Initial commit

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.spm filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,761 @@
+---
+library_name: transformers
+language:
+- br
+- cy
+- de
+- en
+- es
+- fr
+- ga
+- gd
+- gv
+- kw
+- pt
+
+tags:
+- translation
+- opus-mt-tc-bible
+
+license: apache-2.0
+model-index:
+- name: opus-mt-tc-bible-big-cel-deu_eng_fra_por_spa
+  results:
+  - task:
+      name: Translation cym-deu
+      type: translation
+      args: cym-deu
+    dataset:
+      name: flores200-devtest
+      type: flores200-devtest
+      args: cym-deu
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 22.6
+       - name: chr-F
+         type: chrf
+         value: 0.52745
+  - task:
+      name: Translation cym-eng
+      type: translation
+      args: cym-eng
+    dataset:
+      name: flores200-devtest
+      type: flores200-devtest
+      args: cym-eng
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 55.5
+       - name: chr-F
+         type: chrf
+         value: 0.75234
+  - task:
+      name: Translation cym-fra
+      type: translation
+      args: cym-fra
+    dataset:
+      name: flores200-devtest
+      type: flores200-devtest
+      args: cym-fra
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 31.4
+       - name: chr-F
+         type: chrf
+         value: 0.58339
+  - task:
+      name: Translation cym-por
+      type: translation
+      args: cym-por
+    dataset:
+      name: flores200-devtest
+      type: flores200-devtest
+      args: cym-por
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 18.3
+       - name: chr-F
+         type: chrf
+         value: 0.47566
+  - task:
+      name: Translation cym-spa
+      type: translation
+      args: cym-spa
+    dataset:
+      name: flores200-devtest
+      type: flores200-devtest
+      args: cym-spa
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 19.9
+       - name: chr-F
+         type: chrf
+         value: 0.48834
+  - task:
+      name: Translation gla-deu
+      type: translation
+      args: gla-deu
+    dataset:
+      name: flores200-devtest
+      type: flores200-devtest
+      args: gla-deu
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 13.0
+       - name: chr-F
+         type: chrf
+         value: 0.41962
+  - task:
+      name: Translation gla-eng
+      type: translation
+      args: gla-eng
+    dataset:
+      name: flores200-devtest
+      type: flores200-devtest
+      args: gla-eng
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 26.4
+       - name: chr-F
+         type: chrf
+         value: 0.53374
+  - task:
+      name: Translation gla-fra
+      type: translation
+      args: gla-fra
+    dataset:
+      name: flores200-devtest
+      type: flores200-devtest
+      args: gla-fra
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 16.6
+       - name: chr-F
+         type: chrf
+         value: 0.44916
+  - task:
+      name: Translation gla-por
+      type: translation
+      args: gla-por
+    dataset:
+      name: flores200-devtest
+      type: flores200-devtest
+      args: gla-por
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 12.1
+       - name: chr-F
+         type: chrf
+         value: 0.39790
+  - task:
+      name: Translation gla-spa
+      type: translation
+      args: gla-spa
+    dataset:
+      name: flores200-devtest
+      type: flores200-devtest
+      args: gla-spa
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 12.9
+       - name: chr-F
+         type: chrf
+         value: 0.40375
+  - task:
+      name: Translation gle-deu
+      type: translation
+      args: gle-deu
+    dataset:
+      name: flores200-devtest
+      type: flores200-devtest
+      args: gle-deu
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 19.2
+       - name: chr-F
+         type: chrf
+         value: 0.49962
+  - task:
+      name: Translation gle-eng
+      type: translation
+      args: gle-eng
+    dataset:
+      name: flores200-devtest
+      type: flores200-devtest
+      args: gle-eng
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 38.9
+       - name: chr-F
+         type: chrf
+         value: 0.64866
+  - task:
+      name: Translation gle-fra
+      type: translation
+      args: gle-fra
+    dataset:
+      name: flores200-devtest
+      type: flores200-devtest
+      args: gle-fra
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 26.7
+       - name: chr-F
+         type: chrf
+         value: 0.54564
+  - task:
+      name: Translation gle-por
+      type: translation
+      args: gle-por
+    dataset:
+      name: flores200-devtest
+      type: flores200-devtest
+      args: gle-por
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 14.9
+       - name: chr-F
+         type: chrf
+         value: 0.44768
+  - task:
+      name: Translation gle-spa
+      type: translation
+      args: gle-spa
+    dataset:
+      name: flores200-devtest
+      type: flores200-devtest
+      args: gle-spa
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 18.7
+       - name: chr-F
+         type: chrf
+         value: 0.47347
+  - task:
+      name: Translation cym-deu
+      type: translation
+      args: cym-deu
+    dataset:
+      name: flores101-devtest
+      type: flores_101
+      args: cym deu devtest
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 22.4
+       - name: chr-F
+         type: chrf
+         value: 0.52672
+  - task:
+      name: Translation cym-fra
+      type: translation
+      args: cym-fra
+    dataset:
+      name: flores101-devtest
+      type: flores_101
+      args: cym fra devtest
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 31.3
+       - name: chr-F
+         type: chrf
+         value: 0.58299
+  - task:
+      name: Translation cym-por
+      type: translation
+      args: cym-por
+    dataset:
+      name: flores101-devtest
+      type: flores_101
+      args: cym por devtest
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 18.4
+       - name: chr-F
+         type: chrf
+         value: 0.47733
+  - task:
+      name: Translation gle-eng
+      type: translation
+      args: gle-eng
+    dataset:
+      name: flores101-devtest
+      type: flores_101
+      args: gle eng devtest
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 38.6
+       - name: chr-F
+         type: chrf
+         value: 0.64773
+  - task:
+      name: Translation gle-fra
+      type: translation
+      args: gle-fra
+    dataset:
+      name: flores101-devtest
+      type: flores_101
+      args: gle fra devtest
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 26.5
+       - name: chr-F
+         type: chrf
+         value: 0.54559
+  - task:
+      name: Translation cym-deu
+      type: translation
+      args: cym-deu
+    dataset:
+      name: ntrex128
+      type: ntrex128
+      args: cym-deu
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 16.3
+       - name: chr-F
+         type: chrf
+         value: 0.46627
+  - task:
+      name: Translation cym-eng
+      type: translation
+      args: cym-eng
+    dataset:
+      name: ntrex128
+      type: ntrex128
+      args: cym-eng
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 40.0
+       - name: chr-F
+         type: chrf
+         value: 0.65343
+  - task:
+      name: Translation cym-fra
+      type: translation
+      args: cym-fra
+    dataset:
+      name: ntrex128
+      type: ntrex128
+      args: cym-fra
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 23.8
+       - name: chr-F
+         type: chrf
+         value: 0.51183
+  - task:
+      name: Translation cym-por
+      type: translation
+      args: cym-por
+    dataset:
+      name: ntrex128
+      type: ntrex128
+      args: cym-por
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 14.4
+       - name: chr-F
+         type: chrf
+         value: 0.42857
+  - task:
+      name: Translation cym-spa
+      type: translation
+      args: cym-spa
+    dataset:
+      name: ntrex128
+      type: ntrex128
+      args: cym-spa
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 25.0
+       - name: chr-F
+         type: chrf
+         value: 0.51542
+  - task:
+      name: Translation gle-deu
+      type: translation
+      args: gle-deu
+    dataset:
+      name: ntrex128
+      type: ntrex128
+      args: gle-deu
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 15.5
+       - name: chr-F
+         type: chrf
+         value: 0.46495
+  - task:
+      name: Translation gle-eng
+      type: translation
+      args: gle-eng
+    dataset:
+      name: ntrex128
+      type: ntrex128
+      args: gle-eng
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 33.5
+       - name: chr-F
+         type: chrf
+         value: 0.60913
+  - task:
+      name: Translation gle-fra
+      type: translation
+      args: gle-fra
+    dataset:
+      name: ntrex128
+      type: ntrex128
+      args: gle-fra
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 20.7
+       - name: chr-F
+         type: chrf
+         value: 0.49513
+  - task:
+      name: Translation gle-por
+      type: translation
+      args: gle-por
+    dataset:
+      name: ntrex128
+      type: ntrex128
+      args: gle-por
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 13.2
+       - name: chr-F
+         type: chrf
+         value: 0.41767
+  - task:
+      name: Translation gle-spa
+      type: translation
+      args: gle-spa
+    dataset:
+      name: ntrex128
+      type: ntrex128
+      args: gle-spa
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 23.6
+       - name: chr-F
+         type: chrf
+         value: 0.50755
+  - task:
+      name: Translation bre-eng
+      type: translation
+      args: bre-eng
+    dataset:
+      name: tatoeba-test-v2021-08-07
+      type: tatoeba_mt
+      args: bre-eng
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 35.0
+       - name: chr-F
+         type: chrf
+         value: 0.53473
+  - task:
+      name: Translation bre-fra
+      type: translation
+      args: bre-fra
+    dataset:
+      name: tatoeba-test-v2021-08-07
+      type: tatoeba_mt
+      args: bre-fra
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 28.3
+       - name: chr-F
+         type: chrf
+         value: 0.49013
+  - task:
+      name: Translation cym-eng
+      type: translation
+      args: cym-eng
+    dataset:
+      name: tatoeba-test-v2021-08-07
+      type: tatoeba_mt
+      args: cym-eng
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 52.4
+       - name: chr-F
+         type: chrf
+         value: 0.68892
+  - task:
+      name: Translation gla-eng
+      type: translation
+      args: gla-eng
+    dataset:
+      name: tatoeba-test-v2021-08-07
+      type: tatoeba_mt
+      args: gla-eng
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 23.2
+       - name: chr-F
+         type: chrf
+         value: 0.39607
+  - task:
+      name: Translation gla-spa
+      type: translation
+      args: gla-spa
+    dataset:
+      name: tatoeba-test-v2021-08-07
+      type: tatoeba_mt
+      args: gla-spa
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 26.1
+       - name: chr-F
+         type: chrf
+         value: 0.51208
+  - task:
+      name: Translation gle-eng
+      type: translation
+      args: gle-eng
+    dataset:
+      name: tatoeba-test-v2021-08-07
+      type: tatoeba_mt
+      args: gle-eng
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 50.7
+       - name: chr-F
+         type: chrf
+         value: 0.64268
+  - task:
+      name: Translation multi-multi
+      type: translation
+      args: multi-multi
+    dataset:
+      name: tatoeba-test-v2020-07-28-v2023-09-26
+      type: tatoeba_mt
+      args: multi-multi
+    metrics:
+       - name: BLEU
+         type: bleu
+         value: 24.9
+       - name: chr-F
+         type: chrf
+         value: 0.42670
+---
+# opus-mt-tc-bible-big-cel-deu_eng_fra_por_spa
+
+## Table of Contents
+- [Model Details](#model-details)
+- [Uses](#uses)
+- [Risks, Limitations and Biases](#risks-limitations-and-biases)
+- [How to Get Started With the Model](#how-to-get-started-with-the-model)
+- [Training](#training)
+- [Evaluation](#evaluation)
+- [Citation Information](#citation-information)
+- [Acknowledgements](#acknowledgements)
+
+## Model Details
+
+Neural machine translation model for translating from Celtic languages (cel) to unknown (deu+eng+fra+por+spa).
+
+This model is part of the [OPUS-MT project](https://github.com/Helsinki-NLP/Opus-MT), an effort to make neural machine translation models widely available and accessible for many languages in the world. All models are originally trained using the amazing framework of [Marian NMT](https://marian-nmt.github.io/), an efficient NMT implementation written in pure C++. The models have been converted to pyTorch using the transformers library by huggingface. Training data is taken from [OPUS](https://opus.nlpl.eu/) and training pipelines use the procedures of [OPUS-MT-train](https://github.com/Helsinki-NLP/Opus-MT-train).
+**Model Description:**
+- **Developed by:** Language Technology Research Group at the University of Helsinki
+- **Model Type:** Translation (transformer-big)
+- **Release**: 2024-05-30
+- **License:** Apache-2.0
+- **Language(s):**  
+  - Source Language(s): bre cor cym gla gle glv
+  - Target Language(s): deu eng fra por spa
+  - Valid Target Language Labels: >>deu<< >>eng<< >>fra<< >>por<< >>spa<< >>xxx<<
+- **Original Model**: [opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-30.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/cel-deu+eng+fra+por+spa/opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-30.zip)
+- **Resources for more information:**
+  -  [OPUS-MT dashboard](https://opus.nlpl.eu/dashboard/index.php?pkg=opusmt&test=all&scoreslang=all&chart=standard&model=Tatoeba-MT-models/cel-deu%2Beng%2Bfra%2Bpor%2Bspa/opusTCv20230926max50%2Bbt%2Bjhubc_transformer-big_2024-05-30)
+  - [OPUS-MT-train GitHub Repo](https://github.com/Helsinki-NLP/OPUS-MT-train)
+  - [More information about MarianNMT models in the transformers library](https://huggingface.co/docs/transformers/model_doc/marian)
+  - [Tatoeba Translation Challenge](https://github.com/Helsinki-NLP/Tatoeba-Challenge/)
+  - [HPLT bilingual data v1 (as part of the Tatoeba Translation Challenge dataset)](https://hplt-project.org/datasets/v1)
+  - [A massively parallel Bible corpus](https://aclanthology.org/L14-1215/)
+
+This is a multilingual translation model with multiple target languages. A sentence initial language token is required in the form of `>>id<<` (id = valid target language ID), e.g. `>>deu<<`
+
+## Uses
+
+This model can be used for translation and text-to-text generation.
+
+## Risks, Limitations and Biases
+
+**CONTENT WARNING: Readers should be aware that the model is trained on various public data sets that may contain content that is disturbing, offensive, and can propagate historical and current stereotypes.**
+
+Significant research has explored bias and fairness issues with language models (see, e.g., [Sheng et al. (2021)](https://aclanthology.org/2021.acl-long.330.pdf) and [Bender et al. (2021)](https://dl.acm.org/doi/pdf/10.1145/3442188.3445922)).
+
+## How to Get Started With the Model
+
+A short example code:
+
+```python
+from transformers import MarianMTModel, MarianTokenizer
+
+src_text = [
+    ">>deu<< Replace this with text in an accepted source language.",
+    ">>spa<< This is the second sentence."
+]
+
+model_name = "pytorch-models/opus-mt-tc-bible-big-cel-deu_eng_fra_por_spa"
+tokenizer = MarianTokenizer.from_pretrained(model_name)
+model = MarianMTModel.from_pretrained(model_name)
+translated = model.generate(**tokenizer(src_text, return_tensors="pt", padding=True))
+
+for t in translated:
+    print( tokenizer.decode(t, skip_special_tokens=True) )
+```
+
+You can also use OPUS-MT models with the transformers pipelines, for example:
+
+```python
+from transformers import pipeline
+pipe = pipeline("translation", model="Helsinki-NLP/opus-mt-tc-bible-big-cel-deu_eng_fra_por_spa")
+print(pipe(">>deu<< Replace this with text in an accepted source language."))
+```
+
+## Training
+
+- **Data**: opusTCv20230926max50+bt+jhubc ([source](https://github.com/Helsinki-NLP/Tatoeba-Challenge))
+- **Pre-processing**: SentencePiece (spm32k,spm32k)
+- **Model Type:**  transformer-big
+- **Original MarianNMT Model**: [opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-30.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/cel-deu+eng+fra+por+spa/opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-30.zip)
+- **Training Scripts**: [GitHub Repo](https://github.com/Helsinki-NLP/OPUS-MT-train)
+
+## Evaluation
+
+* [Model scores at the OPUS-MT dashboard](https://opus.nlpl.eu/dashboard/index.php?pkg=opusmt&test=all&scoreslang=all&chart=standard&model=Tatoeba-MT-models/cel-deu%2Beng%2Bfra%2Bpor%2Bspa/opusTCv20230926max50%2Bbt%2Bjhubc_transformer-big_2024-05-30)
+* test set translations: [opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-29.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/cel-deu+eng+fra+por+spa/opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-29.test.txt)
+* test set scores: [opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-29.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/cel-deu+eng+fra+por+spa/opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-29.eval.txt)
+* benchmark results: [benchmark_results.txt](benchmark_results.txt)
+* benchmark output: [benchmark_translations.zip](benchmark_translations.zip)
+
+| langpair | testset | chr-F | BLEU  | #sent | #words |
+|----------|---------|-------|-------|-------|--------|
+| bre-eng | tatoeba-test-v2021-08-07 | 0.53473 | 35.0 | 383 | 2065 |
+| bre-fra | tatoeba-test-v2021-08-07 | 0.49013 | 28.3 | 2494 | 13324 |
+| cym-eng | tatoeba-test-v2021-08-07 | 0.68892 | 52.4 | 818 | 5563 |
+| gla-eng | tatoeba-test-v2021-08-07 | 0.39607 | 23.2 | 955 | 6611 |
+| gla-spa | tatoeba-test-v2021-08-07 | 0.51208 | 26.1 | 289 | 1608 |
+| gle-eng | tatoeba-test-v2021-08-07 | 0.64268 | 50.7 | 1913 | 11190 |
+| cym-deu | flores101-devtest | 0.52672 | 22.4 | 1012 | 25094 |
+| cym-fra | flores101-devtest | 0.58299 | 31.3 | 1012 | 28343 |
+| cym-por | flores101-devtest | 0.47733 | 18.4 | 1012 | 26519 |
+| gle-eng | flores101-devtest | 0.64773 | 38.6 | 1012 | 24721 |
+| gle-fra | flores101-devtest | 0.54559 | 26.5 | 1012 | 28343 |
+| cym-deu | flores200-devtest | 0.52745 | 22.6 | 1012 | 25094 |
+| cym-eng | flores200-devtest | 0.75234 | 55.5 | 1012 | 24721 |
+| cym-fra | flores200-devtest | 0.58339 | 31.4 | 1012 | 28343 |
+| cym-por | flores200-devtest | 0.47566 | 18.3 | 1012 | 26519 |
+| cym-spa | flores200-devtest | 0.48834 | 19.9 | 1012 | 29199 |
+| gla-deu | flores200-devtest | 0.41962 | 13.0 | 1012 | 25094 |
+| gla-eng | flores200-devtest | 0.53374 | 26.4 | 1012 | 24721 |
+| gla-fra | flores200-devtest | 0.44916 | 16.6 | 1012 | 28343 |
+| gla-spa | flores200-devtest | 0.40375 | 12.9 | 1012 | 29199 |
+| gle-deu | flores200-devtest | 0.49962 | 19.2 | 1012 | 25094 |
+| gle-eng | flores200-devtest | 0.64866 | 38.9 | 1012 | 24721 |
+| gle-fra | flores200-devtest | 0.54564 | 26.7 | 1012 | 28343 |
+| gle-por | flores200-devtest | 0.44768 | 14.9 | 1012 | 26519 |
+| gle-spa | flores200-devtest | 0.47347 | 18.7 | 1012 | 29199 |
+| cym-deu | ntrex128 | 0.46627 | 16.3 | 1997 | 48761 |
+| cym-eng | ntrex128 | 0.65343 | 40.0 | 1997 | 47673 |
+| cym-fra | ntrex128 | 0.51183 | 23.8 | 1997 | 53481 |
+| cym-por | ntrex128 | 0.42857 | 14.4 | 1997 | 51631 |
+| cym-spa | ntrex128 | 0.51542 | 25.0 | 1997 | 54107 |
+| gle-deu | ntrex128 | 0.46495 | 15.5 | 1997 | 48761 |
+| gle-eng | ntrex128 | 0.60913 | 33.5 | 1997 | 47673 |
+| gle-fra | ntrex128 | 0.49513 | 20.7 | 1997 | 53481 |
+| gle-por | ntrex128 | 0.41767 | 13.2 | 1997 | 51631 |
+| gle-spa | ntrex128 | 0.50755 | 23.6 | 1997 | 54107 |
+
+## Citation Information
+
+* Publications: [Democratizing neural machine translation with OPUS-MT](https://doi.org/10.1007/s10579-023-09704-w) and [OPUS-MT – Building open translation services for the World](https://aclanthology.org/2020.eamt-1.61/) and [The Tatoeba Translation Challenge – Realistic Data Sets for Low Resource and Multilingual MT](https://aclanthology.org/2020.wmt-1.139/) (Please, cite if you use this model.)
+
+```bibtex
+@article{tiedemann2023democratizing,
+  title={Democratizing neural machine translation with {OPUS-MT}},
+  author={Tiedemann, J{\"o}rg and Aulamo, Mikko and Bakshandaeva, Daria and Boggia, Michele and Gr{\"o}nroos, Stig-Arne and Nieminen, Tommi and Raganato, Alessandro and Scherrer, Yves and Vazquez, Raul and Virpioja, Sami},
+  journal={Language Resources and Evaluation},
+  number={58},
+  pages={713--755},
+  year={2023},
+  publisher={Springer Nature},
+  issn={1574-0218},
+  doi={10.1007/s10579-023-09704-w}
+}
+
+@inproceedings{tiedemann-thottingal-2020-opus,
+    title = "{OPUS}-{MT} {--} Building open translation services for the World",
+    author = {Tiedemann, J{\"o}rg  and Thottingal, Santhosh},
+    booktitle = "Proceedings of the 22nd Annual Conference of the European Association for Machine Translation",
+    month = nov,
+    year = "2020",
+    address = "Lisboa, Portugal",
+    publisher = "European Association for Machine Translation",
+    url = "https://aclanthology.org/2020.eamt-1.61",
+    pages = "479--480",
+}
+
+@inproceedings{tiedemann-2020-tatoeba,
+    title = "The Tatoeba Translation Challenge {--} Realistic Data Sets for Low Resource and Multilingual {MT}",
+    author = {Tiedemann, J{\"o}rg},
+    booktitle = "Proceedings of the Fifth Conference on Machine Translation",
+    month = nov,
+    year = "2020",
+    address = "Online",
+    publisher = "Association for Computational Linguistics",
+    url = "https://aclanthology.org/2020.wmt-1.139",
+    pages = "1174--1182",
+}
+```
+
+## Acknowledgements
+
+The work is supported by the [HPLT project](https://hplt-project.org/), funded by the European Union’s Horizon Europe research and innovation programme under grant agreement No 101070350. We are also grateful for the generous computational resources and IT infrastructure provided by [CSC -- IT Center for Science](https://www.csc.fi/), Finland, and the [EuroHPC supercomputer LUMI](https://www.lumi-supercomputer.eu/).
+
+## Model conversion info
+
+* transformers version: 4.45.1
+* OPUS-MT git hash: a0ea3b3
+* port time: Mon Oct  7 23:09:42 EEST 2024
+* port machine: LM0-400-22516.local

benchmark_results.txt

@@ -0,0 +1,52 @@
+multi-multi	tatoeba-test-v2020-07-28-v2023-09-26	0.42670	24.9	10000	57351
+cym-deu	flores101-devtest	0.52672	22.4	1012	25094
+cym-fra	flores101-devtest	0.58299	31.3	1012	28343
+cym-por	flores101-devtest	0.47733	18.4	1012	26519
+gle-eng	flores101-devtest	0.64773	38.6	1012	24721
+gle-fra	flores101-devtest	0.54559	26.5	1012	28343
+cym-deu	flores200-devtest	0.52745	22.6	1012	25094
+cym-eng	flores200-devtest	0.75234	55.5	1012	24721
+cym-fra	flores200-devtest	0.58339	31.4	1012	28343
+cym-por	flores200-devtest	0.47566	18.3	1012	26519
+cym-spa	flores200-devtest	0.48834	19.9	1012	29199
+gla-deu	flores200-devtest	0.41962	13.0	1012	25094
+gla-eng	flores200-devtest	0.53374	26.4	1012	24721
+gla-fra	flores200-devtest	0.44916	16.6	1012	28343
+gla-por	flores200-devtest	0.39790	12.1	1012	26519
+gla-spa	flores200-devtest	0.40375	12.9	1012	29199
+gle-deu	flores200-devtest	0.49962	19.2	1012	25094
+gle-eng	flores200-devtest	0.64866	38.9	1012	24721
+gle-fra	flores200-devtest	0.54564	26.7	1012	28343
+gle-por	flores200-devtest	0.44768	14.9	1012	26519
+gle-spa	flores200-devtest	0.47347	18.7	1012	29199
+cym-deu	ntrex128	0.46627	16.3	1997	48761
+cym-eng	ntrex128	0.65343	40.0	1997	47673
+cym-fra	ntrex128	0.51183	23.8	1997	53481
+cym-por	ntrex128	0.42857	14.4	1997	51631
+cym-spa	ntrex128	0.51542	25.0	1997	54107
+gle-deu	ntrex128	0.46495	15.5	1997	48761
+gle-eng	ntrex128	0.60913	33.5	1997	47673
+gle-fra	ntrex128	0.49513	20.7	1997	53481
+gle-por	ntrex128	0.41767	13.2	1997	51631
+gle-spa	ntrex128	0.50755	23.6	1997	54107
+cor-fra	tatoeba-test-v2020-07-28	0.24652	6.2	567	3136
+gla-eng	tatoeba-test-v2020-07-28	0.40979	25.3	917	6366
+gle-eng	tatoeba-test-v2020-07-28	0.64935	51.8	1924	11247
+bre-eng	tatoeba-test-v2021-03-30	0.53219	34.3	385	2091
+bre-fra	tatoeba-test-v2021-03-30	0.49675	28.8	2500	13343
+cor-deu	tatoeba-test-v2021-03-30	0.24298	6.8	822	4682
+cor-fra	tatoeba-test-v2021-03-30	0.24669	6.2	568	3142
+cor-spa	tatoeba-test-v2021-03-30	0.21930	4.5	207	1085
+gla-eng	tatoeba-test-v2021-03-30	0.41147	25.6	957	6628
+gla-spa	tatoeba-test-v2021-03-30	0.49577	24.6	290	1611
+gle-eng	tatoeba-test-v2021-03-30	0.64935	51.8	1924	11247
+bre-eng	tatoeba-test-v2021-08-07	0.53473	35.0	383	2065
+bre-fra	tatoeba-test-v2021-08-07	0.49013	28.3	2494	13324
+cor-deu	tatoeba-test-v2021-08-07	0.24055	6.5	821	4676
+cor-eng	tatoeba-test-v2021-08-07	0.19002	4.9	3198	16829
+cor-fra	tatoeba-test-v2021-08-07	0.24494	6.4	555	3092
+cor-spa	tatoeba-test-v2021-08-07	0.22170	4.7	206	1080
+cym-eng	tatoeba-test-v2021-08-07	0.68892	52.4	818	5563
+gla-eng	tatoeba-test-v2021-08-07	0.39607	23.2	955	6611
+gla-spa	tatoeba-test-v2021-08-07	0.51208	26.1	289	1608
+gle-eng	tatoeba-test-v2021-08-07	0.64268	50.7	1913	11190

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "pytorch-models/opus-mt-tc-bible-big-cel-deu_eng_fra_por_spa",
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "MarianMTModel"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classifier_dropout": 0.0,
+  "d_model": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 56598,
+  "decoder_vocab_size": 56599,
+  "dropout": 0.1,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 574,
+  "forced_eos_token_id": null,
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "max_length": null,
+  "max_position_embeddings": 1024,
+  "model_type": "marian",
+  "normalize_embedding": false,
+  "num_beams": null,
+  "num_hidden_layers": 6,
+  "pad_token_id": 56598,
+  "scale_embedding": true,
+  "share_encoder_decoder_embeddings": true,
+  "static_position_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.1",
+  "use_cache": true,
+  "vocab_size": 56599
+}

generation_config.json

@@ -0,0 +1,16 @@
+{
+  "_from_model_config": true,
+  "bad_words_ids": [
+    [
+      56598
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 56598,
+  "eos_token_id": 574,
+  "forced_eos_token_id": 574,
+  "max_length": 512,
+  "num_beams": 4,
+  "pad_token_id": 56598,
+  "transformers_version": "4.45.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f13b0f3fd4fa985bb0809140b29431083e4178945d8ffa382cd367a3a6c08dd3
+size 937515020

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12ba5d8557a1cc2b826582f7042c281e64cd05cbeebc21dfa3efb23dcbb2f30f
+size 937566277

source.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3d47a98f51d3b3ef3a0bdb9ab022bbbdcf14f45dde7dec4ab910e2baab534b0
+size 801982

special_tokens_map.json

@@ -0,0 +1 @@
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}

target.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70212b4c82db279a975546bac06c313785735f0a78e534aedcb9a297293af9f0
+size 800773

tokenizer_config.json

@@ -0,0 +1 @@
+{"source_lang": "cel", "target_lang": "deu+eng+fra+por+spa", "unk_token": "<unk>", "eos_token": "</s>", "pad_token": "<pad>", "model_max_length": 512, "sp_model_kwargs": {}, "separate_vocabs": false, "special_tokens_map_file": null, "name_or_path": "marian-models/opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-30/cel-deu+eng+fra+por+spa", "tokenizer_class": "MarianTokenizer"}