CosyVoice2.0-Windows系统安装指南

CosyVoice2.0-Windows系统安装指南

安装说明

  1. 安装教程地址 Window安装教程
  2. 请确保已安装 CONDA
  3. 请确保已安装 GIT
  4. 请确保已安装 FFMPEG
  5. 请确保已安装 cuda>=12.1 cuDNN
  6. 整合包下载 点击下载
# 克隆代码 提示警告 按回车仍然粘贴 克隆后直接切换到项目目录
git clone --recursive https://github.com/FunAudioLLM/CosyVoice.git cd CosyVoice
# 初始化模块
git submodule update --init --recursive
# 创建并激活虚拟环境-默认路径C盘
conda create -n cosyvoice -y python=3.10 conda activate cosyvoice
# 创建并激活虚拟环境-指定路径 E:/your_path 👉 替换为你想要存放环境的实际路径，wzf（新建文件夹）
conda create --prefix E:/your_path/wzf python=3.10 conda activate E:/your_path/wzf
# 安装 pynini
conda install -y -c conda-forge pynini==2.1.5
# 安装PyTorch
conda install pytorch==2.3.1 torchvision==0.18.1 torchaudio==2.3.1 pytorch-cuda=12.1 -c pytorch -c nvidia
# 安装依赖
pip install -r requirements.txt -i https://mirrors.aliyun.com/pypi/simple/ --trusted-host=mirrors.aliyun.com
# 下载模型，请确保已安装git lfs
choco install git-lfs git lfs install mkdir -p pretrained_models git clone https://www.modelscope.cn/iic/CosyVoice2-0.5B.git pretrained_models/CosyVoice2-0.5B 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
# 启动程序
python webui.py --port 50000 --model_dir pretrained_models/CosyVoice2-0.5B python webui.py --port 50000 --model_dir pretrained_models/CosyVoice-300M python webui.py --port 50000 --model_dir pretrained_models/CosyVoice-300M-SFT python webui.py --port 50000 --model_dir pretrained_models/CosyVoice-300M-Instruct