mirror of
https://www.modelscope.cn/iic/CosyVoice2-0.5B.git
synced 2025-04-10 11:50:22 +08:00
update
This commit is contained in:
lyuxiang.lx
parent
8cb32bda1d
commit
fa7edb69b3
1
.gitattributes
vendored
1
.gitattributes
vendored
@ -58,3 +58,4 @@ flow.decoder.estimator.fp16.a800.plan filter=lfs diff=lfs merge=lfs -text
|
||||
flow.decoder.estimator.fp16.l20.plan filter=lfs diff=lfs merge=lfs -text
|
||||
flow.decoder.estimator.fp16.a10.plan filter=lfs diff=lfs merge=lfs -text
|
||||
flow.decoder.estimator.fp16.v100.plan filter=lfs diff=lfs merge=lfs -text
|
||||
flow.encoder.fp16.zip filter=lfs diff=lfs merge=lfs -text
|
||||
|
||||
137
README.md
137
README.md
@ -1,42 +1,51 @@
|
||||
# CosyVoice
|
||||
[](https://github.com/Akshay090/svg-banners)
|
||||
|
||||
## 👉🏻 [CosyVoice2 Demos](https://funaudiollm.github.io/cosyvoice2/) 👈🏻
|
||||
[[CosyVoice2 Paper](https://fun-audio-llm.github.io/pdf/CosyVoice_v1.pdf)][[CosyVoice2 Studio](https://www.modelscope.cn/studios/iic/CosyVoice2-0.5B)]
|
||||
## 👉🏻 CosyVoice 👈🏻
|
||||
**CosyVoice 2.0**: [Demos](https://funaudiollm.github.io/cosyvoice2/); [Paper](https://arxiv.org/abs/2412.10117); [Modelscope](https://www.modelscope.cn/studios/iic/CosyVoice2-0.5B); [HuggingFace](https://huggingface.co/spaces/FunAudioLLM/CosyVoice2-0.5B)
|
||||
|
||||
## 👉🏻 [CosyVoice Demos](https://fun-audio-llm.github.io/) 👈🏻
|
||||
[[CosyVoice Paper](https://fun-audio-llm.github.io/pdf/CosyVoice_v1.pdf)][[CosyVoice Studio](https://www.modelscope.cn/studios/iic/CosyVoice-300M)][[CosyVoice Code](https://github.com/FunAudioLLM/CosyVoice)]
|
||||
**CosyVoice 1.0**: [Demos](https://fun-audio-llm.github.io); [Paper](https://funaudiollm.github.io/pdf/CosyVoice_v1.pdf); [Modelscope](https://www.modelscope.cn/studios/iic/CosyVoice-300M)
|
||||
|
||||
For `SenseVoice`, visit [SenseVoice repo](https://github.com/FunAudioLLM/SenseVoice) and [SenseVoice space](https://www.modelscope.cn/studios/iic/SenseVoice).
|
||||
## Highlight🔥
|
||||
|
||||
**CosyVoice 2.0** has been released! Compared to version 1.0, the new version offers more accurate, more stable, faster, and better speech generation capabilities.
|
||||
### Multilingual
|
||||
- **Supported Language**: Chinese, English, Japanese, Korean, Chinese dialects (Cantonese, Sichuanese, Shanghainese, Tianjinese, Wuhanese, etc.)
|
||||
- **Crosslingual & Mixlingual**：Support zero-shot voice cloning for cross-lingual and code-switching scenarios.
|
||||
### Ultra-Low Latency
|
||||
- **Bidirectional Streaming Support**: CosyVoice 2.0 integrates offline and streaming modeling technologies.
|
||||
- **Rapid First Packet Synthesis**: Achieves latency as low as 150ms while maintaining high-quality audio output.
|
||||
### High Accuracy
|
||||
- **Improved Pronunciation**: Reduces pronunciation errors by 30% to 50% compared to CosyVoice 1.0.
|
||||
- **Benchmark Achievements**: Attains the lowest character error rate on the hard test set of the Seed-TTS evaluation set.
|
||||
### Strong Stability
|
||||
- **Consistency in Timbre**: Ensures reliable voice consistency for zero-shot and cross-language speech synthesis.
|
||||
- **Cross-language Synthesis**: Marked improvements compared to version 1.0.
|
||||
### Natural Experience
|
||||
- **Enhanced Prosody and Sound Quality**: Improved alignment of synthesized audio, raising MOS evaluation scores from 5.4 to 5.53.
|
||||
- **Emotional and Dialectal Flexibility**: Now supports more granular emotional controls and accent adjustments.
|
||||
|
||||
## Roadmap
|
||||
|
||||
- [x] 2024/12
|
||||
|
||||
- [x] CosyVoice2-0.5B model release
|
||||
- [x] CosyVoice2-0.5B streaming inference with no quality degradation
|
||||
|
||||
- [x] 2024/07
|
||||
|
||||
- [x] Flow matching training support
|
||||
- [x] WeTextProcessing support when ttsfrd is not avaliable
|
||||
- [x] Fastapi server and client
|
||||
|
||||
- [x] 2024/08
|
||||
|
||||
- [x] Repetition Aware Sampling(RAS) inference for llm stability
|
||||
- [x] Streaming inference mode support, including kv cache and sdpa for rtf optimization
|
||||
- [x] 25hz cosyvoice 2.0 released
|
||||
|
||||
- [x] 2024/09
|
||||
|
||||
- [x] 25hz cosyvoice base model
|
||||
- [x] 25hz cosyvoice voice conversion model
|
||||
|
||||
- [ ] TBD
|
||||
- [x] 2024/08
|
||||
|
||||
- [x] Repetition Aware Sampling(RAS) inference for llm stability
|
||||
- [x] Streaming inference mode support, including kv cache and sdpa for rtf optimization
|
||||
|
||||
- [x] 2024/07
|
||||
|
||||
- [x] Flow matching training support
|
||||
- [x] WeTextProcessing support when ttsfrd is not available
|
||||
- [x] Fastapi server and client
|
||||
|
||||
- [ ] CosyVoice2-0.5B bistream inference support
|
||||
- [ ] CosyVoice2-0.5B training and finetune recipie
|
||||
- [ ] CosyVoice-500M trained with more multi-lingual data
|
||||
- [ ] More...
|
||||
|
||||
## Install
|
||||
|
||||
@ -69,9 +78,7 @@ sudo yum install sox sox-devel
|
||||
|
||||
**Model download**
|
||||
|
||||
We strongly recommend that you download our pretrained `CosyVoice-300M` `CosyVoice-300M-SFT` `CosyVoice-300M-Instruct` model and `CosyVoice-ttsfrd` resource.
|
||||
|
||||
If you are expert in this field, and you are only interested in training your own CosyVoice model from scratch, you can skip this step.
|
||||
We strongly recommend that you download our pretrained `CosyVoice2-0.5B` `CosyVoice-300M` `CosyVoice-300M-SFT` `CosyVoice-300M-Instruct` model and `CosyVoice-ttsfrd` resource.
|
||||
|
||||
``` python
|
||||
# SDK模型下载
|
||||
@ -95,42 +102,41 @@ git clone https://www.modelscope.cn/iic/CosyVoice-300M-Instruct.git pretrained_m
|
||||
git clone https://www.modelscope.cn/iic/CosyVoice-ttsfrd.git pretrained_models/CosyVoice-ttsfrd
|
||||
```
|
||||
|
||||
Optionaly, you can unzip `ttsfrd` resouce and install `ttsfrd` package for better text normalization performance.
|
||||
Optionally, you can unzip `ttsfrd` resouce and install `ttsfrd` package for better text normalization performance.
|
||||
|
||||
Notice that this step is not necessary. If you do not install `ttsfrd` package, we will use WeTextProcessing by default.
|
||||
|
||||
``` sh
|
||||
cd pretrained_models/CosyVoice-ttsfrd/
|
||||
unzip resource.zip -d .
|
||||
pip install ttsfrd-0.3.6-cp38-cp38-linux_x86_64.whl
|
||||
pip install ttsfrd_dependency-0.1-py3-none-any.whl
|
||||
pip install ttsfrd-0.4.2-cp310-cp310-linux_x86_64.whl
|
||||
```
|
||||
|
||||
**Basic Usage**
|
||||
|
||||
For zero_shot/cross_lingual inference, please use `CosyVoice2-0.5B` or `CosyVoice-300M` model.
|
||||
For sft inference, please use `CosyVoice-300M-SFT` model.
|
||||
For instruct inference, please use `CosyVoice-300M-Instruct` model.
|
||||
We strongly recommend using `CosyVoice2-0.5B` model for better streaming performance.
|
||||
|
||||
First, add `third_party/Matcha-TTS` to your `PYTHONPATH`.
|
||||
|
||||
``` sh
|
||||
export PYTHONPATH=third_party/Matcha-TTS
|
||||
```
|
||||
We strongly recommend using `CosyVoice2-0.5B` for better performance.
|
||||
Follow code below for detailed usage of each model.
|
||||
|
||||
``` python
|
||||
import sys
|
||||
sys.path.append('third_party/Matcha-TTS')
|
||||
from cosyvoice.cli.cosyvoice import CosyVoice, CosyVoice2
|
||||
from cosyvoice.utils.file_utils import load_wav
|
||||
import torchaudio
|
||||
cosyvoice = CosyVoice2('pretrained_models/CosyVoice2-0.5B', load_jit=True, load_onnx=False, load_trt=False)
|
||||
```
|
||||
|
||||
**CosyVoice2 Usage**
|
||||
```python
|
||||
cosyvoice = CosyVoice2('pretrained_models/CosyVoice2-0.5B', load_jit=False, load_trt=False, fp16=False)
|
||||
|
||||
# NOTE if you want to reproduce the results on https://funaudiollm.github.io/cosyvoice2, please add text_frontend=False during inference
|
||||
# zero_shot usage
|
||||
prompt_speech_16k = load_wav('zero_shot_prompt.wav', 16000)
|
||||
for i, j in enumerate(cosyvoice.inference_zero_shot('收到好友从远方寄来的生日礼物，那份意外的惊喜与深深的祝福让我心中充满了甜蜜的快乐，笑容如花儿般绽放。', '希望你以后能够做的比我还好呦。', prompt_speech_16k, stream=False)):
|
||||
torchaudio.save('zero_shot_{}.wav'.format(i), j['tts_speech'], cosyvoice.sample_rate)
|
||||
|
||||
# fine grained control, for supported control, check cosyvoice/tokenizer/tokenizer.py#L248
|
||||
prompt_speech_16k = load_wav('zero_shot_prompt.wav', 16000)
|
||||
for i, j in enumerate(cosyvoice.inference_cross_lingual('在他讲述那个荒诞故事的过程中，他突然[laughter]停下来，因为他自己也被逗笑了[laughter]。', prompt_speech_16k, stream=False)):
|
||||
torchaudio.save('fine_grained_control_{}.wav'.format(i), j['tts_speech'], cosyvoice.sample_rate)
|
||||
|
||||
@ -139,10 +145,39 @@ for i, j in enumerate(cosyvoice.inference_instruct2('收到好友从远方寄来
|
||||
torchaudio.save('instruct_{}.wav'.format(i), j['tts_speech'], cosyvoice.sample_rate)
|
||||
```
|
||||
|
||||
**CosyVoice Usage**
|
||||
```python
|
||||
cosyvoice = CosyVoice('pretrained_models/CosyVoice-300M-SFT', load_jit=False, load_trt=False, fp16=False)
|
||||
# sft usage
|
||||
print(cosyvoice.list_available_spks())
|
||||
# change stream=True for chunk stream inference
|
||||
for i, j in enumerate(cosyvoice.inference_sft('你好，我是通义生成式语音大模型，请问有什么可以帮您的吗？', '中文女', stream=False)):
|
||||
torchaudio.save('sft_{}.wav'.format(i), j['tts_speech'], cosyvoice.sample_rate)
|
||||
|
||||
cosyvoice = CosyVoice('pretrained_models/CosyVoice-300M') # or change to pretrained_models/CosyVoice-300M-25Hz for 25Hz inference
|
||||
# zero_shot usage, <|zh|><|en|><|jp|><|yue|><|ko|> for Chinese/English/Japanese/Cantonese/Korean
|
||||
prompt_speech_16k = load_wav('zero_shot_prompt.wav', 16000)
|
||||
for i, j in enumerate(cosyvoice.inference_zero_shot('收到好友从远方寄来的生日礼物，那份意外的惊喜与深深的祝福让我心中充满了甜蜜的快乐，笑容如花儿般绽放。', '希望你以后能够做的比我还好呦。', prompt_speech_16k, stream=False)):
|
||||
torchaudio.save('zero_shot_{}.wav'.format(i), j['tts_speech'], cosyvoice.sample_rate)
|
||||
# cross_lingual usage
|
||||
prompt_speech_16k = load_wav('cross_lingual_prompt.wav', 16000)
|
||||
for i, j in enumerate(cosyvoice.inference_cross_lingual('<|en|>And then later on, fully acquiring that company. So keeping management in line, interest in line with the asset that\'s coming into the family is a reason why sometimes we don\'t buy the whole thing.', prompt_speech_16k, stream=False)):
|
||||
torchaudio.save('cross_lingual_{}.wav'.format(i), j['tts_speech'], cosyvoice.sample_rate)
|
||||
# vc usage
|
||||
prompt_speech_16k = load_wav('zero_shot_prompt.wav', 16000)
|
||||
source_speech_16k = load_wav('cross_lingual_prompt.wav', 16000)
|
||||
for i, j in enumerate(cosyvoice.inference_vc(source_speech_16k, prompt_speech_16k, stream=False)):
|
||||
torchaudio.save('vc_{}.wav'.format(i), j['tts_speech'], cosyvoice.sample_rate)
|
||||
|
||||
cosyvoice = CosyVoice('pretrained_models/CosyVoice-300M-Instruct')
|
||||
# instruct usage, support <laughter></laughter><strong></strong>[laughter][breath]
|
||||
for i, j in enumerate(cosyvoice.inference_instruct('在面对挑战时，他展现了非凡的<strong>勇气</strong>与<strong>智慧</strong>。', '中文男', 'Theo \'Crimson\', is a fiery, passionate rebel leader. Fights with fervor for justice, but struggles with impulsiveness.', stream=False)):
|
||||
torchaudio.save('instruct_{}.wav'.format(i), j['tts_speech'], cosyvoice.sample_rate)
|
||||
```
|
||||
|
||||
**Start web demo**
|
||||
|
||||
You can use our web demo page to get familiar with CosyVoice quickly.
|
||||
We support sft/zero_shot/cross_lingual/instruct inference in web demo.
|
||||
|
||||
Please see the demo website for details.
|
||||
|
||||
@ -154,12 +189,11 @@ python3 webui.py --port 50000 --model_dir pretrained_models/CosyVoice-300M
|
||||
**Advanced Usage**
|
||||
|
||||
For advanced user, we have provided train and inference scripts in `examples/libritts/cosyvoice/run.sh`.
|
||||
You can get familiar with CosyVoice following this recipie.
|
||||
|
||||
**Build for deployment**
|
||||
|
||||
Optionally, if you want to use grpc for service deployment,
|
||||
you can run following steps. Otherwise, you can just ignore this step.
|
||||
Optionally, if you want service deployment,
|
||||
you can run following steps.
|
||||
|
||||
``` sh
|
||||
cd runtime/python
|
||||
@ -189,16 +223,5 @@ You can also scan the QR code to join our official Dingding chat group.
|
||||
4. We borrowed a lot of code from [AcademiCodec](https://github.com/yangdongchao/AcademiCodec).
|
||||
5. We borrowed a lot of code from [WeNet](https://github.com/wenet-e2e/wenet).
|
||||
|
||||
## Citations
|
||||
|
||||
``` bibtex
|
||||
@article{du2024cosyvoice,
|
||||
title={Cosyvoice: A scalable multilingual zero-shot text-to-speech synthesizer based on supervised semantic tokens},
|
||||
author={Du, Zhihao and Chen, Qian and Zhang, Shiliang and Hu, Kai and Lu, Heng and Yang, Yexin and Hu, Hangrui and Zheng, Siqi and Gu, Yue and Ma, Ziyang and others},
|
||||
journal={arXiv preprint arXiv:2407.05407},
|
||||
year={2024}
|
||||
}
|
||||
```
|
||||
|
||||
## 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.
|
||||
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.
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user