# CosyVoice
## 👉🏻 [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)]
For `SenseVoice`, visit [SenseVoice repo](https://github.com/FunAudioLLM/SenseVoice) and [SenseVoice space](https://www.modelscope.cn/studios/iic/SenseVoice).
## Roadmap
- [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] 2024/09
- [x] 25hz cosyvoice base model
- [x] 25hz cosyvoice voice conversion model
- [ ] TBD
- [ ] 25hz llama based llm model which supports lora finetune
- [ ] Support more instruction mode
- [ ] Music generation
- [ ] CosyVoice-500M trained with more multi-lingual data
- [ ] More...
## Install
**Clone and install**
- Clone the repo
``` sh
git clone --recursive https://github.com/FunAudioLLM/CosyVoice.git
# If you failed to clone submodule due to network failures, please run following command until success
cd CosyVoice
git submodule update --init --recursive
```
- Install Conda: please see https://docs.conda.io/en/latest/miniconda.html
- Create Conda env:
``` sh
conda create -n cosyvoice python=3.8
conda activate cosyvoice
# pynini is required by WeTextProcessing, use conda to install it as it can be executed on all platform.
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
# If you encounter sox compatibility issues
# ubuntu
sudo apt-get install sox libsox-dev
# centos
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.
``` python
# SDK模型下载
from modelscope import snapshot_download
snapshot_download('iic/CosyVoice-300M', local_dir='pretrained_models/CosyVoice-300M')
snapshot_download('iic/CosyVoice-300M-25Hz', local_dir='pretrained_models/CosyVoice-300M-25Hz')
snapshot_download('iic/CosyVoice-300M-SFT', local_dir='pretrained_models/CosyVoice-300M-SFT')
snapshot_download('iic/CosyVoice-300M-Instruct', local_dir='pretrained_models/CosyVoice-300M-Instruct')
snapshot_download('iic/CosyVoice-ttsfrd', local_dir='pretrained_models/CosyVoice-ttsfrd')
```
``` 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/CosyVoice-300M.git pretrained_models/CosyVoice-300M
git clone https://www.modelscope.cn/iic/CosyVoice-300M-25Hz.git pretrained_models/CosyVoice-300M-25Hz
git clone https://www.modelscope.cn/iic/CosyVoice-300M-SFT.git pretrained_models/CosyVoice-300M-SFT
git clone https://www.modelscope.cn/iic/CosyVoice-300M-Instruct.git pretrained_models/CosyVoice-300M-Instruct
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.
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
```
**Basic Usage**
For zero_shot/cross_lingual inference, please use `CosyVoice-300M` model.
For sft inference, please use `CosyVoice-300M-SFT` model.
For instruct inference, please use `CosyVoice-300M-Instruct` model.
First, add `third_party/Matcha-TTS` to your `PYTHONPATH`.
``` sh
export PYTHONPATH=third_party/Matcha-TTS
```
``` python
from cosyvoice.cli.cosyvoice import CosyVoice
from cosyvoice.utils.file_utils import load_wav
import torchaudio
cosyvoice = CosyVoice('pretrained_models/CosyVoice-300M-SFT', load_jit=True, load_onnx=False, fp16=True)
# sft usage
print(cosyvoice.list_avaliable_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'], 22050)
cosyvoice = CosyVoice('pretrained_models/CosyVoice-300M-25Hz') # or change to pretrained_models/CosyVoice-300M for 50Hz 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'], 22050)
# 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'], 22050)
# 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'], 22050)
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'], 22050)
```
**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.
``` python
# change iic/CosyVoice-300M-SFT for sft inference, or iic/CosyVoice-300M-Instruct for instruct inference
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.
``` sh
cd runtime/python
docker build -t cosyvoice:v1.0 .
# change iic/CosyVoice-300M to iic/CosyVoice-300M-Instruct if you want to use instruct inference
# for grpc usage
docker run -d --runtime=nvidia -p 50000:50000 cosyvoice:v1.0 /bin/bash -c "cd /opt/CosyVoice/CosyVoice/runtime/python/grpc && python3 server.py --port 50000 --max_conc 4 --model_dir iic/CosyVoice-300M && sleep infinity"
cd grpc && python3 client.py --port 50000 --mode <sft|zero_shot|cross_lingual|instruct>
# for fastapi usage
docker run -d --runtime=nvidia -p 50000:50000 cosyvoice:v1.0 /bin/bash -c "cd /opt/CosyVoice/CosyVoice/runtime/python/fastapi && python3 server.py --port 50000 --model_dir iic/CosyVoice-300M && sleep infinity"
cd fastapi && python3 client.py --port 50000 --mode <sft|zero_shot|cross_lingual|instruct>
```
## Discussion & Communication
You can directly discuss on [Github Issues](https://github.com/FunAudioLLM/CosyVoice/issues).
You can also scan the QR code to join our official Dingding chat group.
<img src="./asset/dingding.png" width="250px">
## Acknowledge
1. We borrowed a lot of code from [FunASR](https://github.com/modelscope/FunASR).
2. We borrowed a lot of code from [FunCodec](https://github.com/modelscope/FunCodec).
3. We borrowed a lot of code from [Matcha-TTS](https://github.com/shivammehta25/Matcha-TTS).
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).
## 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.
Raw data
{
"_id": null,
"home_page": "https://github.com/lucasjinreal/CosyVoice",
"name": "cosyvoice",
"maintainer": null,
"docs_url": null,
"requires_python": null,
"maintainer_email": null,
"keywords": "deep learning, script helper, tools",
"author": "Lucas Jin",
"author_email": "jinfagang19@163.com",
"download_url": "https://files.pythonhosted.org/packages/cc/cb/7ed03b5a2e941d70fbf165e5d2e5caeff88ea2bff2e822fc4e75437fc1d0/cosyvoice-0.0.8.tar.gz",
"platform": "any",
"description": "# CosyVoice\n## \ud83d\udc49\ud83c\udffb [CosyVoice Demos](https://fun-audio-llm.github.io/) \ud83d\udc48\ud83c\udffb\n[[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)]\n\nFor `SenseVoice`, visit [SenseVoice repo](https://github.com/FunAudioLLM/SenseVoice) and [SenseVoice space](https://www.modelscope.cn/studios/iic/SenseVoice).\n\n## Roadmap\n\n- [x] 2024/07\n\n - [x] Flow matching training support\n - [x] WeTextProcessing support when ttsfrd is not avaliable\n - [x] Fastapi server and client\n\n- [x] 2024/08\n\n - [x] Repetition Aware Sampling(RAS) inference for llm stability\n - [x] Streaming inference mode support, including kv cache and sdpa for rtf optimization\n\n- [x] 2024/09\n\n - [x] 25hz cosyvoice base model\n - [x] 25hz cosyvoice voice conversion model\n\n- [ ] TBD\n\n - [ ] 25hz llama based llm model which supports lora finetune\n - [ ] Support more instruction mode\n - [ ] Music generation\n - [ ] CosyVoice-500M trained with more multi-lingual data\n - [ ] More...\n\n## Install\n\n**Clone and install**\n\n- Clone the repo\n``` sh\ngit clone --recursive https://github.com/FunAudioLLM/CosyVoice.git\n# If you failed to clone submodule due to network failures, please run following command until success\ncd CosyVoice\ngit submodule update --init --recursive\n```\n\n- Install Conda: please see https://docs.conda.io/en/latest/miniconda.html\n- Create Conda env:\n\n``` sh\nconda create -n cosyvoice python=3.8\nconda activate cosyvoice\n# pynini is required by WeTextProcessing, use conda to install it as it can be executed on all platform.\nconda install -y -c conda-forge pynini==2.1.5\npip install -r requirements.txt -i https://mirrors.aliyun.com/pypi/simple/ --trusted-host=mirrors.aliyun.com\n\n# If you encounter sox compatibility issues\n# ubuntu\nsudo apt-get install sox libsox-dev\n# centos\nsudo yum install sox sox-devel\n```\n\n**Model download**\n\nWe strongly recommend that you download our pretrained `CosyVoice-300M` `CosyVoice-300M-SFT` `CosyVoice-300M-Instruct` model and `CosyVoice-ttsfrd` resource.\n\nIf you are expert in this field, and you are only interested in training your own CosyVoice model from scratch, you can skip this step.\n\n``` python\n# SDK\u6a21\u578b\u4e0b\u8f7d\nfrom modelscope import snapshot_download\nsnapshot_download('iic/CosyVoice-300M', local_dir='pretrained_models/CosyVoice-300M')\nsnapshot_download('iic/CosyVoice-300M-25Hz', local_dir='pretrained_models/CosyVoice-300M-25Hz')\nsnapshot_download('iic/CosyVoice-300M-SFT', local_dir='pretrained_models/CosyVoice-300M-SFT')\nsnapshot_download('iic/CosyVoice-300M-Instruct', local_dir='pretrained_models/CosyVoice-300M-Instruct')\nsnapshot_download('iic/CosyVoice-ttsfrd', local_dir='pretrained_models/CosyVoice-ttsfrd')\n```\n\n``` sh\n# git\u6a21\u578b\u4e0b\u8f7d\uff0c\u8bf7\u786e\u4fdd\u5df2\u5b89\u88c5git lfs\nmkdir -p pretrained_models\ngit clone https://www.modelscope.cn/iic/CosyVoice-300M.git pretrained_models/CosyVoice-300M\ngit clone https://www.modelscope.cn/iic/CosyVoice-300M-25Hz.git pretrained_models/CosyVoice-300M-25Hz\ngit clone https://www.modelscope.cn/iic/CosyVoice-300M-SFT.git pretrained_models/CosyVoice-300M-SFT\ngit clone https://www.modelscope.cn/iic/CosyVoice-300M-Instruct.git pretrained_models/CosyVoice-300M-Instruct\ngit clone https://www.modelscope.cn/iic/CosyVoice-ttsfrd.git pretrained_models/CosyVoice-ttsfrd\n```\n\nOptionaly, you can unzip `ttsfrd` resouce and install `ttsfrd` package for better text normalization performance.\n\nNotice that this step is not necessary. If you do not install `ttsfrd` package, we will use WeTextProcessing by default.\n\n``` sh\ncd pretrained_models/CosyVoice-ttsfrd/\nunzip resource.zip -d .\npip install ttsfrd-0.3.6-cp38-cp38-linux_x86_64.whl\n```\n\n**Basic Usage**\n\nFor zero_shot/cross_lingual inference, please use `CosyVoice-300M` model.\nFor sft inference, please use `CosyVoice-300M-SFT` model.\nFor instruct inference, please use `CosyVoice-300M-Instruct` model.\nFirst, add `third_party/Matcha-TTS` to your `PYTHONPATH`.\n\n``` sh\nexport PYTHONPATH=third_party/Matcha-TTS\n```\n\n``` python\nfrom cosyvoice.cli.cosyvoice import CosyVoice\nfrom cosyvoice.utils.file_utils import load_wav\nimport torchaudio\n\ncosyvoice = CosyVoice('pretrained_models/CosyVoice-300M-SFT', load_jit=True, load_onnx=False, fp16=True)\n# sft usage\nprint(cosyvoice.list_avaliable_spks())\n# change stream=True for chunk stream inference\nfor i, j in enumerate(cosyvoice.inference_sft('\u4f60\u597d\uff0c\u6211\u662f\u901a\u4e49\u751f\u6210\u5f0f\u8bed\u97f3\u5927\u6a21\u578b\uff0c\u8bf7\u95ee\u6709\u4ec0\u4e48\u53ef\u4ee5\u5e2e\u60a8\u7684\u5417\uff1f', '\u4e2d\u6587\u5973', stream=False)):\n torchaudio.save('sft_{}.wav'.format(i), j['tts_speech'], 22050)\n\ncosyvoice = CosyVoice('pretrained_models/CosyVoice-300M-25Hz') # or change to pretrained_models/CosyVoice-300M for 50Hz inference\n# zero_shot usage, <|zh|><|en|><|jp|><|yue|><|ko|> for Chinese/English/Japanese/Cantonese/Korean\nprompt_speech_16k = load_wav('zero_shot_prompt.wav', 16000)\nfor i, j in enumerate(cosyvoice.inference_zero_shot('\u6536\u5230\u597d\u53cb\u4ece\u8fdc\u65b9\u5bc4\u6765\u7684\u751f\u65e5\u793c\u7269\uff0c\u90a3\u4efd\u610f\u5916\u7684\u60ca\u559c\u4e0e\u6df1\u6df1\u7684\u795d\u798f\u8ba9\u6211\u5fc3\u4e2d\u5145\u6ee1\u4e86\u751c\u871c\u7684\u5feb\u4e50\uff0c\u7b11\u5bb9\u5982\u82b1\u513f\u822c\u7efd\u653e\u3002', '\u5e0c\u671b\u4f60\u4ee5\u540e\u80fd\u591f\u505a\u7684\u6bd4\u6211\u8fd8\u597d\u5466\u3002', prompt_speech_16k, stream=False)):\n torchaudio.save('zero_shot_{}.wav'.format(i), j['tts_speech'], 22050)\n# cross_lingual usage\nprompt_speech_16k = load_wav('cross_lingual_prompt.wav', 16000)\nfor 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)):\n torchaudio.save('cross_lingual_{}.wav'.format(i), j['tts_speech'], 22050)\n# vc usage\nprompt_speech_16k = load_wav('zero_shot_prompt.wav', 16000)\nsource_speech_16k = load_wav('cross_lingual_prompt.wav', 16000)\nfor i, j in enumerate(cosyvoice.inference_vc(source_speech_16k, prompt_speech_16k, stream=False)):\n torchaudio.save('vc_{}.wav'.format(i), j['tts_speech'], 22050)\n\ncosyvoice = CosyVoice('pretrained_models/CosyVoice-300M-Instruct')\n# instruct usage, support <laughter></laughter><strong></strong>[laughter][breath]\nfor i, j in enumerate(cosyvoice.inference_instruct('\u5728\u9762\u5bf9\u6311\u6218\u65f6\uff0c\u4ed6\u5c55\u73b0\u4e86\u975e\u51e1\u7684<strong>\u52c7\u6c14</strong>\u4e0e<strong>\u667a\u6167</strong>\u3002', '\u4e2d\u6587\u7537', 'Theo \\'Crimson\\', is a fiery, passionate rebel leader. Fights with fervor for justice, but struggles with impulsiveness.', stream=False)):\n torchaudio.save('instruct_{}.wav'.format(i), j['tts_speech'], 22050)\n```\n\n**Start web demo**\n\nYou can use our web demo page to get familiar with CosyVoice quickly.\nWe support sft/zero_shot/cross_lingual/instruct inference in web demo.\n\nPlease see the demo website for details.\n\n``` python\n# change iic/CosyVoice-300M-SFT for sft inference, or iic/CosyVoice-300M-Instruct for instruct inference\npython3 webui.py --port 50000 --model_dir pretrained_models/CosyVoice-300M\n```\n\n**Advanced Usage**\n\nFor advanced user, we have provided train and inference scripts in `examples/libritts/cosyvoice/run.sh`.\nYou can get familiar with CosyVoice following this recipie.\n\n**Build for deployment**\n\nOptionally, if you want to use grpc for service deployment,\nyou can run following steps. Otherwise, you can just ignore this step.\n\n``` sh\ncd runtime/python\ndocker build -t cosyvoice:v1.0 .\n# change iic/CosyVoice-300M to iic/CosyVoice-300M-Instruct if you want to use instruct inference\n# for grpc usage\ndocker run -d --runtime=nvidia -p 50000:50000 cosyvoice:v1.0 /bin/bash -c \"cd /opt/CosyVoice/CosyVoice/runtime/python/grpc && python3 server.py --port 50000 --max_conc 4 --model_dir iic/CosyVoice-300M && sleep infinity\"\ncd grpc && python3 client.py --port 50000 --mode <sft|zero_shot|cross_lingual|instruct>\n# for fastapi usage\ndocker run -d --runtime=nvidia -p 50000:50000 cosyvoice:v1.0 /bin/bash -c \"cd /opt/CosyVoice/CosyVoice/runtime/python/fastapi && python3 server.py --port 50000 --model_dir iic/CosyVoice-300M && sleep infinity\"\ncd fastapi && python3 client.py --port 50000 --mode <sft|zero_shot|cross_lingual|instruct>\n```\n\n## Discussion & Communication\n\nYou can directly discuss on [Github Issues](https://github.com/FunAudioLLM/CosyVoice/issues).\n\nYou can also scan the QR code to join our official Dingding chat group.\n\n<img src=\"./asset/dingding.png\" width=\"250px\">\n\n## Acknowledge\n\n1. We borrowed a lot of code from [FunASR](https://github.com/modelscope/FunASR).\n2. We borrowed a lot of code from [FunCodec](https://github.com/modelscope/FunCodec).\n3. We borrowed a lot of code from [Matcha-TTS](https://github.com/shivammehta25/Matcha-TTS).\n4. We borrowed a lot of code from [AcademiCodec](https://github.com/yangdongchao/AcademiCodec).\n5. We borrowed a lot of code from [WeNet](https://github.com/wenet-e2e/wenet).\n\n## Disclaimer\nThe 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.\n",
"bugtrack_url": null,
"license": "GPL-3.0",
"summary": "CosyVoice TTS with multilangual support",
"version": "0.0.8",
"project_urls": {
"Homepage": "https://github.com/lucasjinreal/CosyVoice"
},
"split_keywords": [
"deep learning",
" script helper",
" tools"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "cccb7ed03b5a2e941d70fbf165e5d2e5caeff88ea2bff2e822fc4e75437fc1d0",
"md5": "299b0d41cf77ac1563d797affa5a77a8",
"sha256": "c813467853dc5d25d011058dc6ee02fbfd079d6254e353c2fd57c71f9e826c5f"
},
"downloads": -1,
"filename": "cosyvoice-0.0.8.tar.gz",
"has_sig": false,
"md5_digest": "299b0d41cf77ac1563d797affa5a77a8",
"packagetype": "sdist",
"python_version": "source",
"requires_python": null,
"size": 25358,
"upload_time": "2024-11-17T07:41:52",
"upload_time_iso_8601": "2024-11-17T07:41:52.692756Z",
"url": "https://files.pythonhosted.org/packages/cc/cb/7ed03b5a2e941d70fbf165e5d2e5caeff88ea2bff2e822fc4e75437fc1d0/cosyvoice-0.0.8.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-11-17 07:41:52",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "lucasjinreal",
"github_project": "CosyVoice",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"requirements": [
{
"name": "conformer",
"specs": [
[
"==",
"0.3.2"
]
]
},
{
"name": "deepspeed",
"specs": [
[
"==",
"0.14.2"
]
]
},
{
"name": "diffusers",
"specs": [
[
"==",
"0.27.2"
]
]
},
{
"name": "gdown",
"specs": [
[
"==",
"5.1.0"
]
]
},
{
"name": "gradio",
"specs": [
[
"==",
"4.32.2"
]
]
},
{
"name": "grpcio",
"specs": [
[
"==",
"1.57.0"
]
]
},
{
"name": "grpcio-tools",
"specs": [
[
"==",
"1.57.0"
]
]
},
{
"name": "hydra-core",
"specs": [
[
"==",
"1.3.2"
]
]
},
{
"name": "HyperPyYAML",
"specs": [
[
"==",
"1.2.2"
]
]
},
{
"name": "inflect",
"specs": [
[
"==",
"7.3.1"
]
]
},
{
"name": "librosa",
"specs": [
[
"==",
"0.10.2"
]
]
},
{
"name": "lightning",
"specs": [
[
"==",
"2.2.4"
]
]
},
{
"name": "matplotlib",
"specs": [
[
"==",
"3.7.5"
]
]
},
{
"name": "modelscope",
"specs": [
[
"==",
"1.15.0"
]
]
},
{
"name": "networkx",
"specs": [
[
"==",
"3.1"
]
]
},
{
"name": "omegaconf",
"specs": [
[
"==",
"2.3.0"
]
]
},
{
"name": "onnxruntime-gpu",
"specs": [
[
"==",
"1.16.0"
]
]
},
{
"name": "onnxruntime",
"specs": [
[
"==",
"1.16.0"
]
]
},
{
"name": "openai-whisper",
"specs": [
[
"==",
"20231117"
]
]
},
{
"name": "protobuf",
"specs": [
[
"==",
"4.25"
]
]
},
{
"name": "pydantic",
"specs": [
[
"==",
"2.7.0"
]
]
},
{
"name": "rich",
"specs": [
[
"==",
"13.7.1"
]
]
},
{
"name": "soundfile",
"specs": [
[
"==",
"0.12.1"
]
]
},
{
"name": "tensorboard",
"specs": [
[
"==",
"2.14.0"
]
]
},
{
"name": "torch",
"specs": [
[
"==",
"2.0.1"
]
]
},
{
"name": "torchaudio",
"specs": [
[
"==",
"2.0.2"
]
]
},
{
"name": "wget",
"specs": [
[
"==",
"3.2"
]
]
},
{
"name": "fastapi",
"specs": [
[
"==",
"0.111.0"
]
]
},
{
"name": "fastapi-cli",
"specs": [
[
"==",
"0.0.4"
]
]
},
{
"name": "WeTextProcessing",
"specs": [
[
"==",
"1.0.3"
]
]
}
],
"lcname": "cosyvoice"
}
JSON
