_name: CC-MAIN-2016-26 data_files: - split: train path: CC-MAIN-2016-26/train-* - config_name: CC-MAIN-2016-30 data_files: - split: train path: CC-MAIN-2016-30/train-* - config_name: CC-MAIN-2016-36 data_files: - split: train path: CC-MAIN-2016-36/train-* - config_name: CC-MAIN-2016-40 data_files: - split: train path: CC-MAIN-2016-40/train-* - config_name: CC-MAIN-2016-44 data_files: - split: train path: CC-MAIN-2016-44/train-* - config_name: CC-MAIN-2016-50 data_files: - split: train path: CC-MAIN-2016-50/train-* - config_name: CC-MAIN-2017-04 data_files: - split: train path: CC-MAIN-2017-04/train-* - config_name: CC-MAIN-2017-09 data_files: - split: train path: CC-MAIN-2017-09/train-* - config_name: CC-MAIN-2017-13 data_files: - split: train path: CC-MAIN-2017-13/train-* - config_name: CC-MAIN-2017-17 data_files: - split: train path: CC-MAIN-2017-17/train-* - config_name: CC-MAIN-2017-22 data_files: - split: train path: CC-MAIN-2017-22/train-* - config_name: CC-MAIN-2017-26 data_files: - split: train path: CC-MAIN-2017-26/train-* - config_name: CC-MAIN-2017-30 data_files: - split: train path: CC-MAIN-2017-30/train-* - config_name: CC-MAIN-2017-34 data_files: - split: train path: CC-MAIN-2017-34/train-* - config_name: CC-MAIN-2017-39 data_files: - split: train path: CC-MAIN-2017-39/train-* - config_name: CC-MAIN-2017-43 data_files: - split: train path: CC-MAIN-2017-43/train-* - config_name: CC-MAIN-2017-47 data_files: - split: train path: CC-MAIN-2017-47/train-* - config_name: CC-MAIN-2017-51 data_files: - split: train path: CC-MAIN-2017-51/train-* - config_name: CC-MAIN-2018-05 data_files: - split: train path: CC-MAIN-2018-05/train-* - config_name: CC-MAIN-2018-09 data_files: - split: train path: CC-MAIN-2018-09/train-* - config_name: CC-MAIN-2018-13 data_files: - split: train path: CC-MAIN-2018-13/train-* - config_name: CC-MAIN-2018-17 data_files: - split: train path: CC-MAIN-2018-17/train-* - config_name: CC-MAIN-2018-22 data_files: - split: train path: CC-MAIN-2018-22/train-* - config_name: CC-MAIN-2018-26 data_files: - split: train path: CC-MAIN-2018-26/train-* - config_name: CC-MAIN-2018-30 data_files: - split: train path: CC-MAIN-2018-30/train-* - config_name: CC-MAIN-2018-34 data_files: - split: train path: CC-MAIN-2018-34/train-* - config_name: CC-MAIN-2018-39 data_files: - split: train path: CC-MAIN-2018-39/train-* - config_name: CC-MAIN-2018-43 data_files: - split: train path: CC-MAIN-2018-43/train-* - config_name: CC-MAIN-2018-47 data_files: - split: train path: CC-MAIN-2018-47/train-* - config_name: CC-MAIN-2018-51 data_files: - split: train path: CC-MAIN-2018-51/train-* - config_name: CC-MAIN-2019-04 data_files: - split: train path: CC-MAIN-2019-04/train-* - config_name: CC-MAIN-2019-09 data_files: - split: train path: CC-MAIN-2019-09/train-* - config_name: CC-MAIN-2019-13 data_files: - split: train path: CC-MAIN-2019-13/train-* - config_name: CC-MAIN-2019-18 data_files: - split: train path: CC-MAIN-2019-18/train-* - config_name: CC-MAIN-2019-22 data_files: - split: train path: CC-MAIN-2019-22/train-* - config_name: CC-MAIN-2019-26 data_files: - split: train path: CC-MAIN-2019-26/train-* - config_name: CC-MAIN-2019-30 data_files: - split: train path: CC-MAIN-2019-30/train-* - config_name: CC-MAIN-2019-35 data_files: - split: train path: CC-MAIN-2019-35/train-* - config_name: CC-MAIN-2019-39 data_files: - split: train path: CC-MAIN-2019-39/train-* - config_name: CC-MAIN-2019-43 data_files: - split: train path: CC-MAIN-2019-43/train-* - config_name: CC-MAIN-2019-47 data_files: - split: train path: CC-MAIN-2019-47/train-* - config_name: CC-MAIN-2019-51 data_files: - split: train path: CC-MAIN-2019-51/train-* - config_name: CC-MAIN-2020-05 data_files: - split: train path: CC-MAIN-2020-05/train-* - config_name: CC-MAIN-2020-10 data_files: - split: train path: CC-MAIN-2020-10/train-* - config_name: CC-MAIN-2020-16 data_files: - split: train path: CC-MAIN-2020-16/train-* - config_name: CC-MAIN-2020-24 data_files: - split: train path: CC-MAIN-2020-24/train-* - config_name: CC-MAIN-2020-29 data_files: - split: train path: CC-MAIN-2020-29/train-* - config_name: CC-MAIN-2020-34 data_files: - split: train path: CC-MAIN-2020-34/train-* - config_name: CC-MAIN-2020-40 data_files: - split: train path: CC-MAIN-2020-40/train-* - config_name: CC-MAIN-2020-45 data_files: - split: train path: CC-MAIN-2020-45/train-* - config_name: CC-MAIN-2020-50 data_files: - split: train path: CC-MAIN-2020-50/train-* - config_name: CC-MAIN-2021-04 data_files: - split: train path: CC-MAIN-2021-04/train-* - config_name: CC-MAIN-2021-10 data_files: - split: train path: CC-MAIN-2021-10/train-* - config_name: CC-MAIN-2021-17 data_files: - split: train path: CC-MAIN-2021-17/train-* - config_name: CC-MAIN-2021-21 data_files: - split: train path: CC-MAIN-2021-21/train-* - config_name: CC-MAIN-2021-25 data_files: - split: train path: CC-MAIN-2021-25/train-* - config_name: CC-MAIN-2021-31 data_files: - split: train path: CC-MAIN-2021-31/train-* - config_name: CC-MAIN-2021-39 data_files: - split: train path: CC-MAIN-2021-39/train-* - config_name: CC-MAIN-2021-43 data_files: - split: train path: CC-MAIN-2021-43/train-* - config_name: CC-MAIN-2021-49 data_files: - split: train path: CC-MAIN-2021-49/train-* - config_name: CC-MAIN-2022-05 data_files: - split: train path: CC-MAIN-2022-05/train-* - config_name: CC-MAIN-2022-21 data_files: - split: train path: CC-MAIN-2022-21/train-* - config_name: CC-MAIN-2022-27 data_files: - split: train path: CC-MAIN-2022-27/train-* - config_name: CC-MAIN-2022-33 data_files: - split: train path: CC-MAIN-2022-33/train-* - config_name: CC-MAIN-2022-40 data_files: - split: train path: CC-MAIN-2022-40/train-* - config_name: CC-MAIN-2022-49 data_files: - split: train path: CC-MAIN-2022-49/train-* - config_name: CC-MAIN-2023-06 data_files: - split: train path: CC-MAIN-2023-06/train-* - config_name: CC-MAIN-2023-14 data_files: - split: train path: CC-MAIN-2023-14/train-* - config_name: CC-MAIN-2023-23 data_files: - split: train path: CC-MAIN-2023-23/train-* - config_name: CC-MAIN-2023-40 data_files: - split: train path: CC-MAIN-2023-40/train-* - config_name: CC-MAIN-2023-50 data_files: - split: train path: CC-MAIN-2023-50/train-* --- ⭐️ **NOTE:** Several parquet files were marked unsafe (viruses) by official scaning of hf, while they are reported safe by ClamAV and Virustotal. We found [many false positive cases](https://discuss.huggingface.co/u/mcpotato/summary) of the hf automatic scanning in hf discussions and raise [one discussion](https://discuss.huggingface.co/t/one-parquet-file-of-my-dataset-was-marked-unsafe/113745) to ask for a re-scanning. # OmniCorpus-CC This is the repository of OmniCorpus-CC, which contains 988 million image-text interleaved documents collected from [Common Crawl](https://commoncrawl.org/). - Repository: https://github.com/OpenGVLab/OmniCorpus - Paper: https://arxiv.org/abs/2406.08418 OmniCorpus dataset is a large-scale image-text interleaved dataset, which pushes the boundaries of scale and diversity by encompassing **8.6 billion images** interleaved with **1,696 text tokens** from diverse sources, significantly surpassing previous datasets. This dataset demonstrates several advantages over its counterparts: 1. **Larger data scale:** Our dataset is 1.7 times larger in images and 12.5 times larger in texts compared to the previously largest multimodal dataset, LAION-5B, while maintaining excellent data quality. 2. **Richer data diversity:** Drawing from a broader range of data sources, our dataset is more diverse than other image-text interleaved datasets. It includes bilingual multimodal data in both Chinese and English, and encompasses text-centric and vision-centric documents extracted from common websites and video platforms. 3. **More flexible format:** The streaming data format of our dataset offers exceptional flexibility, allowing adaptation to various data structures, including pure text corpora, image-text pairs, and interleaved data formats. <img width="578" alt="image" src="https://github.com/OpenGVLab/OmniCorpus/assets/47669167/641a6427-ba50-41e6-8634-8810113fd803"> The OmniCorpus contains three sections: - **OmniCorpus-CC**: processed from dumps in Common Crawl from 2013 to Nov./Dec. 2023. - **OmniCorpus-CW**: sourced from Chinese internet resources, will be availiable in [OpenDataLab](https://opendatalab.com/) platform. - **OmniCorpus-YT**: samples Youtube video frames as images and collects subtitles as texts. Code for pre-training, evaluating, main body extracting, and filtering have been released in the official [repository](https://github.com/OpenGVLab/OmniCorpus). A pre-trained model is availiable [here](https://huggingface.co./Qingyun/OmniCorpus-InternVL). # Data Pipeline Our data pipeline consists of five key stages: main body extraction, preliminary text filtering, document deduplication, image downloading \& filtering, and detailed text filtering. Each stage efficiently reduces the dataset to retain only high-quality data. Please refer to our paper for more details about the data pipeline. <img width="723" alt="image" src="https://github.com/OpenGVLab/OmniCorpus/assets/47669167/a6de8928-58fb-4ff4-8ef9-4bd90e9ada5f"> # Usages The image-text interleaved documents are recommanded for the following usages: - Pre-training multimodal large language model (MLLM): Recent MLLMs (such as Flamingo series, EMU series, IDEFICS series, MM1, Cambrian-1, and xGen-MM) have shown that image-text interleaved data aids multimodal in-context learning and maintains the capabilities of large language models during multimodal fine-tuning. - Long text-image retrieval: We provide image-text similarities calculated with CLIP, which can convert the documents to image-text retrieval dataset with longer text. A retrieval model pre-trained on such data can retrieval images based on longer text, which can be used for multimodal RAG, converting pure text to multimodal sample, etc. - Source for futher dataset research: Our data is large-scale, which can serve as the source for researches for data curation strategies. We provide many useful attributes as metadata for each document, which can enrich the filtering strategy and reduce the cost. - ...... # Data Format Following common practices, the data is organized into Parquet file format. You might encounter errors when using `pandas.read_parquet` (because the data structure contains nested elements). We recommend using fastparquet to load the parquet files. ```Python import fastparquet df = fastparquet.ParquetFile(parquet_file_path).to_pandas() # You can also use iter_batches parquet_file = pq.ParquetFile(filepath) for batch in parquet_file.iter_batches(): df = batch.to_pandas() ``` You can convert the i-th document and convert it into a dictionary. ```Python doc_dict = df.iloc[i].to_dict() ``` The document format is as follow: ```json { 'images': [ <str: image_1_url>, None, <str: image_2_url>, None, ], 'texts': [ None, <str: text_paragraph_1_content> None, <str: text_paragraph_2_content>, ] 'metadata': [ <dict: image_1_metadata>, None, <dict: image_2_metadata>, None ], 'general_metadata': { "url": <str: document url>, "id": <str: document id>, "domain": <list[str]: domains extracted from document url>, "fluency_prob": <float: the probability of fluency>, "non_advertisement_prob": <float: the probability of non-advertisement>, "porn_prob": <float: the probability of porn content>, "politics_prob": <float: the probability of politics content>, "toxic_prob": <float: the probability of toxic content>, } } ``` Each image metadata is as follow: ```json { "img_url_sha": <str: sha code of image url>, "width": <int: image width>, "height": <int: image height>, "bytes": <int: byte number of the image file>, "d_hash": <str: d_hash code of the image, used for image deduplication>, "p_hash": <str: p_hash code of the image, used for image deduplication>, "d_hash_dup_count": <int: duplicated times detected by d_hash code>, "p_hash_dup_count": <int: duplicated times detected by p_hash code>, "aesthetic prob": <float: aesthetic probility>, "unsafe prob": <float: NSFW probility>, } ``` # License OmniCorpus is released under a [CC-BY-4.0](https://creativecommons.org/licenses/by/4.0/deed.en) license, with the primary intent of supporting research activities. # Citation ``` @article{li2024omnicorpus, title={OmniCorpus: A Unified Multimodal Corpus of 10 Billion-Level Images Interleaved with Text}, author={Li, Qingyun and Chen, Zhe and Wang, Weiyun and Wang, Wenhai and Ye, Shenglong and Jin, Zhenjiang and others}, journal={arXiv preprint arXiv:2406.08418}, year={2024} } ```

allenai/reward-bench-results

allenai

--- dataset_info: features: - name: prompt dtype: string - name: chosen dtype: string - name: chosen_model dtype: string - name: rejected dtype: string - name: rejected_model dtype: string - name: subset dtype: string - name: id dtype: int64 - name: text_chosen dtype: string - name: text_rejected dtype: string - name: results dtype: int64 splits: - name: filtered num_bytes: 8126708 num_examples: 2093 download_size: 4062729 dataset_size: 8126708 configs: - config_name: default data_files: - split: filtered path: data/filtered-* --- # Results for Holisitic Evaluation of Reward Models (HERM) Benchmark Here, you'll find the raw scores for the HERM project. The repository is structured as follows. ``` ├── best-of-n/ <- Nested directory for different completions on Best of N challenge | ├── alpaca_eval/ └── results for each reward model | | ├── tulu-13b/{org}/{model}.json | | └── zephyr-7b/{org}/{model}.json | └── mt_bench/ | ├── tulu-13b/{org}/{model}.json | └── zephyr-7b/{org}/{model}.json ├── eval-set-scores/{org}/{model}.json <- Per-prompt scores on our core evaluation set. ├── eval-set/ <- Aggregated results on our core eval. set. ├── pref-sets-scores/{org}/{model}.json <- Per-prompt scores on existing test sets. └── pref-sets/ <- Aggregated results on existing test sets. ``` The data is loaded by the other projects in this repo and released for further research. See the [GitHub repo](https://github.com/allenai/herm) or the [leaderboard source code](https://huggingface.co./spaces/ai2-adapt-dev/HERM-Leaderboard/tree/main) for examples on loading and manipulating the data. Tools for analysis are found on [GitHub](https://github.com/allenai/reward-bench/blob/main/analysis/utils.py). Contact: `nathanl at allenai dot org` For example, this data can be used to aggregate the distribution of scores across models (it also powers our leaderboard)! <img src="https://huggingface.co./datasets/allenai/blog-images/resolve/main/reward-bench/dist.png" alt="RewardBench Distribution" width="800" style="margin-left:'auto' margin-right:'auto' display:'block'"/>

zalando-datasets/fashion_mnist

zalando-datasets

--- annotations_creators: - expert-generated language_creators: - found language: - en license: - mit multilinguality: - monolingual size_categories: - 10K<n<100K source_datasets: - original task_categories: - image-classification task_ids: - multi-class-image-classification paperswithcode_id: fashion-mnist pretty_name: FashionMNIST dataset_info: config_name: fashion_mnist features: - name: image dtype: image - name: label dtype: class_label: names: '0': T - shirt / top '1': Trouser '2': Pullover '3': Dress '4': Coat '5': Sandal '6': Shirt '7': Sneaker '8': Bag '9': Ankle boot splits: - name: train num_bytes: 31049107.0 num_examples: 60000 - name: test num_bytes: 5192560.0 num_examples: 10000 download_size: 36106894 dataset_size: 36241667.0 configs: - config_name: fashion_mnist data_files: - split: train path: fashion_mnist/train-* - split: test path: fashion_mnist/test-* default: true --- # Dataset Card for FashionMNIST ## Table of Contents - [Dataset Description](#dataset-description) - [Dataset Summary](#dataset-summary) - [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards) - [Languages](#languages) - [Dataset Structure](#dataset-structure) - [Data Instances](#data-instances) - [Data Fields](#data-fields) - [Data Splits](#data-splits) - [Dataset Creation](#dataset-creation) - [Curation Rationale](#curation-rationale) - [Source Data](#source-data) - [Annotations](#annotations) - [Personal and Sensitive Information](#personal-and-sensitive-information) - [Considerations for Using the Data](#considerations-for-using-the-data) - [Social Impact of Dataset](#social-impact-of-dataset) - [Discussion of Biases](#discussion-of-biases) - [Other Known Limitations](#other-known-limitations) - [Additional Information](#additional-information) - [Dataset Curators](#dataset-curators) - [Licensing Information](#licensing-information) - [Citation Information](#citation-information) - [Contributions](#contributions) ## Dataset Description - **Homepage:** [GitHub](https://github.com/zalandoresearch/fashion-mnist) - **Repository:** [GitHub](https://github.com/zalandoresearch/fashion-mnist) - **Paper:** [arXiv](https://arxiv.org/pdf/1708.07747.pdf) - **Leaderboard:** - **Point of Contact:** ### Dataset Summary Fashion-MNIST is a dataset of Zalando's article images—consisting of a training set of 60,000 examples and a test set of 10,000 examples. Each example is a 28x28 grayscale image, associated with a label from 10 classes. We intend Fashion-MNIST to serve as a direct drop-in replacement for the original MNIST dataset for benchmarking machine learning algorithms. It shares the same image size and structure of training and testing splits. ### Supported Tasks and Leaderboards - `image-classification`: The goal of this task is to classify a given image of Zalando's article into one of 10 classes. The leaderboard is available [here](https://paperswithcode.com/sota/image-classification-on-fashion-mnist). ### Languages [More Information Needed] ## Dataset Structure ### Data Instances A data point comprises an image and its label. ``` { 'image': <PIL.PngImagePlugin.PngImageFile image mode=L size=28x28 at 0x27601169DD8>, 'label': 9 } ``` ### Data Fields - `image`: A `PIL.Image.Image` object containing the 28x28 image. Note that when accessing the image column: `dataset[0]["image"]` the image file is automatically decoded. Decoding of a large number of image files might take a significant amount of time. Thus it is important to first query the sample index before the `"image"` column, *i.e.* `dataset[0]["image"]` should **always** be preferred over `dataset["image"][0]`. - `label`: an integer between 0 and 9 representing the classes with the following mapping: | Label | Description | | --- | --- | | 0 | T-shirt/top | | 1 | Trouser | | 2 | Pullover | | 3 | Dress | | 4 | Coat | | 5 | Sandal | | 6 | Shirt | | 7 | Sneaker | | 8 | Bag | | 9 | Ankle boot | ### Data Splits The data is split into training and test set. The training set contains 60,000 images and the test set 10,000 images. ## Dataset Creation ### Curation Rationale **From the arXiv paper:** The original MNIST dataset contains a lot of handwritten digits. Members of the AI/ML/Data Science community love this dataset and use it as a benchmark to validate their algorithms. In fact, MNIST is often the first dataset researchers try. "If it doesn't work on MNIST, it won't work at all", they said. "Well, if it does work on MNIST, it may still fail on others." Here are some good reasons: - MNIST is too easy. Convolutional nets can achieve 99.7% on MNIST. Classic machine learning algorithms can also achieve 97% easily. Check out our side-by-side benchmark for Fashion-MNIST vs. MNIST, and read "Most pairs of MNIST digits can be distinguished pretty well by just one pixel." - MNIST is overused. In this April 2017 Twitter thread, Google Brain research scientist and deep learning expert Ian Goodfellow calls for people to move away from MNIST. - MNIST can not represent modern CV tasks, as noted in this April 2017 Twitter thread, deep learning expert/Keras author François Chollet. ### Source Data #### Initial Data Collection and Normalization **From the arXiv paper:** Fashion-MNIST is based on the assortment on Zalando’s website. Every fashion product on Zalando has a set of pictures shot by professional photographers, demonstrating different aspects of the product, i.e. front and back looks, details, looks with model and in an outfit. The original picture has a light-gray background (hexadecimal color: #fdfdfd) and stored in 762 × 1000 JPEG format. For efficiently serving different frontend components, the original picture is resampled with multiple resolutions, e.g. large, medium, small, thumbnail and tiny. We use the front look thumbnail images of 70,000 unique products to build Fashion-MNIST. Those products come from different gender groups: men, women, kids and neutral. In particular, whitecolor products are not included in the dataset as they have low contrast to the background. The thumbnails (51 × 73) are then fed into the following conversion pipeline: 1. Converting the input to a PNG image. 2. Trimming any edges that are close to the color of the corner pixels. The “closeness” is defined by the distance within 5% of the maximum possible intensity in RGB space. 3. Resizing the longest edge of the image to 28 by subsampling the pixels, i.e. some rows and columns are skipped over. 4. Sharpening pixels using a Gaussian operator of the radius and standard deviation of 1.0, with increasing effect near outlines. 5. Extending the shortest edge to 28 and put the image to the center of the canvas. 6. Negating the intensities of the image. 7. Converting the image to 8-bit grayscale pixels. #### Who are the source language producers? **From the arXiv paper:** Every fashion product on Zalando has a set of pictures shot by professional photographers, demonstrating different aspects of the product, i.e. front and back looks, details, looks with model and in an outfit. ### Annotations #### Annotation process **From the arXiv paper:** For the class labels, they use the silhouette code of the product. The silhouette code is manually labeled by the in-house fashion experts and reviewed by a separate team at Zalando. Each product Zalando is the Europe’s largest online fashion platform. Each product contains only one silhouette code. #### Who are the annotators? **From the arXiv paper:** The silhouette code is manually labeled by the in-house fashion experts and reviewed by a separate team at Zalando. ### Personal and Sensitive Information [More Information Needed] ## Considerations for Using the Data ### Social Impact of Dataset [More Information Needed] ### Discussion of Biases [More Information Needed] ### Other Known Limitations [More Information Needed] ## Additional Information ### Dataset Curators Han Xiao and Kashif Rasul and Roland Vollgraf ### Licensing Information MIT Licence ### Citation Information ``` @article{DBLP:journals/corr/abs-1708-07747, author = {Han Xiao and Kashif Rasul and Roland Vollgraf}, title = {Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms}, journal = {CoRR}, volume = {abs/1708.07747}, year = {2017}, url = {http://arxiv.org/abs/1708.07747}, archivePrefix = {arXiv}, eprint = {1708.07747}, timestamp = {Mon, 13 Aug 2018 16:47:27 +0200}, biburl = {https://dblp.org/rec/bib/journals/corr/abs-1708-07747}, bibsource = {dblp computer science bibliography, https://dblp.org} } ``` ### Contributions Thanks to [@gchhablani](https://github.com/gchablani) for adding this dataset.

Mutonix/Vript

Mutonix

--- task_categories: - video-classification - visual-question-answering - text-to-video - text-to-image - image-to-video language: - en size_categories: - 100K<n<1M configs: - config_name: vript-long data_files: - split: train path: vript_captions/vript_long_videos_captions.jsonl - config_name: vript-short data_files: - split: train path: vript_captions/vript_short_videos_captions.jsonl --- # 🎬 Vript: Refine Video Captioning into Video Scripting [[Github Repo](https://github.com/mutonix/Vript)] --- We construct a **fine-grained** video-text dataset with 12K annotated high-resolution videos **(~400k clips)**. The annotation of this dataset is inspired by the video script. If we want to make a video, we have to first write a script to organize how to shoot the scenes in the videos. To shoot a scene, we need to decide the content, shot type (medium shot, close-up, etc), and how the camera moves (panning, tilting, etc). Therefore, we extend video captioning to video scripting by annotating the videos in the format of video scripts. Different from the previous video-text datasets, we densely annotate the entire videos without discarding any scenes and each scene has a caption with **~145** words. Besides the vision modality, we transcribe the voice-over into text and put it along with the video title to give more background information for annotating the videos. **_<font color=red>Warning: Some zip files may contain empty folders. You can ignore them as these folders have no video clips and no annotation files.</font>_** <p align="center"> <img src="assets/Vript-overview_00.png" width="800"> </p> ## Getting Started **By downloading these datasets, you agree to the terms of the [License](#License).** The captions of the videos in the Vript dataset are structured as follows: ``` { "meta": { "video_id": "339dXVNQXac", "video_title": "...", "num_clips": ..., "integrity": true, }, "data": { "339dXVNQXac-Scene-001": { "video_id": "339dXVNQXac", "clip_id": "339dXVNQXac-Scene-001", "video_title": "...", "caption":{ "shot_type": "...", "camera_movement": "...", "content": "...", "scene_title": "...", }, "voiceover": ["..."], }, "339dXVNQXac-Scene-002": { ... } } } ``` - `video_id`: The ID of the video from YouTube. - `video_title`: The title of the video. - `num_clips`: The number of clips in the video. If the `integrity` is `false`, some clips may not be captioned. - `integrity`: Whether all clips are captioned. - `clip_id`: The ID of the clip in the video, which is the concatenation of the `video_id` and the scene number. - `caption`: The caption of the scene, including the shot type, camera movement, content, and scene title. - `voiceover`: The transcription of the voice-over in the scene. The data is organized as follows: ``` Vript/ | ├── vript_meta/ │ ├── vript_long_videos_meta.json │ └── vript_short_videos_meta.json │ ├── vript_captions/ │ ├── vript_long_videos_captions.zip │ │ ├── 007EvOaWFOA_caption.json │ │ └── ... │ └── vript_short_videos_captions.zip │ └── ... │ ├── vript_long_videos/ │ ├── video_1_of_1095.zip │ │ ├── 007EvOaWFOA.mp4 │ │ └── ... │ ├── video_2_of_1095.zip │ └── ... │ ├── vript_short_videos/ │ ├── short_video_1_of_42.zip │ │ ├── 02toZL7p4_0.mp4 │ │ └── ... │ ├── short_video_2_of_42.zip │ └── ... │ ├── vript_long_videos_clips/ │ ├── clips_1_of_1095.zip │ │ ├── 007EvOaWFOA/ │ │ │ ├── 007EvOaWFOA_cut_meta.json │ │ │ ├── 007EvOaWFOA_asr.jsonl │ │ │ ├── 007EvOaWFOA-Scene-001.mp4 │ │ │ └── ... │ │ └── ... │ ├── clips_2_of_1095.zip │ └── ... │ └── vript_short_videos_clips/ ├── shorts_clips_1_of_42.zip │ ├── 02toZL7p4_0/ │ │ ├── 02toZL7p4_0_cut_meta.json │ │ ├── 02toZL7p4_0_asr.jsonl │ │ ├── 02toZL7p4_0-Scene-001.mp4 │ │ └── ... │ └── ... ├── shorts_clips_2_of_42.zip └── ... ``` - `vript_meta/`: The meta information of the videos in the Vript dataset, including the video id, title, url, description, category, etc. - `vript_captions/`: The video captions of the videos in the Vript dataset, which are structured as described above. - `vript_long_videos/` (667 GB) and `vript_short_videos/` (8.8 GB): The untrimmed videos in the Vript dataset. Long videos are from YouTube, and short videos are from YouTube Shorts and TikTok. We divide the whole data into multiple zip files, each containing 10 long videos / 50 short videos. All the videos are in **720p** resolution, and _we will provide the videos in the highest quality (up to 2K) available later_ (or you can download them from YouTube directly). - `vript_long_videos_clips/` (822 GB) and `vript_short_videos_clips/` (12 GB): The trimmed video clips in the Vript dataset, which correspond to scenes in the `video_captions`. - `xxx_cut_meta.json`: The meta information about how the video is trimmed, including the start time, end time, and the duration of the scene. - `xxx_asr.jsonl`: The transcription of the voice-over in the scene. ## License By downloading or using the data or model, you understand, acknowledge, and agree to all the terms in the following agreement. - ACADEMIC USE ONLY Any content from Vript/Vript-Bench dataset and Vriptor model is available for academic research purposes only. You agree not to reproduce, duplicate, copy, trade, or exploit for any commercial purposes - NO DISTRIBUTION Respect the privacy of personal information of the original source. Without the permission of the copyright owner, you are not allowed to perform any form of broadcasting, modification or any other similar behavior to the data set content. - RESTRICTION AND LIMITATION OF LIABILITY In no event shall we be liable for any other damages whatsoever arising out of the use of, or inability to use this dataset and its associated software, even if we have been advised of the possibility of such damages. - DISCLAIMER You are solely responsible for legal liability arising from your improper use of the dataset content. We reserve the right to terminate your access to the dataset at any time. You should delete the Vript/Vript-Bench dataset or Vriptor model if required. This license is modified from the [HD-VG-100M](https://github.com/daooshee/HD-VG-130M) license. <!-- ## Citation ``` ``` --> ## Contact **Dongjie Yang**: [[email protected]]([email protected]) Paper: arxiv.org/abs/2406.06040

isp-uv-es/WorldFloodsv2

isp-uv-es

--- license: cc-by-nc-4.0 pipeline_tag: image-segmentation tags: - remote sensing - sentinel2 - landsat - floods --- # *WorldFloodsv2* dataset This repository contains the *WorldFloodsv2* dataset released with the publication: > E. Portalés-Julià, G. Mateo-García, C. Purcell, and L. Gómez-Chova [Global flood extent segmentation in optical satellite images](https://www.nature.com/articles/s41598-023-47595-7). _Scientific Reports 13, 20316_ (2023). DOI: 10.1038/s41598-023-47595-7. The [*WorldFloodsv2* database](https://www.nature.com/articles/s41598-023-47595-7) contains 509 pairs of Sentinel-2 images and flood segmentation masks. Splitted in train, val and test sets. It requires approximately 76GB of hard-disk storage. <img src="worldfloods_v2.png" alt="licence" width="65%"/> ## Download the dataset ``` huggingface-cli download --cache-dir /path/to/cachedir --local-dir /path/to/localdir/WorldFloodsv2 --repo-type dataset isp-uv-es/WorldFloodsv2 ``` ## Explore the dataset The [exploring *WorldFloodsv2*](https://spaceml-org.github.io/ml4floods/content/prep/exploring_worldfloods.html) tutorial in the [ml4floods](https://github.com/spaceml-org/ml4floods) package shows how to process the dataset and plot the images and masks. ## Licence The *WorldFloods* database and all pre-trained models are released under a [Creative Commons non-commercial licence](https://creativecommons.org/licenses/by-nc/4.0/legalcode.txt) ## Cite If you find this work useful, please cite: ``` @article{portales-julia_global_2023, title = {Global flood extent segmentation in optical satellite images}, volume = {13}, issn = {2045-2322}, doi = {10.1038/s41598-023-47595-7}, number = {1}, urldate = {2023-11-30}, journal = {Scientific Reports}, author = {Portalés-Julià, Enrique and Mateo-García, Gonzalo and Purcell, Cormac and Gómez-Chova, Luis}, month = nov, year = {2023}, pages = {20316}, } ```

knkarthick/dialogsum

knkarthick

--- annotations_creators: - expert-generated language_creators: - expert-generated language: - en license: cc-by-nc-sa-4.0 multilinguality: - monolingual size_categories: - 10K<n<100K source_datasets: - original task_categories: - summarization - text2text-generation - text-generation task_ids: [] pretty_name: DIALOGSum Corpus tags: - dialogue-summary - one-liner-summary - meeting-title - email-subject --- # Dataset Card for DIALOGSum Corpus ## Dataset Description ### Links - **Homepage:** https://aclanthology.org/2021.findings-acl.449 - **Repository:** https://github.com/cylnlp/dialogsum - **Paper:** https://aclanthology.org/2021.findings-acl.449 - **Point of Contact:** https://huggingface.co./knkarthick ### Dataset Summary DialogSum is a large-scale dialogue summarization dataset, consisting of 13,460 (Plus 100 holdout data for topic generation) dialogues with corresponding manually labeled summaries and topics. ### Languages English ## Dataset Structure ### Data Instances DialogSum is a large-scale dialogue summarization dataset, consisting of 13,460 dialogues (+1000 tests) split into train, test and validation. The first instance in the training set: {'id': 'train_0', 'summary': "Mr. Smith's getting a check-up, and Doctor Hawkins advises him to have one every year. Hawkins'll give some information about their classes and medications to help Mr. Smith quit smoking.", 'dialogue': "#Person1#: Hi, Mr. Smith. I'm Doctor Hawkins. Why are you here today?\n#Person2#: I found it would be a good idea to get a check-up.\n#Person1#: Yes, well, you haven't had one for 5 years. You should have one every year.\n#Person2#: I know. I figure as long as there is nothing wrong, why go see the doctor?\n#Person1#: Well, the best way to avoid serious illnesses is to find out about them early. So try to come at least once a year for your own good.\n#Person2#: Ok.\n#Person1#: Let me see here. Your eyes and ears look fine. Take a deep breath, please. Do you smoke, Mr. Smith?\n#Person2#: Yes.\n#Person1#: Smoking is the leading cause of lung cancer and heart disease, you know. You really should quit.\n#Person2#: I've tried hundreds of times, but I just can't seem to kick the habit.\n#Person1#: Well, we have classes and some medications that might help. I'll give you more information before you leave.\n#Person2#: Ok, thanks doctor.", 'topic': "get a check-up} ### Data Fields - dialogue: text of dialogue. - summary: human written summary of the dialogue. - topic: human written topic/one liner of the dialogue. - id: unique file id of an example. ### Data Splits - train: 12460 - val: 500 - test: 1500 - holdout: 100 [Only 3 features: id, dialogue, topic] ## Dataset Creation ### Curation Rationale In paper: We collect dialogue data for DialogSum from three public dialogue corpora, namely Dailydialog (Li et al., 2017), DREAM (Sun et al., 2019) and MuTual (Cui et al., 2019), as well as an English speaking practice website. These datasets contain face-to-face spoken dialogues that cover a wide range of daily-life topics, including schooling, work, medication, shopping, leisure, travel. Most conversations take place between friends, colleagues, and between service providers and customers. Compared with previous datasets, dialogues from DialogSum have distinct characteristics: Under rich real-life scenarios, including more diverse task-oriented scenarios; Have clear communication patterns and intents, which is valuable to serve as summarization sources; Have a reasonable length, which comforts the purpose of automatic summarization. We ask annotators to summarize each dialogue based on the following criteria: Convey the most salient information; Be brief; Preserve important named entities within the conversation; Be written from an observer perspective; Be written in formal language. ### Who are the source language producers? linguists ### Who are the annotators? language experts ## Licensing Information CC BY-NC-SA 4.0 ## Citation Information ``` @inproceedings{chen-etal-2021-dialogsum, title = "{D}ialog{S}um: {A} Real-Life Scenario Dialogue Summarization Dataset", author = "Chen, Yulong and Liu, Yang and Chen, Liang and Zhang, Yue", booktitle = "Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021", month = aug, year = "2021", address = "Online", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2021.findings-acl.449", doi = "10.18653/v1/2021.findings-acl.449", pages = "5062--5074", ``` ## Contributions Thanks to [@cylnlp](https://github.com/cylnlp) for adding this dataset.

ltg/en-wiki-paraphrased

ltg

--- license: apache-2.0 ---

allenai/s2-naip

allenai

--- license: apache-2.0 --- AI2-S2-NAIP is a remote sensing dataset consisting of aligned NAIP, Sentinel-2, Sentinel-1, and Landsat images spanning the entire continental US. Data is divided into tiles. Each tile spans 512x512 pixels at 1.25 m/pixel in one of the 10 UTM projections covering the continental US. At each tile, the following data is available: - [National Agriculture Imagery Program (NAIP)](https://www.usgs.gov/centers/eros/science/usgs-eros-archive-aerial-photography-national-agriculture-imagery-program-naip): an image from 2019-2021 at 1.25 m/pixel (512x512). - [Sentinel-2 (L1C)](https://sentinels.copernicus.eu/web/sentinel/missions/sentinel-2): between 16 and 32 images captured within a few months of the NAIP image at 10 m/pixel (64x64). - [Sentinel-1](https://sentinels.copernicus.eu/web/sentinel/missions/sentinel-1): between 2 and 8 images captured within a few months of the NAIP image at 10 m/pixel (64x64). - [Landsat-8/9](https://www.usgs.gov/landsat-missions/landsat-8): 4 images captured in the same year as the NAIP image at 10 m/pixel (64x64). - [OpenStreetMap](https://www.openstreetmap.org): a GeoJSON containing buildings, roads, and 30 other categories. It uses pixel coordinates relative to the 512x512 NAIP image. - [WorldCover](https://worldcover2021.esa.int/): the 2021 land cover image at 10 m/pixel (64x64). AI2-S2-NAIP is applicable to several supervised and unsupervised tasks in remote sensing, including super-resolution (e.g. NAIP -> Sentinel-2), segmentation and detection (e.g. NAIP or Sentinel-2 -> OpenStreetMap or WorldCover), and multi-modal masked autoencoder pre-training. For questions or feedback about AI2-S2-NAIP, please open an issue on Github at https://github.com/allenai/satlas.  Structure --------- Once extracted, the dataset contains the different data types in different folders. Each folder contains files named by a tile ID, which consists of the UTM projection, column, and row. The column and row are based on tiles that are 512x512 pixels with pixel coordinates at 1.25 m/pixel, e.g. `32612_960_-6049.png` spans (614400, -3871360) to (615040, -3870720) in EPSG:32612 projection units. Here is an example of NAIP data: ``` naip/ 32612_960_-6049.png 32612_960_-6050.png 32612_960_-6051.png ... ``` And an example of Sentinel-2 data: ``` sentinel2/ 32612_960_-6049_16.tif 32612_960_-6049_32.tif 32612_960_-6049_8.tif 32612_960_-6050_16.tif ... ``` The Sentinel-2, Sentinel-1, and Landsat images are GeoTIFFS so they contain georeference metadata. Other data does not have georeference metadata, but data at each tile is aligned, so the georeference metadata from the above images is applicable to the other data as well with only a resolution shift. Mapping Longitude and Latitude to Tile -------------------------------------- Here is an example of mapping longitude and latitude to a tile. First install packages: pip install rasterio shapely utm Then launch Python shell: from rasterio.crs import CRS from rasterio.warp import transform_geom import shapely import utm # Define source location. src_crs = CRS.from_epsg(4326) src_point = shapely.Point(-122.331711, 47.648450) # Get UTM zone. _, _, zone_suffix, _ = utm.from_latlon(src_point.y, src_point.x) epsg_code = 32600 + zone_suffix dst_crs = CRS.from_epsg(epsg_code) # Transform to UTM CRS. dst_point = transform_geom(src_crs, dst_crs, src_point) dst_point = shapely.geometry.shape(dst_point) # dst_point is in projection coordinates (meters). # Now convert to pixel coordinates at 1.25 m/pixel. col = int(dst_point.x/1.25) row = int(dst_point.y/-1.25) # Print the prefix for the image filenames. print(f"{epsg_code}_{col//512}_{row//512}") # Print the prefix for the tar filenames to know which one to download. # These group together many 1.25 m/pixel 512x512 tiles into one tar file. print(f"{epsg_code}_{col//512//32}_{row//512//32}") So then you would download the tar file from the second prefix, extract it, and look at the file with name matching the first prefix. See visualize_tile.py for example of visualizing the data at a particular tile. Sentinel-2 ---------- The 10 m/pixel (`_8.tif`), 20 m/pixel (`_16.tif`), and 60 m/pixel (`_32.tif`) bands are stored separately. Pixel values are the L1C 16-bit values. The band order is as follows: - _8.tif (64x64): B02, B03, B04, B08 - _16.tif (32x32): B05, B06, B07, B8A, B11, B12 - _32.tif (16x16): B01, B09, B10 The GeoTIFFs contain multiple images concatenated along the channel axis. The CSV shows the original Sentinel-2 scene ID of each image. Sentinel-1 ---------- The Sentinel-1 bands are 10 m/pixel and ordered VV then VH. Only IW VV+VH scenes are used. The pixel values are 32-bit floating point values representing decibels 10*log10(x). We obtain the radiometric-calibrated and terrain-corrected images from Google Earth Engine so see https://developers.google.com/earth-engine/datasets/catalog/COPERNICUS_S1_GRD for details. The GeoTIFFs contain multiple images concatenated along the channel axis. The CSV shows the original Sentinel-1 scene ID of each image. NAIP ---- The NAIP image is 512x512 with four 8-bit bands: R, G, B, IR. It is encoded as PNG but the IR is alpha mask so cannot be visualized correctly in image viewer without removing the alpha mask. There are two NAIP images available, one under "naip" (2019-2022) and one under "oldnaip" (2015-2018). The CSV shows the original NAIP scene ID of each image. Landsat ------- We include OLI-TIRS images from Landsat-8 and Landsat-9. As with Sentinel-2, we select Landsat images that were captured within a few months of the NAIP image. We store the 15 m/pixel bands (i.e. B8) at 10 m/pixel, and the 30 m/pixel bands (all the others) at 20 m/pixel. There are separate GeoTIFFs for the 10 m/pixel (`_8.tif`) and 20 m/pixel (`_16.tif`). All pixel values are 16-bit. The band order is as follows: - _8.tif (64x64): B8 - _16.tif (32x32): B1, B2, B3, B4, B5, B6, B7, B9, B10, B11 The GeoTIFFS contain multiple images concatenated along the channel axis. The CSV shows the original Landsat scene ID of each image.

pixparse/cc12m-wds

pixparse

--- license: other license_name: conceptual-12m license_link: LICENSE task_categories: - image-to-text size_categories: - 10M<n<100M --- # Dataset Card for Conceptual Captions 12M (CC12M) ## Dataset Description - **Repository:** [Conceptual 12M repository](https://github.com/google-research-datasets/conceptual-12m) - **Paper:** [Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts](https://arxiv.org/abs/2102.08981) - **Point of Contact:** [Conceptual Captions e-mail](mailto:[email protected]) ### Dataset Summary Conceptual 12M (CC12M) is a dataset with 12 million image-text pairs specifically meant to be used for visionand-language pre-training. Its data collection pipeline is a relaxed version of the one used in Conceptual Captions 3M (CC3M). ### Usage This instance of Conceptual Captions is in [webdataset](https://github.com/webdataset/webdataset/commits/main) .tar format. It can be used with webdataset library or upcoming releases of Hugging Face `datasets`. ...More Detail TBD ### Data Splits This dataset was downloaded using img2dataset. Images resized on download if shortest edge > 512 to shortest edge = 512. #### Train * `cc12m-train-*.tar` * Downloaded on 2021/18/22 * 2176 shards, 10968539 samples ## Additional Information ### Dataset Curators Soravit Changpinyo, Piyush Sharma, Nan Ding and Radu Soricut. ### Licensing Information The dataset may be freely used for any purpose, although acknowledgement of Google LLC ("Google") as the data source would be appreciated. The dataset is provided "AS IS" without any warranty, express or implied. Google disclaims all liability for any damages, direct or indirect, resulting from the use of the dataset. ### Citation Information ```bibtex @inproceedings{changpinyo2021cc12m, title = {{Conceptual 12M}: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts}, author = {Changpinyo, Soravit and Sharma, Piyush and Ding, Nan and Soricut, Radu}, booktitle = {CVPR}, year = {2021}, } ```

tiange/Cap3D

tiange

--- license: odc-by viewer: false task_categories: - text-to-3d - image-to-3d --- ## Dataset Description - **Paper:** [Scalable 3D Captioning with Pretrained Models](https://arxiv.org/abs/2306.07279) - **Paper:** [View Selection for 3D Captioning via Diffusion Ranking](https://arxiv.org/abs/2404.07984) - **Repository**: [Github_Cap3D](https://github.com/crockwell/Cap3D) - **Repository**: [Github_DiffuRank](https://github.com/tiangeluo/DiffuRank) - **Project**: [Project](https://cap3d-um.github.io/) This repository hosts data for [Scalable 3D Captioning with Pretrained Models](https://cap3d-um.github.io/) and [View Selection for 3D Captioning via Diffusion Ranking](http://arxiv.org/abs/2404.07984), including descriptive **captions** for 3D objects in [Objaverse](https://arxiv.org/abs/2212.08051), [Objaverse-XL](https://arxiv.org/pdf/2307.05663.pdf), [ABO](https://arxiv.org/abs/2110.06199), and [ShapeNet](https://arxiv.org/abs/1512.03012). This repo also includes **point clouds** and **rendered images with camera, depth, and MatAlpha information** of Objaverse objects, as well as their Shap-E latent codes. All the captions and data provided by our papers are released under ODC-By 1.0 license. ## Usage Please download and unzip files from [**Page**](https://huggingface.co./datasets/tiange/Cap3D/tree/main) according to your usage. Below is a table listing fiels descriptions, followed by example Python scripts for data loading. | Filename | Description | | -------------------------------------- | ------------------------------------------------------------ | | **Cap3D_automated_Objaverse_full.csv** | By integrating text descriptions initially generated by [Cap3D](https://arxiv.org/abs/2306.07279) and subsequently refined by [DiffuRank](https://arxiv.org/abs/2404.07984), we have produced a total of **1,006,782** 3D-caption pairs. Out of the total, **785,150** pairs have been contributed to the whole [Objaverse](https://arxiv.org/abs/2212.08051) dataset, with the balance for the [Objaverse-XL](https://arxiv.org/pdf/2307.05663.pdf) dataset (specifically the highquality subset described in Section 4.1 Alignment Finetuning of [Objaverse-XL](https://proceedings.neurips.cc/paper_files/paper/2023/file/70364304877b5e767de4e9a2a511be0c-Paper-Datasets_and_Benchmarks.pdf)). For the object identifier in the left column, strings with a length of 32 characters are **UIDs** from Objaverse 1.0 (retrieved using `import objaverse; uids = objaverse.load_uids()`). Strings with a length of 64 characters are **SHA256** hashes provided by Objaverse-XL. | | Cap3D_automated_**ABO**.csv | Our captions generated by [Cap3D](https://arxiv.org/abs/2306.07279) and [DiffuRank](https://arxiv.org/abs/2404.07984) for the [ABO dataset](https://arxiv.org/abs/2110.06199), including both general and compositional descriptions. | | Cap3D_automated_**ShapeNet**.csv | Our captions generated by [Cap3D](https://arxiv.org/abs/2306.07279) and [DiffuRank](https://arxiv.org/abs/2404.07984) for the [ShapeNet dataset](https://arxiv.org/abs/1512.03012). | | **PointCloud_zips** | Provided by [Cap3D](https://arxiv.org/abs/2306.07279) and [DiffuRank](https://arxiv.org/abs/2404.07984), **1,006,782** PointClouds (16,384 colorful points) extracted from Objaverse objects. Saved as `.ply` file. | | PointCloud_zips_**ABO** | Provided by [Cap3D](https://arxiv.org/abs/2306.07279) and [DiffuRank](https://arxiv.org/abs/2404.07984), **7,953** PointClouds (16,384 colorful points) extracted from ABO objects. Saved as `.ply` file. | | PointCloud_zips_**ShapeNet** | Provided by [Cap3D](https://arxiv.org/abs/2306.07279) and [DiffuRank](https://arxiv.org/abs/2404.07984), **52,472** PointClouds (16,384 colorful points) extracted from ShapeNet objects. Saved as `.ply` file. | | **RenderedImage_perobj_zips** | Provided by [DiffuRank](https://arxiv.org/abs/2404.07984), Rendered images for **1,006,782** Objaverse objects. Once unzip `compressed_imgs_perobj_xx.zip` will have multiple zip files which consists of **20** rendered images along with camera details (intrinsic & extrinsic), depth data, and masks ([one example](https://huggingface.co./datasets/tiange/Cap3D/tree/main/RenderedImage_perobj_zips/example_zipfile)). Please specify the unzip path, such as `unzip ed51a51909ee46c780db3a85e821feb2.zip -d ed51a51909ee46c780db3a85e821feb2`. More information are in [here](https://huggingface.co./datasets/tiange/Cap3D/blob/main/RenderedImage_perobj_zips/README.md). | | RenderedImage_perobj_zips_**ABO** | Provided by [DiffuRank](https://arxiv.org/abs/2404.07984), Rendered images for **7,953** ABO objects. Details similar to the above. | | RenderedImage_perobj_zips_**ShapeNet** | Provided by [DiffuRank](https://arxiv.org/abs/2404.07984), Rendered images for **52,472** ShapeNet objects. Similar to the above but with 8 rendered images. | | misc | Including miscellaneous files such as human-authored captions, finetuned models, objaverse pointclouds stored as .pt, shapE latent codes, and etc. Please refer to this [README](https://huggingface.co./datasets/tiange/Cap3D/blob/main/misc/README.md) | ``` python # load our captions import pandas as pd captions = pd.read_csv('Cap3D_automated_Objaverse_full.csv', header=None) ## captions: ## 0 1 ## 0 ed51a51909ee46c780db3a85e821feb2 Matte green rifle with a long barrel, stock, a... ## 1 9110b606f6c547b2980fcb3c8c4b6a1c Rustic single-story building with a weathered ... ## 2 80d9caaa1fa04502af666135196456e1 a pair of purple and black swords with white h... ## 3 28d43a218cd8466a8c1f82b29b71e314 3D model of a cluttered outdoor scene with veg... ## 4 75582285fab442a2ba31733f9c8fae66 Floating terrain piece with grassy landscape a... ## ... ... ... ## 1002417 3623e74f34c1c3c523af6b2bb8ffcbe2d2dce897ef61b9... Abstract 3D composition with human figures and... ## 1002418 64e9f7b7a1fc4c4ec56ed8b5917dfd610930043ac5e15f... 3D object with a rough, irregular pink surface... ## 1002419 fcd089d6a237fee21dfd5f0d6d9b74b2fd1150cdc61c7f... Bright pink abstract 3D model of a building wi... ## 1002420 f812dc980050f2d5f4b37df2a8620372f810dd6456a5f2... Monochromatic gray 3D model of a stylized huma... ## 1002421 77c09500b4d8e4b881e1ce6929d56c23658b87173c0996... Modular futuristic spacecraft with red and ora... ## if u want to obtain the caption for specific UID caption = captions[captions[0] == '80d9caaa1fa04502af666135196456e1'][1].values[0] # load point clouds (unzip https://huggingface.co./datasets/tiange/Cap3D/tree/main/PointCloud_pt_zips) import torch pts = torch.load('Cap3D_pcs_pt/80d9caaa1fa04502af666135196456e1.pt') ## pts.shape == torch.Size([6, 16384]) ``` If you have any questions, please contact [Tiange](mailto:[email protected]) or [Chris](mailto:[email protected]). ## Citation Information If you find our data or code useful, please consider citing: ```bibtex @article{luo2023scalable, title={Scalable 3D Captioning with Pretrained Models}, author={Luo, Tiange and Rockwell, Chris and Lee, Honglak and Johnson, Justin}, journal={arXiv preprint arXiv:2306.07279}, year={2023} } @article{luo2024view, title={View Selection for 3D Captioning via Diffusion Ranking}, author={Luo, Tiange and Johnson, Justin and Lee, Honglak}, journal={arXiv preprint arXiv:2404.07984}, year={2024} } ``` Please cite ***Objaverse*** and ***ABO*** paper accordingly, if you use related data. ``` @inproceedings{deitke2023objaverse, title={Objaverse: A universe of annotated 3d objects}, author={Deitke, Matt and Schwenk, Dustin and Salvador, Jordi and Weihs, Luca and Michel, Oscar and VanderBilt, Eli and Schmidt, Ludwig and Ehsani, Kiana and Kembhavi, Aniruddha and Farhadi, Ali}, booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition}, pages={13142--13153}, year={2023} } @article{deitke2024objaverse, title={Objaverse-xl: A universe of 10m+ 3d objects}, author={Deitke, Matt and Liu, Ruoshi and Wallingford, Matthew and Ngo, Huong and Michel, Oscar and Kusupati, Aditya and Fan, Alan and Laforte, Christian and Voleti, Vikram and Gadre, Samir Yitzhak and others}, journal={Advances in Neural Information Processing Systems}, volume={36}, year={2024} } @inproceedings{collins2022abo, title={Abo: Dataset and benchmarks for real-world 3d object understanding}, author={Collins, Jasmine and Goel, Shubham and Deng, Kenan and Luthra, Achleshwar and Xu, Leon and Gundogdu, Erhan and Zhang, Xi and Vicente, Tomas F Yago and Dideriksen, Thomas and Arora, Himanshu and others}, booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition}, pages={21126--21136}, year={2022} } ```

mteb/sts15-sts

mteb

--- language: - en ---

deepghs/gelbooru_full

deepghs

--- license: other task_categories: - image-classification - zero-shot-image-classification - text-to-image language: - en tags: - art - anime - not-for-all-audiences size_categories: - 10M<n<100M annotations_creators: - no-annotation source_datasets: - gelbooru --- # Gelbooru Full Dataset This is the full dataset of [gelbooru.com](https://gelbooru.com/). And all the original images are maintained here. # How to Painlessly Use This Use [cheesechaser](https://github.com/deepghs/cheesechaser) to quickly get images from this repository. Before using this code, you have to **grant the access from this gated repository**. And then **set your personal HuggingFace token into `HF_TOKEN` environment variable** to give the code authorization for this repository. ```python from cheesechaser.datapool import GelbooruDataPool pool = GelbooruDataPool() pool.batch_download_to_directory( # download images #7000000-7000100, any ranges or id lists are okay resource_ids=range(7000000, 7000100), # save to directory /data/gelbooru dst_dir='/data/gelbooru', ) ``` # Information ## Images There are 10102818 images in total. The maximum ID of these images is 11191859. Last updated at `2025-01-03 05:29:50 JST`. These are the information of recent 50 images: | id | filename | width | height | mimetype | tags | file_size | file_url | |---------:|:--------------|--------:|---------:|:-----------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|------------:|:-----------------------------------------------------------------------------| | 11191859 | 11191859.jpeg | 1211 | 2048 | image/jpeg | 1boy black_bodysuit blue_eyes bodysuit closed_mouth colored_skin dragon_ball dragon_ball_super earrings expressionless fused_zamasu green_skin jewelry long_sleeves looking_at_viewer luna_306 pointy_ears potara_earrings red_sash sash solo spiked_hair white_hair | 304541 | https://img3.gelbooru.com/images/77/34/7734c747ab552629e27b6781697af073.jpeg | | 11191858 | 11191858.jpeg | 1953 | 2859 | image/jpeg | 1girl aile_(mega_man_zx) alternate_breast_size arms_at_sides artist_name black_bodysuit black_footwear blannis blue_background blue_footwear blue_jacket bodysuit boots bracelet breasts brown_hair capcom covered_collarbone covered_navel cropped_jacket embarrassed eyebrows eyelashes female_focus from_above full_body green_eyes grin jacket jewelry large_breasts lips long_hair looking_at_viewer looking_up low_ponytail mega_man_(series) multicolored_footwear multicolored_jacket nervous nervous_smile open_clothes open_jacket ponytail shorts simple_background smile solo standing teeth two-tone_jacket white_shorts yellow_footwear yellow_jacket | 308768 | https://img3.gelbooru.com/images/8e/fa/8efa0dfc7e83f44bd45ffc8133746e35.jpeg | | 11191857 | 11191857.png | 1993 | 2464 | image/png | 1boy 1girl absurdres ahegao alternate_hairstyle anal artist_name bandages belly black_eyes black_thighhighs blunt_bangs breasts breasts_out clenched_hand clothes_lift clothes_pull colored_pubic_hair covering_privates cum cum_in_ass cum_on_ass cum_on_body cum_on_lower_body drooling english_text eyelashes female_masturbation fingernails frilled_shirt frilled_sleeves frills grabbing_another's_breast green_hair green_pubic_hair groping heart heart-shaped_pupils highres large_breasts long_hair long_sleeves looking_ahead looking_at_another lying makeup masturbating_while_penetrated masturbation midriff miniskirt moaning nail_polish navel nipples on_back one_piece open_mouth patreon_username pelvic_curtain penis perona pink_eyes pink_hair pink_nails pleated_skirt pussy pussy_juice pussy_juice_trail pussy_rub red_skirt roronoa_zoro runny_makeup saliva saliva_trail sex shirt shirt_pull short_hair simple_background skirt skirt_lift skull_and_crossbones skull_print snegovski sparkle_background speech_bubble star_(symbol) star_print star_tattoo steam steaming_body stomach striped_clothes striped_thighhighs sweat sweatdrop symbol-shaped_pupils tattoo tearing_up teeth testicles thighhighs tongue topless_male torn_clothes torn_thighhighs two-tone_thighhighs veins very_long_hair white_shirt white_thighhighs | 5741788 | https://img3.gelbooru.com/images/2e/e9/2ee9bfe452b6bef6948c1d37e0529ff0.png | | 11191856 | 11191856.jpeg | 3568 | 2813 | image/jpeg | 2boys bodysuit closed_mouth dougi dragon_ball dragon_ball_super earrings expressionless eye_contact gimdol_z goku_black greyscale jewelry long_sleeves looking_at_another mohawk monochrome multiple_boys parted_lips pointy_ears potara_earrings saiyan shirt short_hair spiked_hair white_background white_hair zamasu | 734125 | https://img3.gelbooru.com/images/82/48/8248dc9d6efc694637011522741149af.jpeg | | 11191855 | 11191855.jpeg | 768 | 1024 | image/jpeg | 1girl 2boys :d ash_ketchum asymmetrical_hair black_footwear black_hair blush boots bow brock_(pokemon) brown_hair brown_pants capelet christmas closed_eyes closed_mouth creatures_(company) fur_trim game_freak gen_1_pokemon gift gloves green_eyes hat holding hood jacket misty_(pokemon) multiple_boys nintendo onix open_mouth orange_hair pants pikachu pokemon ponytail psyduck sack santa_costume santa_hat shoes short_hair side_ponytail sitting smile squatting sweatdrop tongue | 156370 | https://img3.gelbooru.com/images/16/75/1675e80998438d8f47b6e474eeddae3d.jpeg | | 11191854 | 11191854.jpeg | 1307 | 1200 | image/jpeg | 1girl :3 blush closed_eyes closed_mouth creatures_(company) eevee game_freak gen_1_pokemon highres misty_(pokemon) nintendo open_mouth orange_hair pokemon pokemon_rgby seashell shell smile starfish starmie staryu swimming vaporeon water yurano_(upao) | 815648 | https://img3.gelbooru.com/images/78/a1/78a1edb96b87093ee4394ab1d90c40ef.jpeg | | 11191853 | 11191853.jpg | 1879 | 2756 | image/jpeg | 1girl absurdres bare_shoulders breasts cigarette cleavage collarbone dark-skinned_female dark_skin ear_piercing highres holding holding_cigarette huge_breasts monochrome name_tag norman_maggot off-shoulder_shirt off_shoulder olverse original pencil_skirt piercing sarah_(ol-chan) shirt short_hair skirt solo swept_bangs thighs | 244863 | https://img3.gelbooru.com/images/8f/be/8fbe58951b2a4845a4b9ac002ba1e566.jpg | | 11191852 | 11191852.png | 1198 | 1255 | image/png | 1boy 1girl aristocratic_clothes blue_eyes color_guide commentary dated english_commentary fire_emblem fire_emblem_fates gradient_clothes gradient_hair highres japanese_clothes limited_palette long_hair male_focus multicolored_hair nintendo one_eye_closed ponytail red_eyes red_ribbon ribbon sandragh signature simple_background solo takumi_(fire_emblem) two-tone_eyes very_long_hair | 971525 | https://img3.gelbooru.com/images/82/39/823936c08bf752e98dab4cf5c8ed45eb.png | | 11191851 | 11191851.jpg | 2468 | 1635 | image/jpeg | 6+girls ahoge akari_(blue_archive) angcha apron bad_food black_bow black_coat black_hair black_hat black_horns black_shirt blonde_hair blue_archive blue_halo blunt_bangs bow braid breasts breath_weapon breathing_fire brown_eyes brown_hair closed_eyes closed_mouth coat collared_shirt cooking demon_girl demon_horns eating fire food frilled_sleeves frills fuuka_(blue_archive) hair_on_horn halo haruna_(blue_archive) hat headscarf highres holding holding_detonator holding_food horns iori_(blue_archive) izumi_(blue_archive) junko_(blue_archive) juri_(blue_archive) kettle lantern large_breasts long_hair long_sleeves multiple_girls necktie night open_mouth puffy_long_sleeves puffy_sleeves purple_halo red_hair red_halo red_necktie sanpaku scarf school_uniform shirt shoes short_necktie side_braid sidelocks smile tearing_up twintails white_apron white_hair white_shirt wiping_mouth yellow_halo | 499829 | https://img3.gelbooru.com/images/4e/44/4e44b9ab450725b80d042a8565a0f98c.jpg | | 11191850 | 11191850.jpg | 1390 | 900 | image/jpeg | 1girl alternate_costume blue_eyes blue_sky border breasts commentary elysia_(honkai_impact) english_commentary hairband honkai_(series) honkai_impact_3rd long_hair lying nami_(tznami) on_back parted_lips pink_hair sky smile snow solo sweater tree twitter_username white_border white_hairband white_sweater | 141503 | https://img3.gelbooru.com/images/54/61/54618b41d4a01d14d6b9aab3f051ba63.jpg | | 11191849 | 11191849.png | 1296 | 1148 | image/png | 1boy abs ass bald bandaged_chest bandages blood bloody_bandages bodysuit clenched_hand closed_eyes closed_mouth commentary_request dragon_ball dragon_ball_super from_behind greyscale hit_(dragon_ball) kamatama_(bobojobobo) looking_down male_focus monochrome multiple_views muscular muscular_male solo sound_effects topless_male twitter_username veins veiny_arms | 640513 | https://img3.gelbooru.com/images/f7/5d/f75ded0d0af252383e61a56a9e8ded37.png | | 11191848 | 11191848.jpg | 3000 | 3000 | image/jpeg | 1boy absurdres artist_name black_fur bracelet cape christmas chromatic_aberration closed_mouth commentary feet_out_of_frame film_grain fur-trimmed_headwear fur_trim furry furry_male glint gloves hat hedgehog_boy highres instagram_logo instagram_username jewelry looking_at_viewer male_focus red_cape red_eyes red_fur red_hat santa_hat shadow_the_hedgehog shiiyou shoes smile snowflakes solo sonic_(series) symbol-only_commentary twitter_username twitter_x_logo two-tone_fur white_footwear white_gloves | 2152633 | https://img3.gelbooru.com/images/f4/23/f423150983af5d9a5c54808bb0e10d0c.jpg | | 11191847 | 11191847.jpg | 1763 | 3294 | image/jpeg | 1girl :d absurdres artist_name belt black_thighhighs blonde_hair blurry blurry_background breasts burnice_white commentary cup drinking_glass english_commentary eyewear_on_head fingernails fire foxyreine highres holding holding_cup large_breasts looking_at_viewer medium_hair nail_polish naked_ribbon navel open_mouth red_belt red_eyes red_nails ribbon smile solo standing stomach sunglasses teeth thighhighs thighs twintails zenless_zone_zero | 672121 | https://img3.gelbooru.com/images/8a/e4/8ae4b90c57c2908788eb44e05464f762.jpg | | 11191846 | 11191846.jpg | 2718 | 4096 | image/jpeg | 1girl absurdres akami_chiyo black_hair black_necktie black_pants black_tail chromatic_aberration collared_shirt ear_piercing earrings fins fish_tail highres indie_virtual_youtuber jewelry light_blush long_hair looking_at_viewer necktie pants piercing plunplun red_eyes red_hair red_shirt sharp_teeth shirt solo tail teeth virtual_youtuber wing_collar | 830643 | https://img3.gelbooru.com/images/5b/2b/5b2bb15468ebb759d55825e6ef0640bc.jpg | | 11191845 | 11191845.png | 1012 | 1433 | image/png | 1girl :p bike_shorts blue_eyes blush breasts brown_hair cameltoe clothes_pull covering_breasts covering_privates creatures_(company) game_freak grey_background groin highres holding huuuna large_breasts licking_lips looking_at_viewer may_(pokemon) navel nintendo pokemon pokemon_rse pulling_own_clothes red_shirt shirt short_hair shorts skirt skirt_pull solo thighs tongue tongue_out undressing | 746214 | https://img3.gelbooru.com/images/cc/d3/ccd32a632db8e9d2e7eadfacc03473a0.png | | 11191844 | 11191844.png | 2200 | 2200 | image/png | 2girls :d adapted_costume alternate_costume armpits bare_shoulders bat_tattoo beelstarmon bell belt bikini bikini_top_only black_belt black_gloves black_hair black_leotard black_mask black_shorts black_vest blonde_hair blue_eyes box breasts capelet christmas chromatic_aberration cleavage collarbone commentary covered_navel cropped_legs cropped_vest dclaret demon_girl demon_wings detached_sleeves digimon digimon_(creature) elbow_gloves english_commentary eye_mask eyeshadow facial_mark forehead_mark forehead_tattoo fur-trimmed_bikini fur-trimmed_capelet fur-trimmed_shorts fur_trim gift gift_box gloves green_ribbon grin groin hair_ornament hand_up highres holding holding_gift holding_sack horns jingle_bell large_breasts leotard lilithmon long_hair looking_at_viewer makeup mask merry_christmas multiple_girls navel one_eye_closed open_fly open_mouth parted_bangs pointy_ears purple_eyeshadow purple_lips red_background red_bikini red_capelet red_ribbon red_sleeves ribbon sack see-through_cleavage see-through_clothes short_hair short_shorts shorts sidelocks smile standing stomach striped_ribbon swimsuit tattoo teeth third_eye twitter_username underboob v vest wings | 10262725 | https://img3.gelbooru.com/images/6c/0a/6c0a6f3cf889cc2bde83a79394b0b961.png | | 11191843 | 11191843.jpg | 1508 | 2048 | image/jpeg | 1girl black_hair black_ribbon blazer bloom blurry blurry_background book closed_mouth commentary depth_of_field fangs flower fukumaru_koito grey_jacket grey_skirt hair_down hair_flower hair_ornament highres holding holding_book hugging_book hugging_object idolmaster idolmaster_shiny_colors jacket lens_flare light_rays long_sleeves looking_at_viewer medium_hair neck_ribbon pink_eyes pleated_skirt qinglai_haiji ribbon school_uniform shirt sidelighting skin_fangs skirt smile solo sparkle sparkling_aura symbol-only_commentary wavy_hair white_shirt | 313690 | https://img3.gelbooru.com/images/81/95/81957e2dc97875dde99456b6ed4eb835.jpg | | 11191842 | 11191842.jpg | 1920 | 1200 | image/jpeg | 1boy 2girls :3 :d apple_on_head arm_wrap arrow_through_apple baggy_pants black_gloves black_hair black_shirt blonde_hair blue_eyes blue_pants blush bow brown_jacket brown_pants brown_sash brown_shirt brown_skirt colored_skin copyright_notice creature crescent crop_top flower flower_on_head full_body fur-trimmed_sleeves fur_trim gloves green_skin guest_art gun gunslinger_(ragnarok_online) hair_bow hanbok highres holding holding_gun holding_weapon ice ice_cave in-universe_location jacket korean_clothes logo long_sleeves looking_at_another medium_hair multiple_girls navel ninja_(ragnarok_online) obi obijime official_art official_wallpaper open_clothes open_jacket open_mouth orc pants pink_bow pink_flower ragnarok_online sash shirt siroma sitting skirt sleeveless sleeveless_shirt smile soul_linker_(ragnarok_online) standing sui_hutami weapon | 1250973 | https://img3.gelbooru.com/images/b4/17/b41738db807d035a9a2dd8e06bddce8c.jpg | | 11191841 | 11191841.jpg | 1910 | 2048 | image/jpeg | 2girls ? bare_shoulders black_gloves breasts brown_jacket cleavage clothing_cutout collared_shirt commentary dress gloves grey_hair highres jacket jewelry large_breasts long_hair long_sleeves multiple_girls necklace o_204 off_shoulder parted_bangs path_to_nowhere pricilla_(path_to_nowhere) purple_hair red_dress red_lips shirt simple_background strapless strapless_dress swept_bangs tetra_(path_to_nowhere) underboob_cutout upper_body white_background white_shirt | 373507 | https://img3.gelbooru.com/images/dc/65/dc65c57fef534bf69fa3b96dfc0837a2.jpg | | 11191840 | 11191840.jpg | 1920 | 1200 | image/jpeg | 1girl 2boys armor armored_boots bandeau beret bikini bikini_bottom_only black_hair black_tabard blue_bikini blue_hat blush boots breastplate cape chibi copyright_notice cross detached_sleeves flat_chest full_body green_eyes green_hat guest_art gypsy_(ragnarok_online) hat highres hitting jewelry kankiriko leg_armor living_armor logo long_hair lord_knight_(ragnarok_online) multiple_boys navel necklace official_art official_wallpaper open_mouth pauldrons poop_on_head purple_hair ragnarok_online red_cape red_sleeves running shaded_face shoulder_armor solo_focus swimsuit sword_guardian tabard white_bandeau | 1685423 | https://img3.gelbooru.com/images/4d/16/4d160a96e4e268ba4b7d371b7c947c5a.jpg | | 11191839 | 11191839.jpg | 3096 | 4096 | image/jpeg | 1girl absurdres anna_o_renko bandeau bikini blurry blurry_background blush breasts earrings elbow_gloves elle_(vtuber) fur-trimmed_gloves fur-trimmed_headwear fur_trim gloves hat highres hoop_earrings indie_virtual_youtuber jewelry large_breasts looking_at_viewer medium_breasts navel reaching reaching_towards_viewer red_bikini red_hair revealing_clothes santa_bikini santa_gloves santa_hat skindentation smile solo swimsuit twitter_username virtual_youtuber yellow_eyes | 776765 | https://img3.gelbooru.com/images/c7/b4/c7b4ae4c490365e6fd23a37fc0c9b175.jpg | | 11191838 | 11191838.jpg | 4440 | 7761 | image/jpeg | 1girl absurdres alternate_color arm_under_breasts armpit_crease artist_name ascot bare_shoulders blurry blurry_background bottomless censored check_clothing christmas_tree closed_mouth clothing_request commentary convenient_censoring covered_eyes cup drinking_glass english_commentary english_text feather_boa fingernails flower hair_ribbon hat hat_flower herta_(honkai:_star_rail) highres holding holding_cup honkai:_star_rail honkai_(series) indoors jewelry key key_necklace lilpalette long_hair merry_christmas nail_polish necklace red_flower red_hat red_nails red_ribbon ribbon smile solo the_herta_(honkai:_star_rail) very_long_hair white_ascot witch_hat | 9162960 | https://img3.gelbooru.com/images/03/93/0393d5cbc0e589baee262b5ae1f302de.jpg | | 11191837 | 11191837.jpg | 1189 | 2048 | image/jpeg | animal_print bat_print breasts burning burnt collarbone covered_erect_nipples covered_pussy darkstalkers fire green_hair head_wings highres large_breasts messy_hair midriff morrigan_aensland navel nude pantyhose print_pantyhose rokuba tagme torn_clothes wings | 241410 | https://img3.gelbooru.com/images/a3/a6/a3a6d416b9c5f962412d839152a86345.jpg | | 11191836 | 11191836.jpg | 2894 | 4093 | image/jpeg | 1girl :d absurdres blush bow brown_eyes brown_hair coat commentary_request eyelashes hair_bow happy high_ponytail highres inukai_komugi jacket long_hair looking_at_viewer one_eye_closed open_mouth ponytail precure rice_rabbit22 scarf smile snow snowman solo white_jacket winter_clothes winter_coat wonderful_precure! | 1625799 | https://img3.gelbooru.com/images/05/b3/05b3a84394b6e680826e4756c70d1af9.jpg | | 11191835 | 11191835.jpg | 1920 | 1200 | image/jpeg | 3boys 3girls animal_ears armor assassin_(ragnarok_online) assassin_cross_(ragnarok_online) bandages black_gloves black_leotard black_shirt black_wings blunt_bangs bob_cut bow bow_bra bra breasts brown_gloves brown_hair brown_jacket castle cat_ears cat_girl cherry_blossoms cleavage closed_mouth copyright_notice dagger dark-skinned_female dark_skin demon_girl demon_horns demon_wings dog_boy dog_ears elbow_gloves falling fingerless_gloves fish_in_mouth food fox_mask gloves green_eyes grey_eyes grey_hair grin guest_art head_wings highres holding holding_dagger holding_knife holding_weapon horns jacket jamadhar knife large_breasts leotard logo long_hair long_sleeves looking_at_viewer mask mask_on_head meat medium_breasts multiple_boys multiple_girls official_art official_wallpaper one_eye_closed open_mouth pauldrons pointy_ears purple_shirt ragnarok_online red_bow red_scarf scarf shirt short_hair shoulder_armor shrug_(clothing) sideboob sleeveless sleeveless_shirt small_breasts smile thief_(ragnarok_online) torn_clothes torn_scarf underwear upper_body vambraces weapon white_bra wings yuikawa_kazuno | 1428894 | https://img3.gelbooru.com/images/19/4a/194a6d01a2c0c0247e8e7b6d15744f0c.jpg | | 11191834 | 11191834.jpg | 2894 | 4093 | image/jpeg | 1girl absurdres animal_ear_fluff animal_ear_piercing animal_ears black_bow black_bowtie black_choker black_skirt blouse bow bowtie brooch cat_ears cat_girl cat_tail choker chromatic_aberration collared_shirt crossed_bangs enya_yoruneko flying_sweatdrops frilled_shirt frilled_skirt frills green_eyes hair_bow heart heart_brooch highres indie_virtual_youtuber jewelry leaning_forward light_blush long_hair looking_at_viewer multicolored_hair pink_hair pink_tail plunplun puffy_short_sleeves puffy_sleeves shirt short_sleeves skirt smile solo streaked_hair suspender_skirt suspenders tail virtual_youtuber white_hair white_shirt | 1346220 | https://img3.gelbooru.com/images/ac/7c/ac7c2284d81e38a484313f5fb2fc7465.jpg | | 11191833 | 11191833.png | 4303 | 6314 | image/png | 1girl absurdres ass ass_focus back black_choker blending breasts ceres_fauna choker colored_inner_hair commentary cowboy_shot cross-laced_clothes cross-laced_dress dress earrings english_commentary frilled_dress frills from_behind greatodoggo green_hair hair_over_one_eye hair_over_shoulder hand_on_own_chest highres hololive hololive_english horns huge_ass jewelry large_breasts long_hair looking_at_viewer mole mole_under_eye multicolored_hair negative_space one_eye_covered panties parted_lips short_dress sideboob skindentation smile solo thick_thighs thighhighs thighs tree_horns underwear virtual_youtuber white_background white_dress white_hair white_panties white_thighhighs yellow_eyes | 6700316 | https://img3.gelbooru.com/images/f5/a0/f5a036874d1805474906e7e31966bf7b.png | | 11191832 | 11191832.jpg | 1248 | 1135 | image/jpeg | 1other burning exposed_heart fire headless mask najashi oni_mask original rope skeleton standing undead white_rope | 242779 | https://img3.gelbooru.com/images/4e/cc/4eccaf1f020fece510abe916ec25430b.jpg | | 11191831 | 11191831.jpeg | 1000 | 1000 | image/jpeg | 1boy 1girl agpro back-to-back black_hair blue_hair closed_mouth creatures_(company) dress eyelashes game_freak grey_eyes hand_up hat misty_(pokemon) nintendo petals pokemon pokemon_adventures red_(pokemon) shirt short_hair smile upper_body | 876912 | https://img3.gelbooru.com/images/4c/90/4c904a5209c1c207aa07d70e03583bd7.jpeg | | 11191830 | 11191830.jpeg | 699 | 992 | image/jpeg | 1boy 1girl aged_up agpro bad_tag blush breasts closed_mouth creatures_(company) game_freak gym_leader hair_between_eyes looking_at_viewer looking_back misty_(pokemon) nintendo pokemon pokemon_adventures red_(pokemon) shirt short_hair smile | 251624 | https://img3.gelbooru.com/images/37/b5/37b59d6bbc46c52d9ce575a1ec4ac53f.jpeg | | 11191829 | 11191829.png | 2500 | 3125 | image/png | 1girl all_fours animal_ears bare_shoulders black_thighhighs bleach breasts cat_ears cat_paws collarbone dae_dae dark-skinned_female dark_skin fake_animal_ears fake_tail female_focus hair_ornament hanging_breasts highres large_breasts lips long_hair panties parted_bangs ponytail purple_hair shihouin_yoruichi shiny_skin simple_background skindentation tail thighhighs thighs underwear white_background yellow_eyes | 2195504 | https://img3.gelbooru.com/images/11/2a/112a7124e50bc594fa9cd061e707c003.png | | 11191828 | 11191828.jpeg | 2507 | 3541 | image/jpeg | 1girl aftersex akan_mori bikini blonde_hair character_request cum cum_in_pussy dot_nose eyelashes female_focus gloves looking_at_viewer open_mouth pink_hair pink_theme ponytail pussy smile solo sweat swimsuit thick_thighs thighhighs thighs v white_bikini white_gloves white_thighhighs | 585834 | https://img3.gelbooru.com/images/44/52/4452b3447c6676572805642b1bbc71ed.jpeg | | 11191827 | 11191827.png | 3069 | 2170 | image/png | 1boy 4girls absurdres adventurer ahoge arm_behind_head armor belt bikini_armor black_hair blonde_hair blue_eyes breasts closed_eyes collar commission commissioner_upload dagger elf flat_chest glasses green_eyes hair_bun highres hilda_(someinternetloser) knife large_breasts loincloth medium_breasts monika_tatsumi multiple_girls nipples original pointy_ears ponytail purple_hair red_eyes red_hair shield short_hair slave staff sword tattoo_on_neck the_dark_mangaka topless topless_male warrior weapon witch yellow_eyes | 5497138 | https://img3.gelbooru.com/images/84/93/8493d5c5db2721fd856a2d0d3d4b1bfe.png | | 11191826 | 11191826.jpeg | 1000 | 1414 | image/jpeg | 2girls blood christmas gift_bag loli multiple_girls no_panties nosebleed onii-chan_wa_oshimai! oyama_mahiro | 374780 | https://img3.gelbooru.com/images/21/2b/212b47ee1726af6044e1a19a6a364015.jpeg | | 11191825 | 11191825.jpeg | 2859 | 1953 | image/jpeg | 2girls arms_under_breasts artist_name bare_legs black_hair black_jacket black_pants blannis blush breasts closed_mouth coat creatures_(company) crossed_arms crossed_legs dendra_(pokemon) embarrassed eye_contact eyebrows eyelashes eyeshadow feet_out_of_frame female_focus fingerless_gloves fingernails from_side game_freak gloves green_eyes hand_in_pocket huge_breasts implied_yuri indoors jacket large_breasts leaning_forward lips long_fingernails long_sleeves looking_at_another makeup medium_hair miriam_(pokemon) multicolored_hair multicolored_jacket multiple_girls nail_polish nervous nervous_sweating nintendo nose_blush orange_eyes pants parted_lips pink_eyeshadow pink_hair pokemon pokemon_sv ponytail purple_hair purple_skirt sidelocks sitting skirt streaked_hair sweat sweater table teeth track_jacket two-tone_hair two-tone_jacket two-tone_pants wavy_mouth white_coat yellow_jacket yellow_nails yellow_pants yellow_sweater | 602270 | https://img3.gelbooru.com/images/b1/a5/b1a5b076fe70e3b1dfc819160733dd7a.jpeg | | 11191824 | 11191824.jpeg | 1351 | 2048 | image/jpeg | 1girl blue_hair blush boots collar crop_top earrings eyeliner heart jewelry long_hair makeup nintendo octoling red_eyes shiver_(splatoon) sitting skirt smile solo splatoon_(series) splatoon_3 tentacle_hair | 229399 | https://img3.gelbooru.com/images/b9/b1/b9b15820baaead6c7441369132b0fd77.jpeg | | 11191823 | 11191823.jpeg | 1900 | 2600 | image/jpeg | crossover dark-skinned_female dark_skin green_hair hands_behind_own_head iggybomb jungle_de_ikou mecha_pilot_suit mii_(jungle_de_ikou) neon_genesis_evangelion plugsuit shiny_clothes shiny_skin smile tan | 254683 | https://img3.gelbooru.com/images/bc/94/bc945eab8fe815fc06b64e6a5b45df7c.jpeg | | 11191822 | 11191822.jpeg | 1792 | 2600 | image/jpeg | breasts cleavage crossover eiken gigantic_breasts hand_on_own_hip huge_breasts iggybomb long_hair mecha_pilot_suit misono_kirika neon_genesis_evangelion plugsuit purple_eyes purple_hair salute shiny_clothes sidelocks smile v very_long_hair wide_hips | 291791 | https://img3.gelbooru.com/images/b8/b4/b8b4dca4d61f8bc15be6293ff35f70b0.jpeg | | 11191821 | 11191821.jpeg | 1884 | 2600 | image/jpeg | blonde_hair breasts crossover hellsing huge_breasts iggybomb large_breasts mecha_pilot_suit medium_hair neon_genesis_evangelion plugsuit salute seras_victoria | 264715 | https://img3.gelbooru.com/images/99/d3/99d342cf945304401337cfd03ec8c0b6.jpeg | | 11191820 | 11191820.jpeg | 4096 | 1936 | image/jpeg | blonde_hair blue_eyes breasts cleavage crossover dark-skinned_female dark_skin eiken gigantic_breasts green_hair hand_on_own_hip hands_behind_own_head hellsing huge_breasts iggybomb jungle_de_ikou large_breasts long_hair mecha_pilot_suit medium_hair mii_(jungle_de_ikou) misono_kirika multiple_crossover neon_genesis_evangelion plugsuit purple_eyes purple_hair salute seras_victoria shiny_clothes sidelocks smile tan v very_long_hair wide_hips | 545268 | https://img3.gelbooru.com/images/01/19/0119d42770015a5b58c0bb4323af30d9.jpeg | | 11191819 | 11191819.jpeg | 3541 | 2507 | image/jpeg | 1girl akan_mori blonde_hair blue_background blue_flower breasts fang female_focus fingerless_gloves flower gloves hood horns japanese_text large_breasts looking_at_viewer open_mouth purple_eyes skin_fang smile solo translation_request v | 789262 | https://img3.gelbooru.com/images/63/1d/631d8b6c472a66179d18ec5a8b4777c1.jpeg | | 11191818 | 11191818.jpeg | 1000 | 1000 | image/jpeg | 3girls animal_costume antlers bell chloe_von_einzbern christmas fate/kaleid_liner_prisma_illya fate_(series) hanagata_kai horns illyasviel_von_einzbern looking_at_viewer miyu_edelfelt multiple_girls reindeer_antlers reindeer_costume ribbon | 330059 | https://img3.gelbooru.com/images/08/dc/08dc542046dc19486ec9d187c70dca61.jpeg | | 11191817 | 11191817.jpeg | 768 | 1024 | image/jpeg | 1girl adversarial_noise blunt_bangs blush collarbone grey_hair humanization kokei_hakai long_hair looking_at_viewer marie_(splatoon) mole mole_under_eye nintendo open_mouth solo splatoon_(series) splatoon_3 strapless suspenders tube_top upper_body yellow_eyes | 117805 | https://img3.gelbooru.com/images/a7/c8/a7c812144b3be77a4b6614196c92eb32.jpeg | | 11191816 | 11191816.png | 2800 | 2600 | image/png | 1boy 1girl absurdly_long_hair absurdres akari_(pokemon) arms_behind_back ass bdsm black_bodysuit black_eyes blue_hair blue_jacket blush bodysuit bondage bound bound_wrists breasts creatures_(company) crotch_rope cursed_delta drooling fellatio female_focus fur-trimmed_sleeves fur_trim game_freak headband headscarf highres huge_ass jacket large_breasts long_hair long_sleeves looking_at_viewer looking_to_the_side looking_up multiple_views nintendo nipples obi obijime open_clothes open_jacket oral penis pokemon pokemon_legends:_arceus red_scarf rope saliva sash scarf seductive_gaze seductive_smile shibari shibari_over_clothes short_sleeves sidelocks simple_background skin_tight skindentation smile solo_focus thick_thighs thighs very_long_hair white_background white_headband white_headscarf | 3176723 | https://img3.gelbooru.com/images/7f/18/7f18952ec046882bb5772a1adf336e71.png | | 11191815 | 11191815.png | 2800 | 2600 | image/png | 1boy 1girl absurdly_long_hair absurdres akari_(pokemon) arms_behind_back ass ball_gag bdsm black_bodysuit black_eyes blue_hair blue_jacket blush bodysuit bondage bound bound_wrists breasts creatures_(company) crotch_rope cursed_delta drooling fellatio female_focus fur-trimmed_sleeves fur_trim gag gagged game_freak headband headscarf highres huge_ass jacket large_breasts long_hair long_sleeves looking_at_viewer looking_to_the_side looking_up multiple_views nintendo nipples obi obijime open_clothes open_jacket oral penis pokemon pokemon_legends:_arceus red_scarf rope saliva sash scarf seductive_gaze seductive_smile shibari shibari_over_clothes short_sleeves sidelocks simple_background skin_tight skindentation smile solo_focus thick_thighs thighs very_long_hair white_background white_headband white_headscarf | 2794396 | https://img3.gelbooru.com/images/bd/1e/bd1e33b5310b354cd4b9bd1fe5ef19d2.png | | 11191814 | 11191814.png | 2800 | 2600 | image/png | 1boy 1girl absurdly_long_hair absurdres akari_(pokemon) arms_behind_back ass ball_gag bdsm black_bodysuit black_eyes blue_hair blue_jacket blush bodysuit bondage bound bound_wrists breasts creatures_(company) crotch_rope cursed_delta drooling fellatio female_focus fur-trimmed_sleeves fur_trim gag gagged game_freak headband headscarf highres huge_ass jacket large_breasts long_hair long_sleeves looking_at_viewer looking_to_the_side looking_up multiple_views nintendo obi obijime oral penis pokemon pokemon_legends:_arceus red_scarf rope saliva sash scarf seductive_gaze seductive_smile shibari shibari_over_clothes short_sleeves sidelocks simple_background skin_tight skindentation smile solo_focus thick_thighs thighs very_long_hair white_background white_headband white_headscarf | 2776945 | https://img3.gelbooru.com/images/29/c5/29c578f9d1bcfb82470bab61f0c11e9c.png | | 11191813 | 11191813.png | 2894 | 4093 | image/png | 1girl absurdres animal_ear_piercing animal_ears ball bare_shoulders beachball bikini bikini_top_only bow breasts brown_hair brown_tail camouflage_bikini_top collarbone commentary_request cowlick double_bikini eyewear_on_head fangs full_body gold_necklace hair_ornament hairclip highres horse_ears horse_girl horse_tail jewelry jungle_pocket_(umamusume) layered_bikini light_blush looking_at_viewer navel nebusoku necklace open_mouth sidelocks sky small_breasts solo swimsuit tail umamusume water water_drop wet yellow_bikini yellow_eyes | 4551495 | https://img3.gelbooru.com/images/b0/3c/b03cbbe84d24b14211e74c3c25477c02.png | | 11191812 | 11191812.jpeg | 1277 | 1381 | image/jpeg | 1girl child cool-kyou_shinja dragon_girl dragon_horns dragon_tail dress hat horns kanna_kamui kobayashi-san_chi_no_maidragon official_art santa_costume santa_dress santa_hat speech_bubble tail | 177509 | https://img3.gelbooru.com/images/54/63/5463202c29fa1e71219f7225670fb487.jpeg | | 11191811 | 11191811.jpg | 2970 | 4096 | image/jpeg | 1girl absurdres animal_ears artist_name black_pants blue_coat branch coat creature feet_out_of_frame fox_ears fox_girl grey_scarf hair_between_eyes hair_ornament hairclip hat highres holding holding_creature light_particles looking_at_viewer muted_color outdoors pants phase_connect purple_eyes santa_hat scarf short_hair sitting snow snowing swing taku_artworks tenma_maemi theo_(tenma_maemi) watermark white_hair winter winter_clothes | 856135 | https://img3.gelbooru.com/images/e3/63/e363f0ca671d10baa7653d1c4938756f.jpg | | 11191810 | 11191810.jpg | 1320 | 1978 | image/jpeg | 18dikart 5girls animal_ears apricot_the_lich bipsygg black_hair blonde_hair blue_eyes blush box breasts cat_tail christmas_tree commentary demon_horns dress dyarikku_(vtuber) english_commentary fur-trimmed_dress fur-trimmed_headwear fur_trim green_eyes grey_hair hat highres horns huge_breasts in_box in_container indie_virtual_youtuber long_hair looking_at_viewer mini_person minigirl multicolored_hair multiple_girls obkatiekat pink_hair purple_horns red_dress santa_dress santa_hat second-party_source smile solo solo_focus tail twintails twitter_username two-tone_hair virtual_youtuber vshojo yellow_eyes | 362979 | https://img3.gelbooru.com/images/64/cd/64cd174856c93216ca37f5b9947add02.jpg | ## Tags There are 969173 tags in total. These are the top 30 tags (125 tags in total) of type `unknown (-1)`: | id | name | type | count | ambiguous | |-----:|:--------------------------------------------------------------------------------------------------------------------------------------------|-------:|--------:|:------------| | -1 | straightchromia | -1 | 263 | False | | -1 | gekijigen_tag:_blanc_+_neptune_vs_zombie_gundan | -1 | 171 | False | | -1 | seiki_kyushu | -1 | 23 | False | | -1 | toyotaro | -1 | 15 | False | | -1 | ensemble_stars!;character:akehoshi_subaru;happy_elements;male | -1 | 9 | False | | -1 | _double_dash!! | -1 | 7 | False | | -1 | dash!! | -1 | 7 | False | | -1 | fubuki_kyoko | -1 | 7 | False | | -1 | mario_k | -1 | 7 | False | | -1 | star_\(symbol\) | -1 | 7 | False | | -1 | \// | -1 | 6 | False | | -1 | shrug_\(clothing\) | -1 | 6 | False | | -1 | € | -1 | 6 | False | | -1 | kami-sama_onegai!_onii-chan_no_aka-chan_ninshin_shitai_no!_~tsundere_imouto_&_seijun_imouto_to_ecchi_na_kiseki_de_trouble_kozukuri_zanmai♪~ | -1 | 5 | False | | -1 | slime_\(creature\) | -1 | 5 | False | | -1 | \\// | -1 | 4 | False | | -1 | akizuki_rasenn | -1 | 4 | False | | -1 | juju_(pixiv4563634) | -1 | 4 | False | | -1 | pom_pom_\(clothes\) | -1 | 4 | False | | -1 | source:https://nijie.info/view.php?id=151930 | -1 | 4 | False | | -1 | +\l.l./+_(path_to_nowhere) | -1 | 3 | False | | -1 | handing_breasts | -1 | 3 | False | | -1 | star_\(sky\) | -1 | 3 | False | | -1 | /tm | -1 | 2 | False | | -1 | compl\pussy | -1 | 2 | False | | -1 | mahitoⅶ | -1 | 2 | False | | -1 | to_heart:_remember_my_memories | -1 | 2 | False | | -1 | ulquiorra_schiffer | -1 | 2 | False | | -1 | violet_plan | -1 | 2 | False | | -1 | "artist: | -1 | 1 | False | These are the top 30 tags (454442 tags in total) of type `general (0)`: | id | name | type | count | ambiguous | |-------:|:------------------|-------:|--------:|:------------| | 152532 | 1girl | 0 | 6971160 | False | | 12336 | solo | 0 | 5465193 | False | | 265 | long_hair | 0 | 4666744 | True | | 27 | breasts | 0 | 4408977 | False | | 33975 | looking_at_viewer | 0 | 3646980 | False | | 92 | blush | 0 | 3543354 | False | | 796 | smile | 0 | 3091345 | False | | 1100 | open_mouth | 0 | 2664446 | False | | 52 | short_hair | 0 | 2404809 | False | | 67 | blue_eyes | 0 | 2040706 | False | | 28545 | simple_background | 0 | 1996572 | False | | 21905 | large_breasts | 0 | 1992413 | False | | 271 | blonde_hair | 0 | 1792287 | False | | 1999 | shirt | 0 | 1781163 | False | | 66 | black_hair | 0 | 1706716 | True | | 337 | brown_hair | 0 | 1703242 | False | | 179739 | white_background | 0 | 1633759 | False | | 138893 | 1boy | 0 | 1621309 | False | | 107 | skirt | 0 | 1589035 | False | | 98 | gloves | 0 | 1424182 | True | | 1864 | hair_ornament | 0 | 1422965 | False | | 175068 | multiple_girls | 0 | 1412393 | False | | 51 | red_eyes | 0 | 1392377 | True | | 13957 | long_sleeves | 0 | 1371983 | False | | 3477 | navel | 0 | 1345295 | False | | 432 | nipples | 0 | 1327179 | False | | 123 | dress | 0 | 1312217 | False | | 23 | thighhighs | 0 | 1298307 | False | | 6383 | holding | 0 | 1233592 | False | | 153 | animal_ears | 0 | 1187147 | False | These are the top 30 tags (281452 tags in total) of type `artist (1)`: | id | name | type | count | ambiguous | |--------:|:-------------------------|-------:|--------:|:------------| | 46733 | qp:flapper | 1 | 15602 | False | | 555502 | kagami_hirotaka | 1 | 8255 | False | | 219408 | nel-zel_formula | 1 | 8087 | False | | 594229 | ebifurya | 1 | 5771 | False | | 719488 | aoi_nagisa_(metalder) | 1 | 5407 | False | | 470499 | haruyama_kazunori | 1 | 5386 | False | | 25270 | lolita_channel | 1 | 4910 | False | | 401040 | hammer_(sunset_beach) | 1 | 4824 | False | | 603058 | butcha-u | 1 | 4539 | False | | 56027 | yaegashi_nan | 1 | 4460 | False | | 67040 | piromizu | 1 | 4309 | False | | 38088 | yoko_juusuke | 1 | 4149 | False | | 21718 | drawfag | 1 | 4005 | False | | 652987 | ruu_(tksymkw) | 1 | 3879 | False | | 118829 | kanon_(kurogane_knights) | 1 | 3876 | False | | 487842 | boris_(noborhys) | 1 | 3760 | False | | 76506 | circle_anco | 1 | 3733 | False | | 410 | azasuke | 1 | 3622 | False | | 1128557 | kou_hiyoyo | 1 | 3409 | False | | 380097 | matsunaga_kouyou | 1 | 3399 | False | | 1069930 | tony_taka | 1 | 3397 | False | | 481438 | itomugi-kun | 1 | 3288 | False | | 729154 | naga_u | 1 | 3177 | False | | 1051176 | hara_(harayutaka) | 1 | 3069 | False | | 569895 | ojipon | 1 | 3047 | False | | 354817 | bow_(bhp) | 1 | 3023 | False | | 445614 | blade_(galaxist) | 1 | 2989 | False | | 355711 | rebecca_(keinelove) | 1 | 2960 | False | | 14795 | awa | 1 | 2856 | True | | 509171 | neocoill | 1 | 2814 | False | These are the top 30 tags (39877 tags in total) of type `copyright (3)`: | id | name | type | count | ambiguous | |--------:|:----------------------------|-------:|--------:|:------------| | 118 | original | 3 | 1271600 | False | | 126 | touhou | 3 | 780895 | False | | 44106 | nintendo | 3 | 622394 | False | | 448625 | kantai_collection | 3 | 423460 | True | | 43567 | pokemon | 3 | 360475 | False | | 306228 | game_freak | 3 | 358171 | False | | 875834 | creatures_(company) | 3 | 358153 | False | | 342429 | fate_(series) | 3 | 331416 | False | | 1037340 | blue_archive | 3 | 247426 | False | | 545521 | fate/grand_order | 3 | 239095 | False | | 86 | idolmaster | 3 | 235513 | True | | 943985 | genshin_impact | 3 | 225557 | False | | 865663 | hololive | 3 | 217524 | False | | 44086 | vocaloid | 3 | 162662 | False | | 705390 | love_live! | 3 | 150758 | False | | 807658 | arknights | 3 | 135727 | False | | 805915 | azur_lane | 3 | 130432 | False | | 338818 | idolmaster_cinderella_girls | 3 | 120701 | False | | 5074 | fire_emblem | 3 | 112653 | False | | 924 | digimon | 3 | 110402 | False | | 851189 | umamusume | 3 | 102438 | False | | 238 | final_fantasy | 3 | 98925 | False | | 878809 | honkai_(series) | 3 | 88965 | False | | 247 | one_piece | 3 | 81736 | False | | 374082 | girls_und_panzer | 3 | 66277 | False | | 237493 | mahou_shoujo_madoka_magica | 3 | 64504 | False | | 1048700 | hololive_english | 3 | 63359 | False | | 845788 | nijisanji | 3 | 62314 | False | | 1121184 | girls'_frontline | 3 | 61995 | False | | 7 | gundam | 3 | 60344 | True | These are the top 30 tags (189513 tags in total) of type `character (4)`: | id | name | type | count | ambiguous | |--------:|:-------------------------|-------:|--------:|:------------| | 14087 | hatsune_miku | 4 | 110217 | False | | 855 | hakurei_reimu | 4 | 60150 | False | | 130 | kirisame_marisa | 4 | 50925 | False | | 486 | flandre_scarlet | 4 | 46348 | False | | 850 | remilia_scarlet | 4 | 40828 | False | | 1141830 | artoria_pendragon_(fate) | 4 | 37556 | False | | 849 | izayoi_sakuya | 4 | 34169 | False | | 36382 | komeiji_koishi | 4 | 30410 | False | | 848 | konpaku_youmu | 4 | 29152 | False | | 1293 | cirno | 4 | 27961 | False | | 127 | alice_margatroid | 4 | 26944 | False | | 484 | patchouli_knowledge | 4 | 26748 | False | | 14543 | kochiya_sanae | 4 | 26447 | False | | 658 | yakumo_yukari | 4 | 25307 | False | | 83295 | souryuu_asuka_langley | 4 | 23178 | False | | 481 | shameimaru_aya | 4 | 22636 | False | | 237491 | akemi_homura | 4 | 21506 | False | | 847 | reisen_udongein_inaba | 4 | 21363 | False | | 237492 | kaname_madoka | 4 | 21311 | False | | 24290 | nami_(one_piece) | 4 | 20849 | False | | 36383 | komeiji_satori | 4 | 20748 | False | | 761745 | saber_(fate) | 4 | 20348 | False | | 125 | fujiwara_no_mokou | 4 | 20203 | False | | 493 | saigyouji_yuyuko | 4 | 20145 | False | | 14131 | kagamine_rin | 4 | 20139 | False | | 15099 | inubashiri_momiji | 4 | 20050 | False | | 804254 | artoria_pendragon_(all) | 4 | 20043 | False | | 1059472 | ganyu_(genshin_impact) | 4 | 18785 | False | | 881 | link | 4 | 18193 | False | | 2335 | tifa_lockhart | 4 | 17440 | False | These are the top 30 tags (407 tags in total) of type `metadata (5)`: | id | name | type | count | ambiguous | |--------:|:-----------------------|-------:|--------:|:------------| | 262 | highres | 5 | 5951899 | False | | 559 | absurdres | 5 | 1992877 | False | | 150649 | commentary_request | 5 | 1188848 | False | | 136261 | bad_id | 5 | 831072 | False | | 760546 | bad_pixiv_id | 5 | 698226 | False | | 25266 | commentary | 5 | 653731 | False | | 136 | translation_request | 5 | 522206 | False | | 1306 | official_art | 5 | 324500 | False | | 52372 | tagme | 5 | 300150 | False | | 23213 | artist_request | 5 | 247617 | False | | 831896 | english_commentary | 5 | 243145 | False | | 69 | game_cg | 5 | 189273 | True | | 209468 | commission | 5 | 155812 | False | | 13710 | translated | 5 | 155707 | False | | 2229 | lowres | 5 | 113509 | False | | 47252 | character_request | 5 | 110757 | False | | 755092 | bad_twitter_id | 5 | 103829 | False | | 19982 | traditional_media | 5 | 84434 | False | | 789724 | chinese_commentary | 5 | 83837 | False | | 888401 | non-web_source | 5 | 73076 | False | | 853984 | third-party_edit | 5 | 64375 | False | | 426 | scan | 5 | 64344 | False | | 66551 | copyright_request | 5 | 63246 | False | | 323949 | revision | 5 | 56986 | False | | 1139885 | symbol-only_commentary | 5 | 56930 | False | | 1034097 | skeb_commission | 5 | 53527 | False | | 1223605 | paid_reward_available | 5 | 44609 | False | | 191513 | md5_mismatch | 5 | 39240 | False | | 2481 | source_request | 5 | 38997 | False | | 63275 | huge_filesize | 5 | 34145 | True | These are the top 30 tags (3357 tags in total) of type `deprecated (6)`: | id | name | type | count | ambiguous | |--------:|:------------------|-------:|--------:|:------------| | 275 | silver_hair | 6 | 336682 | False | | 205 | striped | 6 | 264451 | False | | 24219 | see-through | 6 | 160050 | False | | 286 | uniform | 6 | 159560 | True | | 214641 | grabbing | 6 | 145175 | False | | 3404 | plaid | 6 | 137228 | False | | 889718 | black_headwear | 6 | 112049 | False | | 264199 | black_legwear | 6 | 102146 | False | | 56035 | light_brown_hair | 6 | 87604 | False | | 850221 | white_headwear | 6 | 82957 | False | | 264263 | white_legwear | 6 | 80489 | False | | 47407 | looking_away | 6 | 65435 | False | | 2818 | ass_grab | 6 | 59394 | False | | 918581 | red_headwear | 6 | 41346 | False | | 82157 | french_braid | 6 | 36466 | False | | 54997 | multiple_penises | 6 | 36286 | False | | 853048 | blue_headwear | 6 | 35686 | False | | 17164 | breast_hold | 6 | 35279 | False | | 18310 | vertical_stripes | 6 | 34542 | False | | 1048560 | light_purple_hair | 6 | 33258 | False | | 26046 | arm_grab | 6 | 26380 | False | | 712440 | red_neckwear | 6 | 26251 | False | | 488916 | oni_horns | 6 | 25061 | False | | 670 | wallpaper | 6 | 24516 | False | | 268269 | torn_legwear | 6 | 21955 | False | | 51586 | screencap | 6 | 20524 | False | | 842746 | green_headwear | 6 | 20207 | False | | 918583 | brown_headwear | 6 | 20205 | False | | 265499 | striped_legwear | 6 | 19590 | False | | 20303 | turret | 6 | 17887 | False |

mlabonne/FineTome-100k

mlabonne

--- dataset_info: features: - name: conversations list: - name: from dtype: string - name: value dtype: string - name: source dtype: string - name: score dtype: float64 splits: - name: train num_bytes: 239650960.7474458 num_examples: 100000 download_size: 116531415 dataset_size: 239650960.7474458 configs: - config_name: default data_files: - split: train path: data/train-* --- # FineTome-100k  The FineTome dataset is a subset of [arcee-ai/The-Tome](https://huggingface.co./datasets/arcee-ai/The-Tome) (without arcee-ai/qwen2-72b-magpie-en), re-filtered using [HuggingFaceFW/fineweb-edu-classifier](https://huggingface.co./HuggingFaceFW/fineweb-edu-classifier). It was made for my article ["Fine-tune Llama 3.1 Ultra-Efficiently with Unsloth"](https://huggingface.co./blog/mlabonne/sft-llama3).

laion/laion-audio-preview

laion

--- license: apache-2.0 ---

lmms-lab/textvqa

lmms-lab

--- dataset_info: features: - name: image_id dtype: string - name: question_id dtype: int32 - name: question dtype: string - name: question_tokens sequence: string - name: image dtype: image - name: image_width dtype: int32 - name: image_height dtype: int32 - name: flickr_original_url dtype: string - name: flickr_300k_url dtype: string - name: answers sequence: string - name: image_classes sequence: string - name: set_name dtype: string - name: ocr_tokens sequence: string splits: - name: train num_bytes: 9839776032.652 num_examples: 34602 - name: validation num_bytes: 1438831837.0 num_examples: 5000 - name: test num_bytes: 1712000724.844 num_examples: 5734 download_size: 8097805782 dataset_size: 12990608594.496 configs: - config_name: default data_files: - split: train path: data/train-* - split: validation path: data/validation-* - split: test path: data/test-* --- <p align="center" width="100%"> <img src="https://i.postimg.cc/g0QRgMVv/WX20240228-113337-2x.png" width="100%" height="80%"> </p> # Large-scale Multi-modality Models Evaluation Suite > Accelerating the development of large-scale multi-modality models (LMMs) with `lmms-eval` 🏠 [Homepage](https://lmms-lab.github.io/) | 📚 [Documentation](docs/README.md) | 🤗 [Huggingface Datasets](https://huggingface.co./lmms-lab) # This Dataset This is a formatted version of [TextVQA](https://textvqa.org/). It is used in our `lmms-eval` pipeline to allow for one-click evaluations of large multi-modality models. ``` @inproceedings{singh2019towards, title={Towards vqa models that can read}, author={Singh, Amanpreet and Natarajan, Vivek and Shah, Meet and Jiang, Yu and Chen, Xinlei and Batra, Dhruv and Parikh, Devi and Rohrbach, Marcus}, booktitle={Proceedings of the IEEE/CVF conference on computer vision and pattern recognition}, pages={8317--8326}, year={2019} } ```

OpenDriveLab/OpenScene

OpenDriveLab

--- license: cc-by-nc-sa-4.0 ---

common-canvas/commoncatalog-cc-by

common-canvas

--- license: cc-by-4.0 dataset_info: features: - name: jpg dtype: image - name: blip2_caption dtype: string - name: caption dtype: string - name: licensename dtype: string - name: licenseurl dtype: string - name: width dtype: int32 - name: height dtype: int32 - name: original_width dtype: int32 - name: original_height dtype: int32 - name: photoid dtype: int64 - name: uid dtype: string - name: unickname dtype: string - name: datetaken dtype: timestamp[us] - name: dateuploaded dtype: int64 - name: capturedevice dtype: string - name: title dtype: string - name: usertags dtype: string - name: machinetags dtype: string - name: longitude dtype: float64 - name: latitude dtype: float64 - name: accuracy dtype: int64 - name: pageurl dtype: string - name: downloadurl dtype: string - name: serverid dtype: int64 - name: farmid dtype: int64 - name: secret dtype: string - name: secretoriginal dtype: string - name: ext dtype: string - name: url dtype: string - name: key dtype: string - name: status dtype: string - name: error_message dtype: string - name: exif dtype: string - name: sha256 dtype: string - name: description dtype: string task_categories: - text-to-image language: - en --- # Dataset Card for CommonCatalog CC-BY This dataset is a large collection of high-resolution Creative Common images (composed of different licenses, see paper Table 1 in the Appendix) collected in 2014 from users of Yahoo Flickr. The dataset contains images of up to 4k resolution, making this one of the highest resolution captioned image datasets. ## Dataset Details ### Dataset Description We provide captions synthetic captions to approximately 100 million high resolution images collected from Yahoo Flickr Creative Commons (YFCC). - **Curated by:** Aaron Gokaslan - **Language(s) (NLP):** en - **License:** See relevant yaml tag / dataset name. ### Dataset Sources <!-- Provide the basic links for the dataset. --> - **Repository:** https://github.com/mosaicml/diffusion - **Paper:** https://arxiv.org/abs/2310.16825 - **Demo:** See CommonCanvas Gradios ## Uses We use CommonCatalog to train a family latent diffusion models called CommonCanvas. The goal is to produce a model that is competitive with Stable Diffusion 2, but to do so using an easily accessible dataset of known provenance. Doing so makes replicating the model significantly easier, and provides a clearer mechanism for applying training-data attribution techniques. ### Direct Use Training text-to-image models Training image-to-text models ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the dataset will not work well for. --> * Crafting content that is offensive or injurious towards individuals, including negative portrayals of their living conditions, cultural backgrounds, religious beliefs, etc. * Deliberately creating or spreading content that is discriminatory or reinforces harmful stereotypes. * Falsely representing individuals without their permission. * Generating sexual content that may be seen by individuals without their consent. * Producing or disseminating false or misleading information. * Creating content that depicts extreme violence or bloodshed. * Distributing content that modifies copyrighted or licensed material in a way that breaches its usage terms. ## Dataset Structure The dataset is divided into 10 subsets each containing parquets about 4GB each. Each subfolder within contains a resolution range of the images and their respective aspect ratios. The dataset is also divided along images licensed for commercial use (C) and those that are not (NC). ## Dataset Creation ### Curation Rationale Creating a standardized, accessible dataset with synthetic caption and releasing it so other people can train on a common dataset for open source image generation. ### Source Data Yahoo Flickr Creative Commons 100M Dataset and Synthetically Generated Caption Data. #### Data Collection and Processing All synthetic captions were generated with BLIP2. See paper for more details. #### Who are the source data producers? <!-- This section describes the people or systems who originally created the data. It should also include self-reported demographic or identity information for the source data creators if this information is available. --> Users of Flickr ## Bias, Risks, and Limitations See Yahoo Flickr Creative Commons 100M dataset for more information. The information was collected circa 2014 and known to have a bias towards internet connected Western countries. Some areas such as the global south lack representation. ## Citation **BibTeX:** ``` @article{gokaslan2023commoncanvas, title={CommonCanvas: An Open Diffusion Model Trained with Creative-Commons Images}, author={Gokaslan, Aaron and Cooper, A Feder and Collins, Jasmine and Seguin, Landan and Jacobson, Austin and Patel, Mihir and Frankle, Jonathan and Stephenson, Cory and Kuleshov, Volodymyr}, journal={arXiv preprint arXiv:2310.16825}, year={2023} } ``` ## Dataset Card Authors [Aaron Gokaslan](https://huggingface.co./Skylion007) ## Dataset Card Contact [Aaron Gokaslan](https://huggingface.co./Skylion007)

togethercomputer/RedPajama-Data-1T-Sample

togethercomputer

--- task_categories: - text-generation language: - en pretty_name: Red Pajama 1T Sample --- # Dataset Card for Dataset Name ### Dataset Summary RedPajama is a clean-room, fully open-source implementation of the LLaMa dataset. This HuggingFace repo contains a 1B-token sample of the RedPajama dataset. The full dataset has the following token counts and is available for [download]( https://huggingface.co./datasets/togethercomputer/RedPajama-Data-1T): | Dataset | Token Count | |---------------|-------------| | Commoncrawl | 878 Billion | | C4 | 175 Billion | | GitHub | 59 Billion | | Books | 26 Billion | | ArXiv | 28 Billion | | Wikipedia | 24 Billion | | StackExchange | 20 Billion | | Total | 1.2 Trillion | A full set of scripts to recreate the dataset from scratch can be found [here](https://github.com/togethercomputer/RedPajama-Data). ### Languages Primarily English, though the Wikipedia slice contains multiple languages. ## Dataset Structure The dataset structure is as follows: ``` { "text": ..., "meta": {"url": "...", "timestamp": "...", "source": "...", "language": "...", ...} } ``` ## Dataset Creation This dataset was created to follow the LLaMa paper as closely as possible to try to reproduce its recipe. ### Source Data #### Commoncrawl We download five dumps from Commoncrawl, and run the dumps through the official `cc_net` pipeline. We then deduplicate on the paragraph level, and filter out low quality text using a linear classifier trained to classify paragraphs as Wikipedia references or random Commoncrawl samples. #### C4 C4 is downloaded from Huggingface. The only preprocessing step is to bring the data into our own format. #### GitHub The raw GitHub data is downloaded from Google BigQuery. We deduplicate on the file level and filter out low quality files and only keep projects that are distributed under the MIT, BSD, or Apache license. #### Wikipedia We use the Wikipedia dataset available on Huggingface, which is based on the Wikipedia dump from 2023-03-20 and contains text in 20 different languages. The dataset comes in preprocessed format, so that hyperlinks, comments and other formatting boilerplate has been removed. #### Gutenberg and Books3 The PG19 subset of the Gutenberg Project and Books3 datasets are downloaded from Huggingface. After downloading, we use simhash to remove near duplicates. #### ArXiv ArXiv data is downloaded from Amazon S3 in the `arxiv` requester pays bucket. We only keep latex source files and remove preambles, comments, macros and bibliographies. #### Stackexchange The Stack Exchange split of the dataset is download from the [Internet Archive](https://archive.org/download/stackexchange). Here we only keep the posts from the 28 largest sites, remove html tags, group the posts into question-answer pairs, and order answers by their score. <!-- ### Annotations #### Annotation process [More Information Needed] #### Who are the annotators? [More Information Needed] ### Personal and Sensitive Information [More Information Needed] ## Considerations for Using the Data ### Social Impact of Dataset [More Information Needed] ### Discussion of Biases [More Information Needed] ### Other Known Limitations [More Information Needed] ## Additional Information ### Dataset Curators [More Information Needed] ### Licensing Information [More Information Needed] ### Citation Information [More Information Needed] ### Contributions [More Information Needed] -->

mlfoundations/MINT-1T-PDF-CC-2023-14

mlfoundations

--- license: cc-by-4.0 task_categories: - image-to-text - text-generation language: - en tags: - multimodal pretty_name: MINT-1T size_categories: - 100B<n<1T --- <h1 align="center"> 🍃 MINT-1T:<br>Scaling Open-Source Multimodal Data by 10x:<br> A Multimodal Dataset with One Trillion Tokens </h1> 🍃 MINT-1T is an open-source **M**ultimodal **INT**erleaved dataset with 1 trillion text tokens and 3.4 billion images, a 10x scale-up from existing open-source datasets. Additionally, we include previously untapped sources such as PDFs and ArXiv papers. 🍃 MINT-1T is designed to facilitate research in multimodal pretraining. 🍃 MINT-1T is created by a team from the University of Washington in collaboration with Salesforce Research, other academic institutions including Stanford University, University of Texas at Austin, and University of California Berkeley. You are currently viewing a subset of the PDF portion of 🍃 MINT-1T associated with CommonCrawl dump `CC-2023-14`. For other PDF, HTML, and ArXiv subsets, refer to the [🍃 MINT-1T collection](https://huggingface.co./collections/mlfoundations/mint-1t-6690216ca4d0df7e518dde1c).  ## Updates ### 9/19/24 We have removed roughly 10% of the PDF samples as there was a mismatch between the frames in the TIFF images and the document metadata. ### 8/8/24 We have become aware that the image hashes in the PDF subset of MINT-1T do not match the images in the documents. We want to emphasize that the images for each document are correct, and only the image hashes in the documents' metadata are mislabeled. ## Dataset Details ### Dataset Sources - **Repository**: https://github.com/mlfoundations/MINT-1T - **Paper:** https://arxiv.org/abs/2406.11271 - **Blog:** https://blog.salesforceairesearch.com/mint-1t/ ## Uses ### Direct Use <!-- This section describes suitable use cases for the dataset. --> 🍃 MINT-1T is designed to facilitate research in multimodal pretraining. The dataset can be used for training multimodal models that can reson about interleaved text and images sequences such as [Idefics2](https://huggingface.co./HuggingFaceM4/idefics2-8b), [XGen-MM](https://huggingface.co./Salesforce/xgen-mm-phi3-mini-instruct-r-v1), and [Chameleon](https://huggingface.co./facebook/chameleon-30b). ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the dataset will not work well for. --> 🍃 MINT-1T was built to make research into large multimodal models more accessible. Using the dataset to train models that ingest or generate personally identifying information (such as images of people’s faces and other sensitive content) as well as military applications are all inappropriate use cases of 🍃 MINT-1T. ## Dataset Creation ### Curation Rationale 🍃 MINT-1T was created to address a significant gap in the open-source domain by providing a large-scale multimodal interleaved dataset for pre-training large multimodal models. This dataset aims to be a valuable resource for the research community, facilitating open science in multimodal pretraining. ### Source Data The dataset is a comprehensive collection of multimodal documents from various sources: - HTML documents: Filtered from CommonCrawl WARC dumps spanning from 2017 to 2024 - PDF documents: Extracted from CommonCrawl WAT dumps covering 2023 to 2024 - ArXiv documents: A subset of papers from the ArXiv repository In total, 🍃 MINT-1T contains 1056.8 million documents, broken down as follows: - 1029.4 million HTML documents - 24.0 million PDF documents - 0.6 million ArXiv documents #### Data Collection and Processing The data collection and processing involved several steps: 1. Document Extraction: - HTML documents were parsed from CommonCrawl WARC files - PDF documents were extracted from CommonCrawl WAT files - ArXiv papers were directly sourced from ArXiv S3 buckets 2. Filtering Process: - Applied text quality filters to ensure content relevance and readability - Removed duplicate content at both paragraph and document levels - Filtered out undesirable content based on predefined criteria - Verified image availability and quality for HTML documents - Limited PDF size to 50MB and 50 pages to manage dataset size and quality 3. Image Processing: - Used NSFW image detection to remove pornographic or otherwise undesirable images - Removed images smaller than 150 pixels or larger than 20,000 pixels - Adjusted aspect ratio thresholds for HTML (2:1) and PDF (3:1) to preserve scientific figures 4. Text Processing: - Used fasttext for language identification, focusing on English content - Masked personally identifiable information such as email addresses and IP addresses - Applied paragraph and document-level deduplication using Bloom filters 5. PDF Specific Processing: - Used PyMuPDF for parsing PDFs and extracting reading order - Clustered text blocks based on columns and ordered from top left to bottom right 6. ArXiv Specific Processing: - Used TexSoup to parse LaTeX source code and interleave images with text - Cleaned up LaTeX code by removing imports, bibliography, tables, and citation tags Various open-source tools were utilized in this process, including fasttext, [PyMuPDF](https://github.com/pymupdf/PyMuPDF), and [DCLM](https://www.datacomp.ai/dclm/) and [bff](https://github.com/revbucket/bff) for deduplication and content filtering. #### Personal and Sensitive Information Despite sourcing from public web data, significant efforts were made to minimize the inclusion of personal and sensitive information: - Email addresses and IP addresses were masked to protect privacy - An NSFW image classifierto remove inappropriate visual content - URLs containing substrings associated with undesirable or sensitive content were filtered out However, users should be aware that as the data originates from the public web, it may still contain some sensitive or personal information. The dataset creators acknowledge this limitation and advise users to exercise caution and potentially apply additional filtering based on their specific use cases. ## Bias, Risks, and Limitations Several potential biases, risks, and limitations have been identified: 1. Data Bias: As the dataset is sourced from web crawls, it may inherit biases present in online content. 2. Content Risks: Despite extensive filtering, there's a possibility that some offensive, insensitive, or inappropriate content may remain in the dataset. 3. Image Availability: The dataset relies on external image URLs, which may become unavailable over time due to link rot, potentially affecting the dataset's long-term usability. 4. PDF Parsing Limitations: The current method for extracting reading order from PDFs may not always accurately capture the intended flow, especially for documents with complex layouts. 5. Potential Legal and Ethical Concerns: While efforts were made to respect robots.txt files and remove sensitive information, there may still be content that individuals did not explicitly consent to include. ### Recommendations Given these considerations, the following recommendations are provided: 1. Additional Filtering: Users are strongly encouraged to apply additional filtering based on their specific use case and ethical considerations. 2. Inappropriate Use Cases: The dataset is not recommended for applications involving the processing or generation of personally identifying information, nor for military applications. 3. Legal Compliance: Users should independently verify compliance with applicable laws before employing MINT-1T for commercial purposes. 4. Bias Awareness: Researchers and developers should be cognizant of potential biases in the dataset and consider their impact on model training and outputs. ## License We release 🍃 MINT-1T under a CC-BY-4.0 license, designating it primarily as a research artifact. While the dataset is freely available, users are responsible for ensuring its legal use in commercial settings. Users must independently verify compliance with applicable laws before employing MINT-1T for commercial purposes. ## Citation ``` @article{awadalla2024mint1t, title={MINT-1T: Scaling Open-Source Multimodal Data by 10x: A Multimodal Dataset with One Trillion Tokens}, author={Anas Awadalla and Le Xue and Oscar Lo and Manli Shu and Hannah Lee and Etash Kumar Guha and Matt Jordan and Sheng Shen and Mohamed Awadalla and Silvio Savarese and Caiming Xiong and Ran Xu and Yejin Choi and Ludwig Schmidt}, year={2024} } ```

fixie-ai/peoples_speech

fixie-ai

--- dataset_info: - config_name: clean features: - name: id dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: duration_ms dtype: int32 - name: text dtype: string - name: continuation dtype: string splits: - name: validation num_bytes: 2511523987.692 num_examples: 18622 - name: test num_bytes: 4259695510.794 num_examples: 34898 - name: train num_bytes: 401646320552.671 num_examples: 1501271 download_size: 398922548670 dataset_size: 408417540051 - config_name: dirty_sa features: - name: id dtype: string - name: audio dtype: audio: sampling_rate: 16000 - name: duration_ms dtype: int32 - name: text dtype: string - name: continuation dtype: string splits: - name: train num_bytes: 144432442623.054 num_examples: 548014 - name: validation num_bytes: 2511524241.692 num_examples: 18622 - name: test num_bytes: 4259695588.794 num_examples: 34898 download_size: 149491764186 dataset_size: 151203662453.53998 configs: - config_name: clean data_files: - split: validation path: clean/validation-* - split: test path: clean/test-* - split: train path: data/train-* - config_name: dirty_sa data_files: - split: train path: dirty_sa/train-* - split: validation path: dirty_sa/validation-* - split: test path: dirty_sa/test-* ---

deepghs/danbooru2023_index

deepghs

--- license: mit task_categories: - image-classification - image-to-image - text-to-image language: - en - ja size_categories: - 1M<n<10M --- Tar index files for [nyanko7/danbooru2023](https://huggingface.co./datasets/nyanko7/danbooru2023). You can download images from both [nyanko7/danbooru2023](https://huggingface.co./datasets/nyanko7/danbooru2023) and [deepghs/danbooru_newest](https://huggingface.co./datasets/deepghs/danbooru_newest) with [cheesechaser](https://github.com/deepghs/cheesechaser). ```python from cheesechaser.datapool import DanbooruNewestDataPool pool = DanbooruNewestDataPool() # download danbooru original images from 7200000-7201000, to directory /data/danbooru_original pool.batch_download_to_directory( resource_ids=range(7200000, 7201000), dst_dir='/data/danbooru_original', max_workers=12, ) ```

MMMU/MMMU

MMMU

--- language: - en license: apache-2.0 size_categories: - 10K<n<100K task_categories: - question-answering - visual-question-answering - multiple-choice pretty_name: mmmu dataset_info: - config_name: Accounting features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 262599.0 num_examples: 5 - name: validation num_bytes: 1598285.0 num_examples: 30 - name: test num_bytes: 22135625.0 num_examples: 380 download_size: 37363379 dataset_size: 23996509.0 - config_name: Agriculture features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 22082656.0 num_examples: 5 - name: validation num_bytes: 119217558.0 num_examples: 30 - name: test num_bytes: 993664077.0 num_examples: 287 download_size: 1158036990 dataset_size: 1134964291.0 - config_name: Architecture_and_Engineering features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 137750.0 num_examples: 5 - name: validation num_bytes: 721378.0 num_examples: 30 - name: test num_bytes: 16054607.0 num_examples: 551 download_size: 48763955 dataset_size: 16913735.0 - config_name: Art features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 6241184.0 num_examples: 5 - name: validation num_bytes: 29934534.0 num_examples: 30 - name: test num_bytes: 237801390.0 num_examples: 231 download_size: 585798641 dataset_size: 273977108.0 - config_name: Art_Theory features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 7435106.0 num_examples: 5 - name: validation num_bytes: 33481558.0 num_examples: 30 - name: test num_bytes: 553174647.0 num_examples: 429 download_size: 930525695 dataset_size: 594091311.0 - config_name: Basic_Medical_Science features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 814310.0 num_examples: 5 - name: validation num_bytes: 4125930.0 num_examples: 30 - name: test num_bytes: 48125891.0 num_examples: 326 download_size: 84666454 dataset_size: 53066131.0 - config_name: Biology features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 574342.0 num_examples: 5 - name: validation num_bytes: 8491863.0 num_examples: 30 - name: test num_bytes: 132966151.0 num_examples: 345 download_size: 410242502 dataset_size: 142032356.0 - config_name: Chemistry features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 262397.0 num_examples: 5 - name: validation num_bytes: 1518573.0 num_examples: 30 - name: test num_bytes: 37219529.0 num_examples: 603 download_size: 108345562 dataset_size: 39000499.0 - config_name: Clinical_Medicine features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 1467945.0 num_examples: 5 - name: validation num_bytes: 10882484.0 num_examples: 30 - name: test num_bytes: 98201863.0 num_examples: 325 download_size: 160611488 dataset_size: 110552292.0 - config_name: Computer_Science features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 440523.0 num_examples: 5 - name: validation num_bytes: 2072018.0 num_examples: 30 - name: test num_bytes: 32047381.0 num_examples: 371 download_size: 55640991 dataset_size: 34559922.0 - config_name: Design features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 2259873.0 num_examples: 5 - name: validation num_bytes: 17923120.0 num_examples: 30 - name: test num_bytes: 77676331.0 num_examples: 169 download_size: 142866617 dataset_size: 97859324.0 - config_name: Diagnostics_and_Laboratory_Medicine features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 2056117.0 num_examples: 5 - name: validation num_bytes: 37106233.0 num_examples: 30 - name: test num_bytes: 157003069.0 num_examples: 162 download_size: 603957093 dataset_size: 196165419.0 - config_name: Economics features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 171434.0 num_examples: 5 - name: validation num_bytes: 1487048.0 num_examples: 30 - name: test num_bytes: 11852300.0 num_examples: 267 download_size: 20777635 dataset_size: 13510782.0 - config_name: Electronics features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 123632.0 num_examples: 5 - name: validation num_bytes: 641377.0 num_examples: 30 - name: test num_bytes: 5717686.0 num_examples: 256 download_size: 11602832 dataset_size: 6482695.0 - config_name: Energy_and_Power features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 105006.0 num_examples: 5 - name: validation num_bytes: 1641935.0 num_examples: 30 - name: test num_bytes: 14748428.0 num_examples: 432 download_size: 35246567 dataset_size: 16495369.0 - config_name: Finance features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 296124.0 num_examples: 5 - name: validation num_bytes: 1071060.0 num_examples: 30 - name: test num_bytes: 12065803.0 num_examples: 355 download_size: 29551521 dataset_size: 13432987.0 - config_name: Geography features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 1494060.0 num_examples: 5 - name: validation num_bytes: 6671316.0 num_examples: 30 - name: test num_bytes: 137218400.0 num_examples: 565 download_size: 374766631 dataset_size: 145383776.0 - config_name: History features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 1444231.0 num_examples: 5 - name: validation num_bytes: 8819857.0 num_examples: 30 - name: test num_bytes: 115228815.0 num_examples: 278 download_size: 232549641 dataset_size: 125492903.0 - config_name: Literature features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 2451201.0 num_examples: 5 - name: validation num_bytes: 14241046.0 num_examples: 30 - name: test num_bytes: 50301541.0 num_examples: 112 download_size: 132145895 dataset_size: 66993788.0 - config_name: Manage features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 449514.0 num_examples: 5 - name: validation num_bytes: 3277436.0 num_examples: 30 - name: test num_bytes: 29963963.0 num_examples: 245 download_size: 51186888 dataset_size: 33690913.0 - config_name: Marketing features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 116960.0 num_examples: 5 - name: validation num_bytes: 1472981.0 num_examples: 30 - name: test num_bytes: 7732976.0 num_examples: 181 download_size: 13146078 dataset_size: 9322917.0 - config_name: Materials features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 239632.0 num_examples: 5 - name: validation num_bytes: 2305223.0 num_examples: 30 - name: test num_bytes: 25256854.0 num_examples: 458 download_size: 105773156 dataset_size: 27801709.0 - config_name: Math features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 175839.0 num_examples: 5 - name: validation num_bytes: 1444496.0 num_examples: 30 - name: test num_bytes: 27701845.0 num_examples: 505 download_size: 174098418 dataset_size: 29322180.0 - config_name: Mechanical_Engineering features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 152542.0 num_examples: 5 - name: validation num_bytes: 874988.0 num_examples: 30 - name: test num_bytes: 15093746.0 num_examples: 429 download_size: 30450114 dataset_size: 16121276.0 - config_name: Music features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 1417615.0 num_examples: 5 - name: validation num_bytes: 9359372.0 num_examples: 30 - name: test num_bytes: 134096770.0 num_examples: 334 download_size: 174725052 dataset_size: 144873757.0 - config_name: Pharmacy features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 207924.0 num_examples: 5 - name: validation num_bytes: 1656342.0 num_examples: 30 - name: test num_bytes: 31866248.0 num_examples: 430 download_size: 62721263 dataset_size: 33730514.0 - config_name: Physics features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 233734.0 num_examples: 5 - name: validation num_bytes: 1114130.0 num_examples: 30 - name: test num_bytes: 15905705.0 num_examples: 408 download_size: 35238571 dataset_size: 17253569.0 - config_name: Psychology features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 600864.0 num_examples: 5 - name: validation num_bytes: 4403886.0 num_examples: 30 - name: test num_bytes: 53813915.0 num_examples: 305 download_size: 102466671 dataset_size: 58818665.0 - config_name: Public_Health features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 234781.0 num_examples: 5 - name: validation num_bytes: 1508761.0 num_examples: 30 - name: test num_bytes: 32150088.0 num_examples: 509 download_size: 48231609 dataset_size: 33893630.0 - config_name: Sociology features: - name: id dtype: string - name: question dtype: string - name: options dtype: string - name: explanation dtype: string - name: image_1 dtype: image - name: image_2 dtype: image - name: image_3 dtype: image - name: image_4 dtype: image - name: image_5 dtype: image - name: image_6 dtype: image - name: image_7 dtype: image - name: img_type dtype: string - name: answer dtype: string - name: topic_difficulty dtype: string - name: question_type dtype: string - name: subfield dtype: string splits: - name: dev num_bytes: 3769220.0 num_examples: 5 - name: validation num_bytes: 18455336.0 num_examples: 30 - name: test num_bytes: 144301123.0 num_examples: 252 download_size: 310313826 dataset_size: 166525679.0 configs: - config_name: Accounting data_files: - split: dev path: Accounting/dev-* - split: validation path: Accounting/validation-* - split: test path: Accounting/test-* - config_name: Agriculture data_files: - split: dev path: Agriculture/dev-* - split: validation path: Agriculture/validation-* - split: test path: Agriculture/test-* - config_name: Architecture_and_Engineering data_files: - split: dev path: Architecture_and_Engineering/dev-* - split: validation path: Architecture_and_Engineering/validation-* - split: test path: Architecture_and_Engineering/test-* - config_name: Art data_files: - split: dev path: Art/dev-* - split: validation path: Art/validation-* - split: test path: Art/test-* - config_name: Art_Theory data_files: - split: dev path: Art_Theory/dev-* - split: validation path: Art_Theory/validation-* - split: test path: Art_Theory/test-* - config_name: Basic_Medical_Science data_files: - split: dev path: Basic_Medical_Science/dev-* - split: validation path: Basic_Medical_Science/validation-* - split: test path: Basic_Medical_Science/test-* - config_name: Biology data_files: - split: dev path: Biology/dev-* - split: validation path: Biology/validation-* - split: test path: Biology/test-* - config_name: Chemistry data_files: - split: dev path: Chemistry/dev-* - split: validation path: Chemistry/validation-* - split: test path: Chemistry/test-* - config_name: Clinical_Medicine data_files: - split: dev path: Clinical_Medicine/dev-* - split: validation path: Clinical_Medicine/validation-* - split: test path: Clinical_Medicine/test-* - config_name: Computer_Science data_files: - split: dev path: Computer_Science/dev-* - split: validation path: Computer_Science/validation-* - split: test path: Computer_Science/test-* - config_name: Design data_files: - split: dev path: Design/dev-* - split: validation path: Design/validation-* - split: test path: Design/test-* - config_name: Diagnostics_and_Laboratory_Medicine data_files: - split: dev path: Diagnostics_and_Laboratory_Medicine/dev-* - split: validation path: Diagnostics_and_Laboratory_Medicine/validation-* - split: test path: Diagnostics_and_Laboratory_Medicine/test-* - config_name: Economics data_files: - split: dev path: Economics/dev-* - split: validation path: Economics/validation-* - split: test path: Economics/test-* - config_name: Electronics data_files: - split: dev path: Electronics/dev-* - split: validation path: Electronics/validation-* - split: test path: Electronics/test-* - config_name: Energy_and_Power data_files: - split: dev path: Energy_and_Power/dev-* - split: validation path: Energy_and_Power/validation-* - split: test path: Energy_and_Power/test-* - config_name: Finance data_files: - split: dev path: Finance/dev-* - split: validation path: Finance/validation-* - split: test path: Finance/test-* - config_name: Geography data_files: - split: dev path: Geography/dev-* - split: validation path: Geography/validation-* - split: test path: Geography/test-* - config_name: History data_files: - split: dev path: History/dev-* - split: validation path: History/validation-* - split: test path: History/test-* - config_name: Literature data_files: - split: dev path: Literature/dev-* - split: validation path: Literature/validation-* - split: test path: Literature/test-* - config_name: Manage data_files: - split: dev path: Manage/dev-* - split: validation path: Manage/validation-* - split: test path: Manage/test-* - config_name: Marketing data_files: - split: dev path: Marketing/dev-* - split: validation path: Marketing/validation-* - split: test path: Marketing/test-* - config_name: Materials data_files: - split: dev path: Materials/dev-* - split: validation path: Materials/validation-* - split: test path: Materials/test-* - config_name: Math data_files: - split: dev path: Math/dev-* - split: validation path: Math/validation-* - split: test path: Math/test-* - config_name: Mechanical_Engineering data_files: - split: dev path: Mechanical_Engineering/dev-* - split: validation path: Mechanical_Engineering/validation-* - split: test path: Mechanical_Engineering/test-* - config_name: Music data_files: - split: dev path: Music/dev-* - split: validation path: Music/validation-* - split: test path: Music/test-* - config_name: Pharmacy data_files: - split: dev path: Pharmacy/dev-* - split: validation path: Pharmacy/validation-* - split: test path: Pharmacy/test-* - config_name: Physics data_files: - split: dev path: Physics/dev-* - split: validation path: Physics/validation-* - split: test path: Physics/test-* - config_name: Psychology data_files: - split: dev path: Psychology/dev-* - split: validation path: Psychology/validation-* - split: test path: Psychology/test-* - config_name: Public_Health data_files: - split: dev path: Public_Health/dev-* - split: validation path: Public_Health/validation-* - split: test path: Public_Health/test-* - config_name: Sociology data_files: - split: dev path: Sociology/dev-* - split: validation path: Sociology/validation-* - split: test path: Sociology/test-* tags: - biology - medical - finance - chemistry - music - art - art_theory - design - music - business - accounting - economics - finance - manage - marketing - health - medicine - basic_medical_science - clinical - pharmacy - public_health - humanities - social_science - history - literature - sociology - psychology - science - biology - chemistry - geography - math - physics - engineering - agriculture - architecture - computer_science - electronics - energy_and_power - materials - mechanical_engineering --- # MMMU (A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI) [**🌐 Homepage**](https://mmmu-benchmark.github.io/) | [**🏆 Leaderboard**](https://mmmu-benchmark.github.io/#leaderboard) | [**🤗 Dataset**](https://huggingface.co./datasets/MMMU/MMMU/) | [**🤗 Paper**](https://huggingface.co./papers/2311.16502) | [**📖 arXiv**](https://arxiv.org/abs/2311.16502) | [**GitHub**](https://github.com/MMMU-Benchmark/MMMU) ## 🔔News - **🛠️[2024-05-30]: Fixed duplicate option issues in Materials dataset items (validation_Materials_25; test_Materials_17, 242) and content error in validation_Materials_25.** - **🛠️[2024-04-30]: Fixed missing "-" or "^" signs in Math dataset items (dev_Math_2, validation_Math_11, 12, 16; test_Math_8, 23, 43, 113, 164, 223, 236, 287, 329, 402, 498) and corrected option errors in validation_Math_2. If you encounter any issues with the dataset, please contact us promptly!** - **🚀[2024-01-31]: We added Human Expert performance on the [Leaderboard](https://mmmu-benchmark.github.io/#leaderboard)!🌟** - **🔥[2023-12-04]: Our evaluation server for test set is now availble on [EvalAI](https://eval.ai/web/challenges/challenge-page/2179/overview). We welcome all submissions and look forward to your participation! 😆** ## Dataset Details ### Dataset Description We introduce MMMU: a new benchmark designed to evaluate multimodal models on massive multi-discipline tasks demanding college-level subject knowledge and deliberate reasoning. MMMU includes **11.5K meticulously collected multimodal questions** from college exams, quizzes, and textbooks, covering six core disciplines: Art & Design, Business, Science, Health & Medicine, Humanities & Social Science, and Tech & Engineering. These questions span **30 subjects** and **183 subfields**, comprising **30 highly heterogeneous image types**, such as charts, diagrams, maps, tables, music sheets, and chemical structures. We believe MMMU will stimulate the community to build next-generation multimodal foundation models towards expert artificial general intelligence (AGI). 🎯 **We have released a full set comprising 150 development samples and 900 validation samples. We have released 10,500 test questions without their answers.** The development set is used for few-shot/in-context learning, and the validation set is used for debugging models, selecting hyperparameters, or quick evaluations. The answers and explanations for the test set questions are withheld. You can submit your model's predictions for the **test set** on **[EvalAI](https://eval.ai/web/challenges/challenge-page/2179/overview)**.  ### Dataset Creation MMMU was created to challenge multimodal models with tasks that demand college-level subject knowledge and deliberate reasoning, pushing the boundaries of what these models can achieve in terms of expert-level perception and reasoning. The data for the MMMU dataset was manually collected by a team of college students from various disciplines, using online sources, textbooks, and lecture materials. - **Content:** The dataset contains 11.5K college-level problems across six broad disciplines (Art & Design, Business, Science, Health & Medicine, Humanities & Social Science, Tech & Engineering) and 30 college subjects. - **Image Types:** The dataset includes 30 highly heterogeneous image types, such as charts, diagrams, maps, tables, music sheets, and chemical structures, interleaved with text.  ## 🏆 Mini-Leaderboard We show a mini-leaderboard here and please find more information in our paper or [**homepage**](https://mmmu-benchmark.github.io/). | Model | Val (900) | Test (10.5K) | |--------------------------------|:---------:|:------------:| | Expert (Best) | 88.6 | - | | Expert (Medium) | 82.6 | - | | Expert (Worst) | 76.2 | - | | GPT-4o* | **69.1** | - | | Gemini 1.5 Pro* | 62.2 | - | | InternVL2-Pro* | 62.0 | **55.7** | | Gemini 1.0 Ultra* | 59.4 | - | | Claude 3 Opus* | 59.4 | - | | GPT-4V(ision) (Playground) | 56.8 | **55.7** | | Reka Core* | 56.3 | - | | Gemini 1.5 Flash* | 56.1 | - | | SenseChat-Vision-0423-Preview* | 54.6 | 50.3 | | Reka Flash* | 53.3 | - | | Claude 3 Sonnet* | 53.1 | - | | HPT Pro* | 52.0 | - | | VILA1.5* | 51.9 | 46.9 | | Qwen-VL-MAX* | 51.4 | 46.8 | | InternVL-Chat-V1.2* | 51.6 | 46.2 | | Skywork-VL* | 51.4 | 46.2 | | LLaVA-1.6-34B* | 51.1 | 44.7 | | Claude 3 Haiku* | 50.2 | - | | Adept Fuyu-Heavy* | 48.3 | - | | Gemini 1.0 Pro* | 47.9 | - | | Marco-VL-Plus* | 46.2 | 44.3 | | Yi-VL-34B* | 45.9 | 41.6 | | Qwen-VL-PLUS* | 45.2 | 40.8 | | HPT Air* | 44.0 | - | | Reka Edge* | 42.8 | - | | Marco-VL* | 41.2 | 40.4 | | OmniLMM-12B* | 41.1 | 40.4 | | Bunny-8B* | 43.3 | 39.0 | | Bunny-4B* | 41.4 | 38.4 | | Weitu-VL-1.0-15B* | - | 38.4 | | InternLM-XComposer2-VL* | 43.0 | 38.2 | | Yi-VL-6B* | 39.1 | 37.8 | | InfiMM-Zephyr-7B* | 39.4 | 35.5 | | InternVL-Chat-V1.1* | 39.1 | 35.3 | | Math-LLaVA-13B* | 38.3 | 34.6 | | SVIT* | 38.0 | 34.1 | | MiniCPM-V* | 37.2 | 34.1 | | MiniCPM-V-2* | 37.1 | - | | Emu2-Chat* | 36.3 | 34.1 | | BLIP-2 FLAN-T5-XXL | 35.4 | 34.0 | | InstructBLIP-T5-XXL | 35.7 | 33.8 | | LLaVA-1.5-13B | 36.4 | 33.6 | | Bunny-3B* | 38.2 | 33.0 | | Qwen-VL-7B-Chat | 35.9 | 32.9 | | SPHINX* | 32.9 | 32.9 | | mPLUG-OWL2* | 32.7 | 32.1 | | BLIP-2 FLAN-T5-XL | 34.4 | 31.0 | | InstructBLIP-T5-XL | 32.9 | 30.6 | | Gemini Nano2* | 32.6 | - | | CogVLM | 32.1 | 30.1 | | Otter | 32.2 | 29.1 | | LLaMA-Adapter2-7B | 29.8 | 27.7 | | MiniGPT4-Vicuna-13B | 26.8 | 27.6 | | Adept Fuyu-8B | 27.9 | 27.4 | | Kosmos2 | 24.4 | 26.6 | | OpenFlamingo2-9B | 28.7 | 26.3 | | Frequent Choice | 22.1 | 23.9 | | Random Choice | 26.8 | 25.8 | *: results provided by the authors. ## Limitations Despite its comprehensive nature, MMMU, like any benchmark, is not without limitations. The manual curation process, albeit thorough, may carry biases. And the focus on college-level subjects might not fully be a sufficient test for Expert AGI. However, we believe it should be necessary for an Expert AGI to achieve strong performance on MMMU to demonstrate their broad and deep subject knowledge as well as expert-level understanding and reasoning capabilities. In future work, we plan to incorporate human evaluations into MMMU. This will provide a more grounded comparison between model capabilities and expert performance, shedding light on the proximity of current AI systems to achieving Expert AGI. ## Disclaimers The guidelines for the annotators emphasized strict compliance with copyright and licensing rules from the initial data source, specifically avoiding materials from websites that forbid copying and redistribution. Should you encounter any data samples potentially breaching the copyright or licensing regulations of any site, we encourage you to notify us. Upon verification, such samples will be promptly removed. ## Contact - Xiang Yue: [email protected] - Yu Su: [email protected] - Wenhu Chen: [email protected] ## Citation **BibTeX:** ```bibtex @inproceedings{yue2023mmmu, title={MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI}, author={Xiang Yue and Yuansheng Ni and Kai Zhang and Tianyu Zheng and Ruoqi Liu and Ge Zhang and Samuel Stevens and Dongfu Jiang and Weiming Ren and Yuxuan Sun and Cong Wei and Botao Yu and Ruibin Yuan and Renliang Sun and Ming Yin and Boyuan Zheng and Zhenzhu Yang and Yibo Liu and Wenhao Huang and Huan Sun and Yu Su and Wenhu Chen}, booktitle={Proceedings of CVPR}, year={2024}, } ```

japanese-asr/whisper_transcriptions.reazon_speech_all.wer_10.0.vectorized

japanese-asr

--- dataset_info: - config_name: subset_0 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44407083236 num_examples: 28889 download_size: 6430216790 dataset_size: 44407083236 - config_name: subset_1 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44089216600 num_examples: 28682 download_size: 6385763048 dataset_size: 44089216600 - config_name: subset_10 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43927652252 num_examples: 28577 download_size: 6336100250 dataset_size: 43927652252 - config_name: subset_100 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44365586824 num_examples: 28862 download_size: 6435201244 dataset_size: 44365586824 - config_name: subset_101 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44324247868 num_examples: 28835 download_size: 6431762006 dataset_size: 44324247868 - config_name: subset_102 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43821526656 num_examples: 28508 download_size: 6367882564 dataset_size: 43821526656 - config_name: subset_103 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44084293668 num_examples: 28679 download_size: 6363475471 dataset_size: 44084293668 - config_name: subset_104 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44042930672 num_examples: 28652 download_size: 6381242681 dataset_size: 44042930672 - config_name: subset_106 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43912140892 num_examples: 28567 download_size: 6343450605 dataset_size: 43912140892 - config_name: subset_107 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43931998624 num_examples: 28580 download_size: 6358400755 dataset_size: 43931998624 - config_name: subset_108 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44042913000 num_examples: 28652 download_size: 6405970862 dataset_size: 44042913000 - config_name: subset_109 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44642253680 num_examples: 29042 download_size: 6437990632 dataset_size: 44642253680 - config_name: subset_11 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44256762756 num_examples: 28791 download_size: 6393712860 dataset_size: 44256762756 - config_name: subset_110 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43889022688 num_examples: 28552 download_size: 6360561092 dataset_size: 43889022688 - config_name: subset_111 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44129144280 num_examples: 28708 download_size: 6408022759 dataset_size: 44129144280 - config_name: subset_112 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44041454396 num_examples: 28651 download_size: 6391629995 dataset_size: 44041454396 - config_name: subset_113 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44218161920 num_examples: 28766 download_size: 6397865173 dataset_size: 44218161920 - config_name: subset_114 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44311827300 num_examples: 28827 download_size: 6392228352 dataset_size: 44311827300 - config_name: subset_115 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43438751460 num_examples: 28259 download_size: 6261293593 dataset_size: 43438751460 - config_name: subset_116 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43895154544 num_examples: 28556 download_size: 6347517025 dataset_size: 43895154544 - config_name: subset_117 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43969041880 num_examples: 28604 download_size: 6375498562 dataset_size: 43969041880 - config_name: subset_118 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44027316104 num_examples: 28642 download_size: 6354466340 dataset_size: 44027316104 - config_name: subset_119 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44289059560 num_examples: 28812 download_size: 6416432647 dataset_size: 44289059560 - config_name: subset_12 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44293612564 num_examples: 28815 download_size: 6433586401 dataset_size: 44293612564 - config_name: subset_120 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44530056588 num_examples: 28969 download_size: 6437978882 dataset_size: 44530056588 - config_name: subset_121 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 3074160 num_examples: 2 download_size: 556271 dataset_size: 3074160 - config_name: subset_122 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44136739628 num_examples: 28713 download_size: 6404302139 dataset_size: 44136739628 - config_name: subset_123 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44096634284 num_examples: 28687 download_size: 6389251368 dataset_size: 44096634284 - config_name: subset_124 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44001467124 num_examples: 28625 download_size: 6385493649 dataset_size: 44001467124 - config_name: subset_125 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44128863696 num_examples: 28708 download_size: 6364505444 dataset_size: 44128863696 - config_name: subset_126 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44382486420 num_examples: 28873 download_size: 6441197752 dataset_size: 44382486420 - config_name: subset_127 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44006092176 num_examples: 28628 download_size: 6361537304 dataset_size: 44006092176 - config_name: subset_128 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43759809728 num_examples: 28468 download_size: 6336544958 dataset_size: 43759809728 - config_name: subset_129 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44024331328 num_examples: 28640 download_size: 6359644430 dataset_size: 44024331328 - config_name: subset_13 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44357930276 num_examples: 28857 download_size: 6420201483 dataset_size: 44357930276 - config_name: subset_130 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44192010836 num_examples: 28749 download_size: 6422867143 dataset_size: 44192010836 - config_name: subset_131 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44099663532 num_examples: 28689 download_size: 6371664563 dataset_size: 44099663532 - config_name: subset_132 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44095360096 num_examples: 28686 download_size: 6383911332 dataset_size: 44095360096 - config_name: subset_133 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43730827940 num_examples: 28449 download_size: 6313519416 dataset_size: 43730827940 - config_name: subset_134 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44007518388 num_examples: 28629 download_size: 6389179458 dataset_size: 44007518388 - config_name: subset_135 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43707840616 num_examples: 28434 download_size: 6317643688 dataset_size: 43707840616 - config_name: subset_136 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44033774672 num_examples: 28646 download_size: 6373240832 dataset_size: 44033774672 - config_name: subset_137 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 3074344 num_examples: 2 download_size: 557594 dataset_size: 3074344 - config_name: subset_138 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43841655788 num_examples: 28521 download_size: 6370669259 dataset_size: 43841655788 - config_name: subset_139 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43793963000 num_examples: 28490 download_size: 6351019624 dataset_size: 43793963000 - config_name: subset_14 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44413389620 num_examples: 28893 download_size: 6406524573 dataset_size: 44413389620 - config_name: subset_140 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43978329680 num_examples: 28610 download_size: 6341082690 dataset_size: 43978329680 - config_name: subset_141 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44030464856 num_examples: 28644 download_size: 6383471765 dataset_size: 44030464856 - config_name: subset_142 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43793910464 num_examples: 28490 download_size: 6348275681 dataset_size: 43793910464 - config_name: subset_143 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44448732656 num_examples: 28916 download_size: 6450504968 dataset_size: 44448732656 - config_name: subset_144 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43686238792 num_examples: 28420 download_size: 6334779676 dataset_size: 43686238792 - config_name: subset_145 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44141228568 num_examples: 28716 download_size: 6363170999 dataset_size: 44141228568 - config_name: subset_146 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43800179728 num_examples: 28494 download_size: 6358878988 dataset_size: 43800179728 - config_name: subset_147 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44294909712 num_examples: 28816 download_size: 6412779644 dataset_size: 44294909712 - config_name: subset_148 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43886264664 num_examples: 28550 download_size: 6377384251 dataset_size: 43886264664 - config_name: subset_149 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44030547976 num_examples: 28644 download_size: 6383895865 dataset_size: 44030547976 - config_name: subset_15 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44014998072 num_examples: 28634 download_size: 6373512015 dataset_size: 44014998072 - config_name: subset_150 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43899790252 num_examples: 28559 download_size: 6346605145 dataset_size: 43899790252 - config_name: subset_151 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43913769264 num_examples: 28568 download_size: 6389364151 dataset_size: 43913769264 - config_name: subset_152 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44493036076 num_examples: 28945 download_size: 6441659355 dataset_size: 44493036076 - config_name: subset_153 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 4611236 num_examples: 3 download_size: 671590 dataset_size: 4611236 - config_name: subset_154 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43904573672 num_examples: 28562 download_size: 6353845259 dataset_size: 43904573672 - config_name: subset_155 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44414946296 num_examples: 28894 download_size: 6399004665 dataset_size: 44414946296 - config_name: subset_156 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43787907000 num_examples: 28486 download_size: 6361131234 dataset_size: 43787907000 - config_name: subset_157 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43838676140 num_examples: 28519 download_size: 6377464479 dataset_size: 43838676140 - config_name: subset_158 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43920002016 num_examples: 28572 download_size: 6365562506 dataset_size: 43920002016 - config_name: subset_159 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44079873808 num_examples: 28676 download_size: 6385289404 dataset_size: 44079873808 - config_name: subset_16 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44135044504 num_examples: 28712 download_size: 6367990267 dataset_size: 44135044504 - config_name: subset_160 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44261370184 num_examples: 28794 download_size: 6435970157 dataset_size: 44261370184 - config_name: subset_161 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44096758836 num_examples: 28687 download_size: 6411447660 dataset_size: 44096758836 - config_name: subset_162 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43901416400 num_examples: 28560 download_size: 6394315107 dataset_size: 43901416400 - config_name: subset_163 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44322671320 num_examples: 28834 download_size: 6421064852 dataset_size: 44322671320 - config_name: subset_164 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43978582144 num_examples: 28610 download_size: 6362813793 dataset_size: 43978582144 - config_name: subset_165 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44018298496 num_examples: 28636 download_size: 6376999923 dataset_size: 44018298496 - config_name: subset_166 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44251922632 num_examples: 28788 download_size: 6419837278 dataset_size: 44251922632 - config_name: subset_167 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44104251680 num_examples: 28692 download_size: 6408687778 dataset_size: 44104251680 - config_name: subset_168 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43790884880 num_examples: 28488 download_size: 6371985468 dataset_size: 43790884880 - config_name: subset_169 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 6147752 num_examples: 4 download_size: 527132 dataset_size: 6147752 - config_name: subset_17 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44179626060 num_examples: 28741 download_size: 6410813569 dataset_size: 44179626060 - config_name: subset_170 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44238190244 num_examples: 28779 download_size: 6425085842 dataset_size: 44238190244 - config_name: subset_171 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43855344672 num_examples: 28530 download_size: 6351374612 dataset_size: 43855344672 - config_name: subset_172 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43744717352 num_examples: 28458 download_size: 6322671761 dataset_size: 43744717352 - config_name: subset_173 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43993634824 num_examples: 28620 download_size: 6324282823 dataset_size: 43993634824 - config_name: subset_174 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44381122280 num_examples: 28872 download_size: 6448679863 dataset_size: 44381122280 - config_name: subset_175 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44391843308 num_examples: 28879 download_size: 6448621992 dataset_size: 44391843308 - config_name: subset_176 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44158323572 num_examples: 28727 download_size: 6408233260 dataset_size: 44158323572 - config_name: subset_177 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44033693424 num_examples: 28646 download_size: 6415876282 dataset_size: 44033693424 - config_name: subset_178 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 42685714068 num_examples: 27769 download_size: 6200737024 dataset_size: 42685714068 - config_name: subset_179 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 42648659092 num_examples: 27745 download_size: 6171525632 dataset_size: 42648659092 - config_name: subset_18 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43836770424 num_examples: 28518 download_size: 6326151956 dataset_size: 43836770424 - config_name: subset_180 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 42551809752 num_examples: 27682 download_size: 6168382243 dataset_size: 42551809752 - config_name: subset_181 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 42434879408 num_examples: 27606 download_size: 6123055947 dataset_size: 42434879408 - config_name: subset_182 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 42408752772 num_examples: 27589 download_size: 6152174336 dataset_size: 42408752772 - config_name: subset_183 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 42966849416 num_examples: 27952 download_size: 6194170724 dataset_size: 42966849416 - config_name: subset_184 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 42540803548 num_examples: 27675 download_size: 6179994976 dataset_size: 42540803548 - config_name: subset_185 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 4610940 num_examples: 3 download_size: 510678 dataset_size: 4610940 - config_name: subset_186 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 42273847412 num_examples: 27501 download_size: 6135274899 dataset_size: 42273847412 - config_name: subset_187 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 42547162108 num_examples: 27679 download_size: 6140828239 dataset_size: 42547162108 - config_name: subset_188 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 42513408276 num_examples: 27657 download_size: 6141115163 dataset_size: 42513408276 - config_name: subset_189 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 42247299832 num_examples: 27484 download_size: 6114021654 dataset_size: 42247299832 - config_name: subset_19 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43870784704 num_examples: 28540 download_size: 6361457035 dataset_size: 43870784704 - config_name: subset_190 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 42559396388 num_examples: 27687 download_size: 6144933007 dataset_size: 42559396388 - config_name: subset_191 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 42727058440 num_examples: 27796 download_size: 6159613829 dataset_size: 42727058440 - config_name: subset_192 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 42465891192 num_examples: 27626 download_size: 6137572406 dataset_size: 42465891192 - config_name: subset_193 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 42687083448 num_examples: 27770 download_size: 6156875941 dataset_size: 42687083448 - config_name: subset_194 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43269701988 num_examples: 28149 download_size: 6279255539 dataset_size: 43269701988 - config_name: subset_195 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43100379428 num_examples: 28039 download_size: 6244533477 dataset_size: 43100379428 - config_name: subset_196 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43182000120 num_examples: 28092 download_size: 6246268592 dataset_size: 43182000120 - config_name: subset_197 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 42488819788 num_examples: 27641 download_size: 6178356059 dataset_size: 42488819788 - config_name: subset_198 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43151315408 num_examples: 28072 download_size: 6236447434 dataset_size: 43151315408 - config_name: subset_199 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43020760060 num_examples: 27987 download_size: 6246173797 dataset_size: 43020760060 - config_name: subset_2 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43987672944 num_examples: 28616 download_size: 6372442472 dataset_size: 43987672944 - config_name: subset_20 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44078517716 num_examples: 28675 download_size: 6385824155 dataset_size: 44078517716 - config_name: subset_200 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43286671192 num_examples: 28160 download_size: 6280144588 dataset_size: 43286671192 - config_name: subset_201 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 3073928 num_examples: 2 download_size: 379680 dataset_size: 3073928 - config_name: subset_202 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 42862469264 num_examples: 27884 download_size: 6203880452 dataset_size: 42862469264 - config_name: subset_203 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 42893042416 num_examples: 27904 download_size: 6220561824 dataset_size: 42893042416 - config_name: subset_204 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43033034108 num_examples: 27995 download_size: 6252547275 dataset_size: 43033034108 - config_name: subset_205 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43129968864 num_examples: 28058 download_size: 6242739407 dataset_size: 43129968864 - config_name: subset_206 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43139090800 num_examples: 28064 download_size: 6235515866 dataset_size: 43139090800 - config_name: subset_207 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43152809356 num_examples: 28073 download_size: 6283290397 dataset_size: 43152809356 - config_name: subset_208 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 42942228856 num_examples: 27936 download_size: 6201443185 dataset_size: 42942228856 - config_name: subset_209 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 42900706308 num_examples: 27909 download_size: 6209468923 dataset_size: 42900706308 - config_name: subset_21 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 3073968 num_examples: 2 download_size: 340735 dataset_size: 3073968 - config_name: subset_210 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43097615852 num_examples: 28037 download_size: 6250699366 dataset_size: 43097615852 - config_name: subset_211 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43345131936 num_examples: 28198 download_size: 6290127680 dataset_size: 43345131936 - config_name: subset_212 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43369720992 num_examples: 28214 download_size: 6322218871 dataset_size: 43369720992 - config_name: subset_213 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43273017772 num_examples: 28151 download_size: 6290984482 dataset_size: 43273017772 - config_name: subset_214 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43339017792 num_examples: 28194 download_size: 6291790140 dataset_size: 43339017792 - config_name: subset_215 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43148309288 num_examples: 28070 download_size: 6274426221 dataset_size: 43148309288 - config_name: subset_216 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43554083872 num_examples: 28334 download_size: 6316086000 dataset_size: 43554083872 - config_name: subset_217 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 6148384 num_examples: 4 download_size: 787021 dataset_size: 6148384 - config_name: subset_218 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43388064416 num_examples: 28226 download_size: 6284993121 dataset_size: 43388064416 - config_name: subset_219 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43400316424 num_examples: 28234 download_size: 6293046087 dataset_size: 43400316424 - config_name: subset_22 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44242802888 num_examples: 28782 download_size: 6406171080 dataset_size: 44242802888 - config_name: subset_220 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43246544032 num_examples: 28134 download_size: 6276081988 dataset_size: 43246544032 - config_name: subset_221 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43091341748 num_examples: 28033 download_size: 6246844874 dataset_size: 43091341748 - config_name: subset_222 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43282260444 num_examples: 28157 download_size: 6273569814 dataset_size: 43282260444 - config_name: subset_223 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43218862392 num_examples: 28116 download_size: 6267480974 dataset_size: 43218862392 - config_name: subset_53 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43020592356 num_examples: 27987 download_size: 6237193214 dataset_size: 43020592356 - config_name: subset_105 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43217581324 num_examples: 28115 download_size: 6241162732 dataset_size: 43217581324 - config_name: subset_23 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44087547940 num_examples: 28681 download_size: 6378825677 dataset_size: 44087547940 - config_name: subset_24 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44250388180 num_examples: 28787 download_size: 6399288392 dataset_size: 44250388180 - config_name: subset_25 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44682379040 num_examples: 29068 download_size: 6472664846 dataset_size: 44682379040 - config_name: subset_26 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43988774372 num_examples: 28617 download_size: 6351536356 dataset_size: 43988774372 - config_name: subset_27 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44124322548 num_examples: 28705 download_size: 6384396942 dataset_size: 44124322548 - config_name: subset_28 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44274970012 num_examples: 28803 download_size: 6405118297 dataset_size: 44274970012 - config_name: subset_29 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44127365308 num_examples: 28707 download_size: 6394981446 dataset_size: 44127365308 - config_name: subset_3 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44010774700 num_examples: 28631 download_size: 6385129614 dataset_size: 44010774700 - config_name: subset_30 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43959947880 num_examples: 28598 download_size: 6351099073 dataset_size: 43959947880 - config_name: subset_31 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43939721468 num_examples: 28585 download_size: 6349698481 dataset_size: 43939721468 - config_name: subset_32 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43701336432 num_examples: 28430 download_size: 6317498365 dataset_size: 43701336432 - config_name: subset_33 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43912133780 num_examples: 28567 download_size: 6347741424 dataset_size: 43912133780 - config_name: subset_34 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43924879268 num_examples: 28575 download_size: 6385061613 dataset_size: 43924879268 - config_name: subset_35 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44198269620 num_examples: 28753 download_size: 6417152268 dataset_size: 44198269620 - config_name: subset_36 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43958143980 num_examples: 28597 download_size: 6371530333 dataset_size: 43958143980 - config_name: subset_37 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 1536892 num_examples: 1 download_size: 145043 dataset_size: 1536892 - config_name: subset_38 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43907738296 num_examples: 28564 download_size: 6370745101 dataset_size: 43907738296 - config_name: subset_39 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43783169540 num_examples: 28483 download_size: 6360636678 dataset_size: 43783169540 - config_name: subset_4 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44035016260 num_examples: 28647 download_size: 6356360790 dataset_size: 44035016260 - config_name: subset_40 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43876677072 num_examples: 28544 download_size: 6363545223 dataset_size: 43876677072 - config_name: subset_41 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44039928304 num_examples: 28650 download_size: 6400395515 dataset_size: 44039928304 - config_name: subset_42 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43550868688 num_examples: 28332 download_size: 6288205442 dataset_size: 43550868688 - config_name: subset_43 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43772245200 num_examples: 28476 download_size: 6312411517 dataset_size: 43772245200 - config_name: subset_44 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44043101784 num_examples: 28652 download_size: 6367757278 dataset_size: 44043101784 - config_name: subset_45 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43839830568 num_examples: 28520 download_size: 6302918743 dataset_size: 43839830568 - config_name: subset_46 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44418011720 num_examples: 28896 download_size: 6420581627 dataset_size: 44418011720 - config_name: subset_47 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44239609176 num_examples: 28780 download_size: 6409168799 dataset_size: 44239609176 - config_name: subset_48 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43441872132 num_examples: 28261 download_size: 6279351848 dataset_size: 43441872132 - config_name: subset_49 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43803148032 num_examples: 28496 download_size: 6348966745 dataset_size: 43803148032 - config_name: subset_5 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 3073752 num_examples: 2 download_size: 269532 dataset_size: 3073752 - config_name: subset_50 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43892315672 num_examples: 28554 download_size: 6352365538 dataset_size: 43892315672 - config_name: subset_51 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44030510104 num_examples: 28644 download_size: 6357746911 dataset_size: 44030510104 - config_name: subset_52 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44004611300 num_examples: 28627 download_size: 6395577673 dataset_size: 44004611300 - config_name: subset_54 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43924607164 num_examples: 28575 download_size: 6394467746 dataset_size: 43924607164 - config_name: subset_55 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43766336872 num_examples: 28472 download_size: 6382887005 dataset_size: 43766336872 - config_name: subset_56 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43924612260 num_examples: 28575 download_size: 6358387007 dataset_size: 43924612260 - config_name: subset_57 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44125903328 num_examples: 28706 download_size: 6429743630 dataset_size: 44125903328 - config_name: subset_58 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44061228392 num_examples: 28664 download_size: 6403276947 dataset_size: 44061228392 - config_name: subset_59 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44005810400 num_examples: 28628 download_size: 6399433408 dataset_size: 44005810400 - config_name: subset_6 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44378012200 num_examples: 28870 download_size: 6424397700 dataset_size: 44378012200 - config_name: subset_60 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44225890868 num_examples: 28771 download_size: 6419332378 dataset_size: 44225890868 - config_name: subset_61 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43650843212 num_examples: 28397 download_size: 6326376655 dataset_size: 43650843212 - config_name: subset_62 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43827520656 num_examples: 28512 download_size: 6330616794 dataset_size: 43827520656 - config_name: subset_63 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44172218520 num_examples: 28736 download_size: 6409944210 dataset_size: 44172218520 - config_name: subset_64 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43918314476 num_examples: 28571 download_size: 6359242235 dataset_size: 43918314476 - config_name: subset_65 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43906125500 num_examples: 28563 download_size: 6375398199 dataset_size: 43906125500 - config_name: subset_66 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44075027964 num_examples: 28673 download_size: 6398349127 dataset_size: 44075027964 - config_name: subset_67 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43609456344 num_examples: 28370 download_size: 6307862180 dataset_size: 43609456344 - config_name: subset_68 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43666361020 num_examples: 28407 download_size: 6328770887 dataset_size: 43666361020 - config_name: subset_69 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44025932180 num_examples: 28641 download_size: 6372276607 dataset_size: 44025932180 - config_name: subset_7 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44059710956 num_examples: 28663 download_size: 6383885034 dataset_size: 44059710956 - config_name: subset_70 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43781700552 num_examples: 28482 download_size: 6318262101 dataset_size: 43781700552 - config_name: subset_71 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44175190528 num_examples: 28738 download_size: 6420404767 dataset_size: 44175190528 - config_name: subset_72 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44059988804 num_examples: 28663 download_size: 6403791239 dataset_size: 44059988804 - config_name: subset_73 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44242682800 num_examples: 28782 download_size: 6393278746 dataset_size: 44242682800 - config_name: subset_74 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43664734768 num_examples: 28406 download_size: 6293869164 dataset_size: 43664734768 - config_name: subset_75 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43830625696 num_examples: 28514 download_size: 6347303356 dataset_size: 43830625696 - config_name: subset_76 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43924502708 num_examples: 28575 download_size: 6368149688 dataset_size: 43924502708 - config_name: subset_77 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43754158544 num_examples: 28464 download_size: 6347205297 dataset_size: 43754158544 - config_name: subset_78 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43781508304 num_examples: 28482 download_size: 6362656422 dataset_size: 43781508304 - config_name: subset_79 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43978478208 num_examples: 28610 download_size: 6398609121 dataset_size: 43978478208 - config_name: subset_8 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44007563004 num_examples: 28629 download_size: 6358760125 dataset_size: 44007563004 - config_name: subset_80 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43807663524 num_examples: 28499 download_size: 6383713010 dataset_size: 43807663524 - config_name: subset_81 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43958216180 num_examples: 28597 download_size: 6360362244 dataset_size: 43958216180 - config_name: subset_82 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44018307032 num_examples: 28636 download_size: 6388770182 dataset_size: 44018307032 - config_name: subset_83 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43431184792 num_examples: 28254 download_size: 6273446746 dataset_size: 43431184792 - config_name: subset_84 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 4611316 num_examples: 3 download_size: 813473 dataset_size: 4611316 - config_name: subset_85 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43873788512 num_examples: 28542 download_size: 6358732185 dataset_size: 43873788512 - config_name: subset_86 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43505081840 num_examples: 28302 download_size: 6336792534 dataset_size: 43505081840 - config_name: subset_87 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44099477124 num_examples: 28689 download_size: 6376905811 dataset_size: 44099477124 - config_name: subset_88 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43800091792 num_examples: 28494 download_size: 6331140342 dataset_size: 43800091792 - config_name: subset_89 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44185886628 num_examples: 28745 download_size: 6399823294 dataset_size: 44185886628 - config_name: subset_9 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43959761872 num_examples: 28598 download_size: 6369092508 dataset_size: 43959761872 - config_name: subset_90 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43943002092 num_examples: 28587 download_size: 6384008687 dataset_size: 43943002092 - config_name: subset_91 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43709159980 num_examples: 28435 download_size: 6348468066 dataset_size: 43709159980 - config_name: subset_92 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43803194856 num_examples: 28496 download_size: 6384519799 dataset_size: 43803194856 - config_name: subset_93 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43806228672 num_examples: 28498 download_size: 6353242379 dataset_size: 43806228672 - config_name: subset_94 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43918235972 num_examples: 28571 download_size: 6359165774 dataset_size: 43918235972 - config_name: subset_95 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44013722788 num_examples: 28633 download_size: 6372836215 dataset_size: 44013722788 - config_name: subset_96 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43912328076 num_examples: 28567 download_size: 6360540190 dataset_size: 43912328076 - config_name: subset_97 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43784551296 num_examples: 28484 download_size: 6341270112 dataset_size: 43784551296 - config_name: subset_98 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 44568669984 num_examples: 28994 download_size: 6461359260 dataset_size: 44568669984 - config_name: subset_99 features: - name: transcription sequence: int64 - name: transcription/en_gpt3.5 sequence: int64 - name: whisper_transcription sequence: int64 - name: whisper_transcription/en_gpt3.5 sequence: int64 - name: input_features sequence: sequence: float32 splits: - name: train num_bytes: 43989120876 num_examples: 28617 download_size: 6385093647 dataset_size: 43989120876 configs: - config_name: subset_0 data_files: - split: train path: subset_0/train-* - config_name: subset_1 data_files: - split: train path: subset_1/train-* - config_name: subset_10 data_files: - split: train path: subset_10/train-* - config_name: subset_100 data_files: - split: train path: subset_100/train-* - config_name: subset_101 data_files: - split: train path: subset_101/train-* - config_name: subset_102 data_files: - split: train path: subset_102/train-* - config_name: subset_103 data_files: - split: train path: subset_103/train-* - config_name: subset_104 data_files: - split: train path: subset_104/train-* - config_name: subset_106 data_files: - split: train path: subset_106/train-* - config_name: subset_107 data_files: - split: train path: subset_107/train-* - config_name: subset_108 data_files: - split: train path: subset_108/train-* - config_name: subset_109 data_files: - split: train path: subset_109/train-* - config_name: subset_11 data_files: - split: train path: subset_11/train-* - config_name: subset_110 data_files: - split: train path: subset_110/train-* - config_name: subset_111 data_files: - split: train path: subset_111/train-* - config_name: subset_112 data_files: - split: train path: subset_112/train-* - config_name: subset_113 data_files: - split: train path: subset_113/train-* - config_name: subset_114 data_files: - split: train path: subset_114/train-* - config_name: subset_115 data_files: - split: train path: subset_115/train-* - config_name: subset_116 data_files: - split: train path: subset_116/train-* - config_name: subset_117 data_files: - split: train path: subset_117/train-* - config_name: subset_118 data_files: - split: train path: subset_118/train-* - config_name: subset_119 data_files: - split: train path: subset_119/train-* - config_name: subset_12 data_files: - split: train path: subset_12/train-* - config_name: subset_120 data_files: - split: train path: subset_120/train-* - config_name: subset_121 data_files: - split: train path: subset_121/train-* - config_name: subset_122 data_files: - split: train path: subset_122/train-* - config_name: subset_123 data_files: - split: train path: subset_123/train-* - config_name: subset_124 data_files: - split: train path: subset_124/train-* - config_name: subset_125 data_files: - split: train path: subset_125/train-* - config_name: subset_126 data_files: - split: train path: subset_126/train-* - config_name: subset_127 data_files: - split: train path: subset_127/train-* - config_name: subset_128 data_files: - split: train path: subset_128/train-* - config_name: subset_129 data_files: - split: train path: subset_129/train-* - config_name: subset_13 data_files: - split: train path: subset_13/train-* - config_name: subset_130 data_files: - split: train path: subset_130/train-* - config_name: subset_131 data_files: - split: train path: subset_131/train-* - config_name: subset_132 data_files: - split: train path: subset_132/train-* - config_name: subset_133 data_files: - split: train path: subset_133/train-* - config_name: subset_134 data_files: - split: train path: subset_134/train-* - config_name: subset_135 data_files: - split: train path: subset_135/train-* - config_name: subset_136 data_files: - split: train path: subset_136/train-* - config_name: subset_137 data_files: - split: train path: subset_137/train-* - config_name: subset_138 data_files: - split: train path: subset_138/train-* - config_name: subset_139 data_files: - split: train path: subset_139/train-* - config_name: subset_14 data_files: - split: train path: subset_14/train-* - config_name: subset_140 data_files: - split: train path: subset_140/train-* - config_name: subset_141 data_files: - split: train path: subset_141/train-* - config_name: subset_142 data_files: - split: train path: subset_142/train-* - config_name: subset_143 data_files: - split: train path: subset_143/train-* - config_name: subset_144 data_files: - split: train path: subset_144/train-* - config_name: subset_145 data_files: - split: train path: subset_145/train-* - config_name: subset_146 data_files: - split: train path: subset_146/train-* - config_name: subset_147 data_files: - split: train path: subset_147/train-* - config_name: subset_148 data_files: - split: train path: subset_148/train-* - config_name: subset_149 data_files: - split: train path: subset_149/train-* - config_name: subset_15 data_files: - split: train path: subset_15/train-* - config_name: subset_150 data_files: - split: train path: subset_150/train-* - config_name: subset_151 data_files: - split: train path: subset_151/train-* - config_name: subset_152 data_files: - split: train path: subset_152/train-* - config_name: subset_153 data_files: - split: train path: subset_153/train-* - config_name: subset_154 data_files: - split: train path: subset_154/train-* - config_name: subset_155 data_files: - split: train path: subset_155/train-* - config_name: subset_156 data_files: - split: train path: subset_156/train-* - config_name: subset_157 data_files: - split: train path: subset_157/train-* - config_name: subset_158 data_files: - split: train path: subset_158/train-* - config_name: subset_159 data_files: - split: train path: subset_159/train-* - config_name: subset_16 data_files: - split: train path: subset_16/train-* - config_name: subset_160 data_files: - split: train path: subset_160/train-* - config_name: subset_161 data_files: - split: train path: subset_161000/train-* - config_name: subset_162 data_files: - split: train path: subset_162/train-* - config_name: subset_163 data_files: - split: train path: subset_163/train-* - config_name: subset_164 data_files: - split: train path: subset_164/train-* - config_name: subset_165 data_files: - split: train path: subset_165/train-* - config_name: subset_166 data_files: - split: train path: subset_166/train-* - config_name: subset_167 data_files: - split: train path: subset_167/train-* - config_name: subset_168 data_files: - split: train path: subset_168/train-* - config_name: subset_169 data_files: - split: train path: subset_169/train-* - config_name: subset_17 data_files: - split: train path: subset_17/train-* - config_name: subset_170 data_files: - split: train path: subset_170/train-* - config_name: subset_171 data_files: - split: train path: subset_171/train-* - config_name: subset_172 data_files: - split: train path: subset_172/train-* - config_name: subset_173 data_files: - split: train path: subset_173/train-* - config_name: subset_174 data_files: - split: train path: subset_174/train-* - config_name: subset_175 data_files: - split: train path: subset_175/train-* - config_name: subset_176 data_files: - split: train path: subset_176/train-* - config_name: subset_177 data_files: - split: train path: subset_177/train-* - config_name: subset_178 data_files: - split: train path: subset_178/train-* - config_name: subset_179 data_files: - split: train path: subset_179/train-* - config_name: subset_18 data_files: - split: train path: subset_18/train-* - config_name: subset_180 data_files: - split: train path: subset_180/train-* - config_name: subset_181 data_files: - split: train path: subset_181/train-* - config_name: subset_182 data_files: - split: train path: subset_182/train-* - config_name: subset_183 data_files: - split: train path: subset_183/train-* - config_name: subset_184 data_files: - split: train path: subset_184/train-* - config_name: subset_185 data_files: - split: train path: subset_185/train-* - config_name: subset_186 data_files: - split: train path: subset_186/train-* - config_name: subset_187 data_files: - split: train path: subset_187/train-* - config_name: subset_188 data_files: - split: train path: subset_188/train-* - config_name: subset_189 data_files: - split: train path: subset_189/train-* - config_name: subset_19 data_files: - split: train path: subset_19000/train-* - config_name: subset_190 data_files: - split: train path: subset_190/train-* - config_name: subset_191 data_files: - split: train path: subset_191/train-* - config_name: subset_192 data_files: - split: train path: subset_192/train-* - config_name: subset_193 data_files: - split: train path: subset_193/train-* - config_name: subset_194 data_files: - split: train path: subset_194/train-* - config_name: subset_195 data_files: - split: train path: subset_195/train-* - config_name: subset_196 data_files: - split: train path: subset_196/train-* - config_name: subset_197 data_files: - split: train path: subset_197/train-* - config_name: subset_198 data_files: - split: train path: subset_198/train-* - config_name: subset_199 data_files: - split: train path: subset_199/train-* - config_name: subset_2 data_files: - split: train path: subset_2/train-* - config_name: subset_20 data_files: - split: train path: subset_20/train-* - config_name: subset_200 data_files: - split: train path: subset_200/train-* - config_name: subset_201 data_files: - split: train path: subset_201/train-* - config_name: subset_202 data_files: - split: train path: subset_202/train-* - config_name: subset_203 data_files: - split: train path: subset_203/train-* - config_name: subset_204 data_files: - split: train path: subset_204/train-* - config_name: subset_205 data_files: - split: train path: subset_205000/train-* - config_name: subset_206 data_files: - split: train path: subset_206000/train-* - config_name: subset_207 data_files: - split: train path: subset_207/train-* - config_name: subset_208 data_files: - split: train path: subset_208000/train-* - config_name: subset_209 data_files: - split: train path: subset_209/train-* - config_name: subset_21 data_files: - split: train path: subset_21/train-* - config_name: subset_210 data_files: - split: train path: subset_210/train-* - config_name: subset_211 data_files: - split: train path: subset_211/train-* - config_name: subset_212 data_files: - split: train path: subset_212/train-* - config_name: subset_213 data_files: - split: train path: subset_213/train-* - config_name: subset_214 data_files: - split: train path: subset_214000/train-* - config_name: subset_215 data_files: - split: train path: subset_215/train-* - config_name: subset_216 data_files: - split: train path: subset_216/train-* - config_name: subset_217 data_files: - split: train path: subset_217/train-* - config_name: subset_218 data_files: - split: train path: subset_218/train-* - config_name: subset_219 data_files: - split: train path: subset_219/train-* - config_name: subset_22 data_files: - split: train path: subset_22/train-* - config_name: subset_220 data_files: - split: train path: subset_220/train-* - config_name: subset_221 data_files: - split: train path: subset_221/train-* - config_name: subset_222 data_files: - split: train path: subset_222/train-* - config_name: subset_223 data_files: - split: train path: subset_223/train-* - config_name: subset_53 data_files: - split: train path: subset_224/train-* - config_name: subset_105 data_files: - split: train path: subset_225/train-* - config_name: subset_23 data_files: - split: train path: subset_23/train-* - config_name: subset_24 data_files: - split: train path: subset_24/train-* - config_name: subset_25 data_files: - split: train path: subset_25/train-* - config_name: subset_26 data_files: - split: train path: subset_26/train-* - config_name: subset_27 data_files: - split: train path: subset_27/train-* - config_name: subset_28 data_files: - split: train path: subset_28/train-* - config_name: subset_29 data_files: - split: train path: subset_29/train-* - config_name: subset_3 data_files: - split: train path: subset_3/train-* - config_name: subset_30 data_files: - split: train path: subset_30/train-* - config_name: subset_31 data_files: - split: train path: subset_31/train-* - config_name: subset_32 data_files: - split: train path: subset_32/train-* - config_name: subset_33 data_files: - split: train path: subset_33/train-* - config_name: subset_34 data_files: - split: train path: subset_34/train-* - config_name: subset_35 data_files: - split: train path: subset_35/train-* - config_name: subset_36 data_files: - split: train path: subset_36/train-* - config_name: subset_37 data_files: - split: train path: subset_37/train-* - config_name: subset_38 data_files: - split: train path: subset_38/train-* - config_name: subset_39 data_files: - split: train path: subset_39/train-* - config_name: subset_4 data_files: - split: train path: subset_4/train-* - config_name: subset_40 data_files: - split: train path: subset_40/train-* - config_name: subset_41 data_files: - split: train path: subset_41/train-* - config_name: subset_42 data_files: - split: train path: subset_42/train-* - config_name: subset_43 data_files: - split: train path: subset_43/train-* - config_name: subset_44 data_files: - split: train path: subset_44/train-* - config_name: subset_45 data_files: - split: train path: subset_45/train-* - config_name: subset_46 data_files: - split: train path: subset_46/train-* - config_name: subset_47 data_files: - split: train path: subset_47/train-* - config_name: subset_48 data_files: - split: train path: subset_48/train-* - config_name: subset_49 data_files: - split: train path: subset_49/train-* - config_name: subset_5 data_files: - split: train path: subset_5/train-* - config_name: subset_50 data_files: - split: train path: subset_50/train-* - config_name: subset_51 data_files: - split: train path: subset_51/train-* - config_name: subset_52 data_files: - split: train path: subset_52/train-* - config_name: subset_54 data_files: - split: train path: subset_54/train-* - config_name: subset_55 data_files: - split: train path: subset_55/train-* - config_name: subset_56 data_files: - split: train path: subset_56/train-* - config_name: subset_57 data_files: - split: train path: subset_57/train-* - config_name: subset_58 data_files: - split: train path: subset_58/train-* - config_name: subset_59 data_files: - split: train path: subset_59/train-* - config_name: subset_6 data_files: - split: train path: subset_6/train-* - config_name: subset_60 data_files: - split: train path: subset_60/train-* - config_name: subset_61 data_files: - split: train path: subset_61/train-* - config_name: subset_62 data_files: - split: train path: subset_62/train-* - config_name: subset_63 data_files: - split: train path: subset_63/train-* - config_name: subset_64 data_files: - split: train path: subset_64/train-* - config_name: subset_65 data_files: - split: train path: subset_65/train-* - config_name: subset_66 data_files: - split: train path: subset_66/train-* - config_name: subset_67 data_files: - split: train path: subset_67/train-* - config_name: subset_68 data_files: - split: train path: subset_68/train-* - config_name: subset_69 data_files: - split: train path: subset_69/train-* - config_name: subset_7 data_files: - split: train path: subset_7/train-* - config_name: subset_70 data_files: - split: train path: subset_70/train-* - config_name: subset_71 data_files: - split: train path: subset_71/train-* - config_name: subset_72 data_files: - split: train path: subset_72/train-* - config_name: subset_73 data_files: - split: train path: subset_73/train-* - config_name: subset_74 data_files: - split: train path: subset_74/train-* - config_name: subset_75 data_files: - split: train path: subset_75/train-* - config_name: subset_76 data_files: - split: train path: subset_76/train-* - config_name: subset_77 data_files: - split: train path: subset_77/train-* - config_name: subset_78 data_files: - split: train path: subset_78/train-* - config_name: subset_79 data_files: - split: train path: subset_79/train-* - config_name: subset_8 data_files: - split: train path: subset_8/train-* - config_name: subset_80 data_files: - split: train path: subset_80/train-* - config_name: subset_81 data_files: - split: train path: subset_81/train-* - config_name: subset_82 data_files: - split: train path: subset_82/train-* - config_name: subset_83 data_files: - split: train path: subset_83/train-* - config_name: subset_84 data_files: - split: train path: subset_84/train-* - config_name: subset_85 data_files: - split: train path: subset_85/train-* - config_name: subset_86 data_files: - split: train path: subset_86/train-* - config_name: subset_87 data_files: - split: train path: subset_87/train-* - config_name: subset_88 data_files: - split: train path: subset_88/train-* - config_name: subset_89 data_files: - split: train path: subset_89/train-* - config_name: subset_9 data_files: - split: train path: subset_9/train-* - config_name: subset_90 data_files: - split: train path: subset_90/train-* - config_name: subset_91 data_files: - split: train path: subset_91/train-* - config_name: subset_92 data_files: - split: train path: subset_92/train-* - config_name: subset_93 data_files: - split: train path: subset_93/train-* - config_name: subset_94 data_files: - split: train path: subset_94/train-* - config_name: subset_95 data_files: - split: train path: subset_95/train-* - config_name: subset_96 data_files: - split: train path: subset_96/train-* - config_name: subset_97 data_files: - split: train path: subset_97/train-* - config_name: subset_98 data_files: - split: train path: subset_98/train-* - config_name: subset_99 data_files: - split: train path: subset_99/train-* ---

applied-ai-018/pretraining_v1-omega_books

applied-ai-018

--- dataset_info: config_name: CC-MAIN-2013-20 features: - name: text dtype: string - name: id dtype: string - name: dump dtype: string - name: url dtype: string - name: file_path dtype: string - name: language dtype: string - name: language_score dtype: float64 - name: token_count dtype: int64 - name: score dtype: float64 - name: int_score dtype: int64 splits: - name: train num_bytes: 235476901236 num_examples: 51901183 download_size: 138494178972 dataset_size: 235476901236 configs: - config_name: CC-MAIN-2013-20 data_files: - split: train path: CC-MAIN-2013-20/train-* ---