RVC文本到语音WebUI
这是使用Edge-TTS的文本到语音级别WebUI。
?在线演示
这可以在没有GPU（但慢）的CPU上运行。
安装
要求：在Windows 11上对Python 3.10进行测试。可能不支持Python 3.11，因此请使用Python 3.10。
git clone https://gith*u*b*.com/litagin02/rvc-tts-webui.git
cd rvc-tts-webui
# Download models in root directory
curl -L -O https://*hug**gingface.co/lj1995/VoiceConversionWebUI/resolve/main/hubert_base.pt
curl -L -O https://hug**gi*ngface.co/lj1995/VoiceConversionWebUI/resolve/main/rmvpe.pt
# Make virtual environment
python -m venv venv
# Activate venv (for Windows)
venv \S cripts \a ctivate
# Install PyTorch manually if you want to use NVIDIA GPU (Windows)
# See https://pytorch*.**org/get-started/locally/ for more details
pip install torch torchvision torchaudio --index-url https://download.*p*y*torch.org/whl/cu118
# Install requirements
pip install -r requirements.txt找到RVC型号
如下：将RVC型号放在weights/目录中：
weights
├── model1
│ ├── my_model1.pth
│ └── my_index_file_for_model1.index
└── model2
├── my_model2.pth
└── my_index_file_for_model2.index
...每个模型目录应完全包含一个.pth文件和最多一个.index文件。目录名称用作模型名称。
看来路径名中的非ASCII字符似乎会产生faiss错误（例如weights/モデル1/index.index ），因此请避免使用它们。
发射
# Activate venv (for Windows)
venv \S cripts \a ctivate
python app.py更新
git pull
venv \S cripts \a ctivate
pip install -r requirements.txt --upgrade故障排除
error: Microsoft Visual C++ 14.0 or greater is required. Get it with "Microsoft C++ Build Tools": https://visualstudio.m**icro*soft.com/visual-cpp-build-tools/
[end of output]
note: This error originates from a subprocess, and is likely not a problem with pip.
ERROR: Failed building wheel for fairseq
Failed to build fairseq
ERROR: Could not build wheels for fairseq, which is required to install pyproject.toml-based projects
也许FairSeq需要Microsoft C ++构建工具。下载安装程序并安装。
下载源码
通过命令行克隆项目:
git clone https://github.com/litagin02/rvc-tts-webui.git