CosyVoice_For_Windows

> 编程语言

开源

CosyVoice在Windows环境下使用的版本

767 stars0 点赞0 次浏览

访问官网 GitHub

工具介绍

CosyVoice在Windows环境下使用的版本

环境搭建

新版本比官方的更加激进，请确保本地安装 python3.11 版本，因为这个版本的性能有优化

并且确保安装最新的 cuda12.6 和 cudnn 9.4 ，以获得更快的推理速度

pip3 install -r requirements.txt

bash

pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu124

本地设备是 4060-laptop，飞一样的感觉。

启动接口服务

python3 api.py

url接口地址: http://localhost:9880/?text=测试测试，这里是测试&speaker=中文女

字幕文件地址:http://localhost:9880/file/output.srt

音频文件地址:http://localhost:9880/file/output.wav

CosyVoice

CosyVoice Demos

[CosyVoice Paper][CosyVoice Studio][CosyVoice Code]

For SenseVoice, visit SenseVoice repo and SenseVoice space.

Install

Clone and install

Clone the repo

bash

git clone --recursive https://github.com/v3ucn/CosyVoice_For_Windows.git
# If you failed to clone submodule due to network failures, please run following command until success
cd CosyVoice_For_Windows
git submodule update --init --recursive

Install Conda: please see https://docs.conda.io/en/latest/miniconda.html
Create Conda env:

bash

conda create -n cosyvoice python=3.11
conda activate cosyvoice
pip install -r requirements.txt -i https://mirrors.aliyun.com/pypi/simple/ --trusted-host=mirrors.aliyun.com

install deepspeed from https://github.com/S95Sedan/Deepspeed-Windows/releases/tag/v14.0%2Bpy311

pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu121

# when you in windows
no need to install sox

Model download

We strongly recommand that you download our pretrained CosyVoice-300M CosyVoice-300M-SFT CosyVoice-300M-Instruct model and speech_kantts_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-SFT', local_dir='pretrained_models/CosyVoice-300M-SFT')
snapshot_download('iic/CosyVoice-300M-Instruct', local_dir='pretrained_models/CosyVoice-300M-Instruct')
snapshot_download('speech_tts/speech_kantts_ttsfrd', local_dir='pretrained_models/speech_kantts_ttsfrd')

bash

# 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-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/speech_tts/speech_kantts_ttsfrd.git pretrained_models/speech_kantts_ttsfrd

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/AcademiCodec and third_party/Matcha-TTS to your PYTHONPATH.

bash

set PYTHONPATH=third_party/AcademiCodec;third_party/Matcha-TTS

…

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 speech_tts/CosyVoice-300M-SFT for sft inference, or speech_tts/CosyVoice-300M-Instruct for instruct inference
python3 webui.py --port 9886 --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.

bash

cd runtime/python
docker build -t cosyvoice:v1.0 .
# change speech_tts/CosyVoice-300M to speech_tts/CosyVoice-300M-Instruct if you want to use instruct inference
docker run -d --runtime=nvidia -p 50000:50000 cosyvoice:v1.0 /bin/bash -c "cd /opt/CosyVoice/CosyVoice/runtime/python && python3 server.py --port 50000 --max_conc 4 --model_dir speech_tts/CosyVoice-300M && sleep infinity"
python3 client.py --port 50000 --mode

Discussion & Communication

You can directly discuss on Github Issues.

You can also scan the QR code to join our officla Dingding chat group.

Acknowledge

We borrowed a lot of code from FunASR.
We borrowed a lot of code from FunCodec.
We borrowed a lot of code from Matcha-TTS.
We borrowed a lot of code from AcademiCodec.
We borrowed a lot of code from 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.