InspireMusic-Base

LICENSE.txt

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

README.md

@@ -1,3 +1,259 @@
----
-license: apache-2.0
----
+---
+license: apache-2.0
+pipeline_tag: text-to-audio
+tags:
+- text-to-music
+- music-generation
+---
+
+# InspireMusic
+
+<p align="center">
+ <a href="https://github.com/FunAudioLLM/InspireMusic" target="_blank">
+        <img alt="InspireMusic" src="https://svg-banners.vercel.app/api?type=origin&text1=Inspire%20Music🎶&text2=🤗%20A%20Fundamental%20Music%20Song%20Audio%20Generation%20Toolkit&width=800&height=210"></a>
+</p>
+
+[**Code**](https://inspiremusic.github.io/) | [**Demo**](https://iris2c.github.io/InspireMusic/) | [**ModelScope**](https://modelscope.cn/models/iic/InspireMusic/summary) | [**HuggingFace**](https://huggingface.co/FunAudioLLM/InspireMusic-Base)
+
+InspireMusic is a fundamental AIGC toolkit designed for music, song, and audio generation using the PyTorch library. 
+
+## Introduction
+> [!Note]
+> This repo contains the algorithm infrastructure and some simple examples.
+
+> [!Tip]
+> To explore the performance, please refer to [**InspireMusic Demo Page**](https://iris2c.github.io/InspireMusic). Space will also coming soon.
+
+InspireMusic is a unified music, song and audio generation framework through the audio tokenization and detokenization process integrated with a large autoregressive transformer. The original motive of this toolkit is to empower the common users to innovate soundscapes and enhance euphony in research through music, song, and audio crafting. The toolkit provides both inference and training code for AI generative models that create high-quality music. Featuring a unified framework, InspireMusic incorporates autoregressive Transformer and conditional flow-matching modeling (CFM), allowing for the controllable generation of music, songs, and audio with both textual and structural music conditioning, as well as neural audio tokenizers. Currently, the toolkit supports text-to-music generation and plans to expand its capabilities to include text-to-song and text-to-audio generation in the future.
+
+<a name="Highligts"></a>
+## Highlights
+**InspireMusic** focuses on music generation, song generation and audio generation.
+- A unified framework for music/song/audio generation.
+- Controllable with text prompts, music genres, music structures, etc.
+- Convenient Fine-tuning and Inference: Provide convenient fine-tuning and inference scripts and strategies, allowing users to easily their music generation models.
+- High audio quality.
+
+<a name="What's News"></a>
+## What's New 🔥
+
+[//]: # (- 2024/12: The [InspireMusic-Base]&#40;https://huggingface.co/FunAudioLLM/InspireMusic-Base&#41; voice understanding model is open-sourced, which offers high quality, diverse text style, music structure, music genre control capability.  )
+- 2024/11: Welcome to preview 👉🏻 [**InspireMusic Demos**](https://iris2c.github.io/InspireMusic) 👈🏻, more features and models will comming soon. We're excited to share this with you and are working hard to bring even more features and models very soon. Your support and feedback mean a lot to us!
+- 2024/11: We are thrilled to announce the open-sourcing of the **InspireMusic** [code repository](https://github.com/FunAudioLLM/InspireMusic) and [demos](https://iris2c.github.io/InspireMusic). **InspireMusic** is a unified framework for music, song, and audio generation, featuring capabilities such as text-to-music conversion, music structure, genre control, and timestamp management. InspireMusic stands out for its exceptional music generation and instruction-following abilities.
+
+## Installation
+
+### Clone
+
+- Clone the repo
+``` sh
+git clone --recursive https://github.com/FunAudioLLM/InspireMusic.git
+# If you failed to clone submodule due to network failures, please run the following command until success
+cd InspireMusic
+git submodule update --init --recursive
+```
+
+### Install
+InspireMusic requires Python 3.8, PyTorch 2.1.0. To install InspireMusic, you can run one of the following:
+
+- Install Conda: please see https://docs.conda.io/en/latest/miniconda.html
+- Create Conda env:
+``` sh
+conda create -n inspiremusic python=3.8
+conda activate inspiremusic
+cd InspireMusic
+# pynini is required by WeTextProcessing, use conda to install it as it can be executed on all platforms.
+conda install -y -c conda-forge pynini==2.1.5
+pip install -r requirements.txt -i https://mirrors.aliyun.com/pypi/simple/ --trusted-host=mirrors.aliyun.com
+# install flash attention to speedup training
+pip install flash-attn --no-build-isolation
+```
+
+- Install within the package:
+```sh
+cd InspireMusic
+# You can run to install the packages
+python setup.py install
+pip install flash-attn --no-build-isolation
+```
+
+We also recommend having `sox` or `ffmpeg` installed, either through your system or Anaconda:
+```sh
+# # Install sox
+# ubuntu
+sudo apt-get install sox libsox-dev
+# centos
+sudo yum install sox sox-devel
+
+# Install ffmpeg
+# ubuntu
+sudo apt-get install ffmpeg
+# centos
+sudo yum install ffmpeg
+```
+
+## Models
+### Download Model
+
+We strongly recommend that you download our pretrained `InspireMusic model`.
+
+If you are an expert in this field, and you are only interested in training your own InspireMusic model from scratch, you can skip this step.
+
+``` sh
+# git模型下载，请确保已安装git lfs
+mkdir -p pretrained_models
+git clone https://www.modelscope.cn/iic/InspireMusic.git pretrained_models/InspireMusic-Base
+```
+
+### Available Models
+Currently, we open source the music generation models that only support 24KHz mono channel audio. 
+The table below presents the links to the ModelScope and Huggingface model hub. More models will be available soon.
+
+| Model name            | Model Links                                                                                                                                                                               | Remarks                                        |
+|------------------------------|-------------------------------------------------------|-------------|
+| InspireMusic-Base     | [![model](https://img.shields.io/badge/ModelScope-Model-orange.svg)](https://modelscope.cn/models/iic/InspireMusic/summary) [![model](https://img.shields.io/badge/HuggingFace-Model-orange.svg)](https://huggingface.co/FunAudioLLM/InspireMusic-Base) | Pre-trained Music Generation Model, 24kHz mono |
+| InspireMusic-1.5B     | [![model](https://img.shields.io/badge/ModelScope-Model-lightgrey.svg)]() [![model](https://img.shields.io/badge/HuggingFace-Model-lightgrey.svg)]()                                      | Pre-trained Music Generation 1.5B Model, 24kHz mono       |
+| InspireSong-Base      | [![model](https://img.shields.io/badge/ModelScope-Model-lightgrey.svg)]() [![model](https://img.shields.io/badge/HuggingFace-Model-lightgrey.svg)]()                                      | Pre-trained Song Generation Base Model, 24kHz mono         |
+| InspireSong-1.5B      | [![model](https://img.shields.io/badge/ModelScope-Model-lightgrey.svg)]() [![model](https://img.shields.io/badge/HuggingFace-Model-lightgrey.svg)]()                                      | Pre-trained Song Generation 1.5B Model, 24kHz mono         |
+| InspireAudio-1.5B     | [![model](https://img.shields.io/badge/ModelScope-Model-lightgrey.svg)]() [![model](https://img.shields.io/badge/HuggingFace-Model-lightgrey.svg)]()                                      | Pre-trained Audio Generation 1.5B Model, 24kHz mono        |
+
+## Basic Usage
+
+At the moment, InspireMusic contains the training code and inference code for [music generation](https://github.com/FunAudioLLM/InspireMusic/tree/main/examples/music_generation). More tasks such as song generation and audio generation will be supported in future.
+
+### Quick Start
+
+Here is a quick start running script to do music generation task including data preparation pipeline, model training, inference. 
+``` sh
+cd InspireMusic/examples/music_generation/
+bash run.sh
+```
+
+### Training
+
+Here is an example to train LLM model. 
+```sh
+torchrun --nnodes=1 --nproc_per_node=8 \
+    --rdzv_id=1024 --rdzv_backend="c10d" --rdzv_endpoint="localhost:0" \
+    inspiremusic/bin/train.py \
+    --train_engine "torch_ddp" \
+    --config conf/inspiremusic.yaml \
+    --train_data data/train.data.list \
+    --cv_data data/dev.data.list \
+    --model llm \
+    --model_dir `pwd`/exp/music_generation/llm/ \
+    --tensorboard_dir `pwd`/tensorboard/music_generation/llm/ \
+    --ddp.dist_backend "nccl" \
+    --num_workers 8 \
+    --prefetch 100 \
+    --pin_memory \
+    --deepspeed_config ./conf/ds_stage2.json \
+    --deepspeed.save_states model+optimizer \
+    --fp16
+```
+
+Here is an example code to train flow matching model. 
+```sh
+torchrun --nnodes=1 --nproc_per_node=8 \
+    --rdzv_id=1024 --rdzv_backend="c10d" --rdzv_endpoint="localhost:0" \
+    inspiremusic/bin/train.py \
+    --train_engine "torch_ddp" \
+    --config conf/inspiremusic.yaml \
+    --train_data data/train.data.list \
+    --cv_data data/dev.data.list \
+    --model flow \
+    --model_dir `pwd`/exp/music_generation/flow/ \
+    --tensorboard_dir `pwd`/tensorboard/music_generation/flow/ \
+    --ddp.dist_backend "nccl" \
+    --num_workers 8 \
+    --prefetch 100 \
+    --pin_memory \
+    --deepspeed_config ./conf/ds_stage2.json \
+    --deepspeed.save_states model+optimizer \
+    --fp16
+```
+
+### Inference
+
+Here is an example script to quickly do model inference.
+``` sh
+cd InspireMusic/examples/music_generation/
+bash infer.sh
+```
+
+Here is an example code to run inference with flow matching model.
+```sh
+pretrained_model_dir = "./pretrained_models/InspireMusic/"
+python inspiremusic/bin/inference.py --mode sft \
+      --gpu 0 \
+      --config conf/inspiremusic.yaml \
+      --prompt_data data/test/parquet/data.list \
+      --flow_model $pretrained_model_dir/flow.pt \
+      --llm_model $pretrained_model_dir/llm.pt \
+      --music_tokenizer $pretrained_model_dir/music_tokenizer \
+      --wavtokenizer $pretrained_model_dir/wavtokenizer \
+      --result_dir `pwd`/exp/inspiremusic/sft_test \
+      --chorus verse \
+      --min_generate_audio_seconds 8 \
+      --max_generate_audio_seconds 30 
+```
+
+Here is an example code to run inference without flow matching model.
+```sh
+pretrained_model_dir = "./pretrained_models/InspireMusic/"
+python inspiremusic/bin/inference.py --mode sft \
+      --gpu 0 \
+      --config conf/inspiremusic.yaml \
+      --prompt_data data/test/parquet/data.list \
+      --flow_model $pretrained_model_dir/flow.pt \
+      --llm_model $pretrained_model_dir/llm.pt \
+      --music_tokenizer $pretrained_model_dir/music_tokenizer \
+      --wavtokenizer $pretrained_model_dir/wavtokenizer \
+      --no_flow_mode True \
+      --result_dir `pwd`/exp/inspiremusic/sft_test \
+      --chorus verse \
+      --min_generate_audio_seconds 8 \
+      --max_generate_audio_seconds 30 
+```
+
+### Friend Links
+Checkout some awesome Github repositories from Speech Lab of Institute for Intelligent Computing, Alibaba Group.
+
+<p align="left">
+<a href="https://github.com/modelscope/ClearerVoice-Studio" target="_blank">
+        <img alt="Demo" src="https://img.shields.io/badge/Repo | Space-ClearVoice?labelColor=&label=ClearVoice&color=green"></a>
+<a href="https://github.com/FunAudioLLM/CosyVoice" target="_blank">
+        <img alt="Demo" src="https://img.shields.io/badge/Repo | Space-CosyVoice?labelColor=&label=CosyVoice&color=green"></a>
+<a href="https://github.com/FunAudioLLM/SenseVoice" target="_blank">
+        <img alt="Demo" src="https://img.shields.io/badge/Repo | Space-SenseVoice?labelColor=&label=SenseVoice&color=green"></a>
+</p>
+
+## Community & Discussion
+* Please support our community project 🌟 by starring it on GitHub 🙏
+* Welcome to join our DingTalk and WeChat groups to share and discuss algorithms, technology, and user experience feedback. You may scan the following QR codes to join our official chat groups accordingly. 
+
+<p align="center">
+  <table>
+    <tr>
+      <td style="text-align:center;">
+        <a href="./asset/QR.jpg"><img alt="FunAudioLLM in DingTalk" src="https://img.shields.io/badge/FunAudioLLM-DingTalk-d9d9d9"></a>
+      </td>
+      <td style="text-align:center;">
+        <a href="./asset/QR.jpg"><img alt="InspireMusic in WeChat" src="https://img.shields.io/badge/InspireMusic-WeChat-d9d9d9"></a>
+      </td>
+    </tr>
+    <tr>
+       <td style="text-align:center;">
+      <img alt="Light" src="./asset/dingding.png" width="68%" />
+      <td style="text-align:center;">
+      <img alt="Light" src="./asset/QR.jpg" width="58%" />
+      </td>
+    </tr>
+  </table>
+</p>
+
+* [Github Discussion](https://github.com/FunAudioLLM/InspireMusic/discussions). Best for sharing feedback and asking questions.
+* [GitHub Issues](https://github.com/FunAudioLLM/InspireMusic/issues). Best for bugs you encounter using InspireMusic, and feature proposals.
+
+## Disclaimer
+The content provided above is for academic purposes only and is intended to demonstrate technical capabilities. Some examples are sourced from the internet. If any content infringes on your rights, please contact us to request its removal.

config.json

@@ -0,0 +1,27 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 24,
+  "model_type": "qwen2",
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.1",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

configuration.json

@@ -0,0 +1 @@
+{"task":"audio-generation"}

flow.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:274801d494a510956c58c0cfea56d20b790265be1574618fc68b296d82971985
+size 306402045

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "pad_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "repetition_penalty": 1.1,
+  "temperature": 0.7,
+  "top_p": 0.8,
+  "top_k": 20,
+  "transformers_version": "4.37.0"
+}

inspiremusic.yaml

@@ -0,0 +1,177 @@
+# set random seed, so that you may reproduce your result.
+__set_seed1: !apply:random.seed [1024]
+__set_seed2: !apply:numpy.random.seed [1024]
+__set_seed3: !apply:torch.manual_seed [1024]
+__set_seed4: !apply:torch.cuda.manual_seed_all [1024]
+
+# fixed params
+sample_rate: 24000
+text_encoder_input_size: 512
+llm_input_size: 896
+llm_output_size: 896
+spk_embed_dim: 192
+
+# model params
+# for all class/function included in this repo, we use !<name> or !<new> for intialization, so that user may find all corresponding class/function according to one single yaml.
+# for system/third_party class/function, we do not require this.
+llm: !new:inspiremusic.llm.plm.PLM
+    text_encoder_input_size: !ref <text_encoder_input_size>
+    llm_input_size: !ref <llm_input_size>
+    llm_output_size: !ref <llm_output_size>
+    audio_token_size: 4096
+    length_normalized_loss: True
+    lsm_weight: 0
+    spk_embed_dim: !ref <spk_embed_dim>
+    text_encoder_conf:
+        name: "none"
+    llm: !new:inspiremusic.transformer.qwen_encoder.QwenEmbeddingEncoder
+        input_size: !ref <text_encoder_input_size>
+        pretrain_path: ../../pretrained_models/InspireMusic-Base/
+        
+    # sampling: !name:inspiremusic.utils.common.topk_sampling
+    #     top_k: 350
+    sampling: !name:inspiremusic.utils.common.ras_sampling
+        top_p: 0.8
+        top_k: 50
+        win_size: 10
+        tau_r: 0.1
+    train_cfg_ratio: 0.2
+    infer_cfg_ratio: 3.0
+flow: !new:inspiremusic.flow.flow.MaskedDiffWithXvec
+    input_size: 256
+    output_size: 80
+    spk_embed_dim: !ref <spk_embed_dim>
+    output_type: 'mel'
+    vocab_size: 4096
+    input_frame_rate: 75
+    only_mask_loss: True
+    encoder: !new:inspiremusic.transformer.encoder.ConformerEncoder
+        output_size: 512
+        attention_heads: 4
+        linear_units: 1024
+        num_blocks: 3
+        dropout_rate: 0.1
+        positional_dropout_rate: 0.1
+        attention_dropout_rate: 0.1
+        normalize_before: True
+        input_layer: 'linear'
+        pos_enc_layer_type: 'rel_pos_espnet'
+        selfattention_layer_type: 'rel_selfattn'
+        input_size: 256
+        use_cnn_module: False
+        macaron_style: False
+    length_regulator: !new:inspiremusic.flow.length_regulator.InterpolateRegulator
+        channels: 512
+        sampling_ratios: [1, 1, 1, 1]
+    decoder: !new:inspiremusic.flow.flow_matching.ConditionalCFM
+        in_channels: 240
+        n_spks: 1
+        spk_emb_dim: 80
+        cfm_params: !new:omegaconf.DictConfig
+            content:
+                sigma_min: 1e-06
+                solver: 'euler'
+                t_scheduler: 'cosine'
+                training_cfg_rate: 0.2
+                inference_cfg_rate: 0.7
+                reg_loss_type: 'l1'
+        estimator: !new:inspiremusic.flow.decoder.ConditionalDecoder
+            in_channels: 1024
+            out_channels: 512
+            channels: [256, 256]
+            dropout: 0.0
+            attention_head_dim: 64
+            n_blocks: 4
+            num_mid_blocks: 8
+            num_heads: 8
+            act_fn: 'gelu'
+
+hift: !new:inspiremusic.hifigan.generator.HiFTGenerator
+    in_channels: 80
+    base_channels: 512
+    nb_harmonics: 8
+    sampling_rate: !ref <sample_rate>
+    nsf_alpha: 0.1
+    nsf_sigma: 0.003
+    nsf_voiced_threshold: 10
+    upsample_rates: [8, 8]
+    upsample_kernel_sizes: [16, 16]
+    istft_params:
+        n_fft: 16
+        hop_len: 4
+    resblock_kernel_sizes: [3, 7, 11]
+    resblock_dilation_sizes: [[1, 3, 5], [1, 3, 5], [1, 3, 5]]
+    source_resblock_kernel_sizes: [7, 11]
+    source_resblock_dilation_sizes: [[1, 3, 5], [1, 3, 5]]
+    lrelu_slope: 0.1
+    audio_limit: 0.99
+    f0_predictor: !new:inspiremusic.hifigan.f0_predictor.ConvRNNF0Predictor
+        num_class: 1
+        in_channels: 80
+        cond_channels: 512
+
+wavtokenizer: !new:inspiremusic.hifigan.generator.HiFTGenerator
+
+# processor functions
+parquet_opener: !name:inspiremusic.dataset.processor.parquet_opener
+get_tokenizer: !name:inspiremusic.text.tokenizer.get_tokenizer
+    tokenizer_path: "../../pretrained_models/InspireMusic-Base/"
+    tokenizer_name: "qwen-2.0"
+allowed_special: 'all'
+tokenize: !name:inspiremusic.dataset.processor.tokenize
+    get_tokenizer: !ref <get_tokenizer>
+    allowed_special: !ref <allowed_special>
+filter: !name:inspiremusic.dataset.processor.filter
+    max_length: 28000
+    min_length: 0
+    token_max_length: 200
+    token_min_length: 1
+resample: !name:inspiremusic.dataset.processor.resample
+    resample_rate: !ref <sample_rate>
+feat_extractor: !name:matcha.utils.audio.mel_spectrogram
+    n_fft: 1024
+    num_mels: 128
+    sampling_rate: !ref <sample_rate>
+    hop_size: 256
+    win_size: 1024
+    fmin: 0
+    fmax: 12000
+    center: False
+compute_fbank: !name:inspiremusic.dataset.processor.compute_fbank
+    feat_extractor: !ref <feat_extractor>
+parse_embedding: !name:inspiremusic.dataset.processor.parse_embedding
+    normalize: True
+shuffle: !name:inspiremusic.dataset.processor.shuffle
+    shuffle_size: 1000
+sort: !name:inspiremusic.dataset.processor.sort
+    sort_size: 500  # sort_size should be less than shuffle_size
+batch: !name:inspiremusic.dataset.processor.batch
+    batch_type: 'dynamic'
+    max_frames_in_batch: 30000
+padding: !name:inspiremusic.dataset.processor.padding
+    use_spk_embedding: False # change to True during sft
+
+# dataset processor pipeline
+data_pipeline: [
+    !ref <parquet_opener>,
+    !ref <tokenize>,
+    !ref <shuffle>,
+    !ref <sort>,
+    !ref <filter>, 
+    !ref <batch>,
+    !ref <padding>,
+]
+
+# train conf
+train_conf:
+    optim: adam
+    optim_conf:
+        lr: 0.00001 # change to 0.001 if you want to train flow from scratch
+    scheduler: warmuplr
+    scheduler_conf:
+        warmup_steps: 1000
+    max_epoch: 200
+    grad_clip: 5
+    accum_grad: 2
+    log_interval: 100
+    save_per_step: 10000

llm.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97a9ceabe2d6ccdbaef154aedb85c2c6cfc71fe309bb31c9b911b742a7424553
+size 2006352049

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:130282af0dfa9fe5840737cc49a0d339d06075f83c5a315c3372c9a0740d0b96
+size 988097824

tokenizer_config.json

@@ -0,0 +1,40 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": ["<|im_start|>", "<|im_end|>"],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}