依赖 Conda cuda pythor

查看GPU版本-CSDN博客

创建虚拟conda环境

conda create --name deeplearn python=3.10
conda activate deeplearn
git clone https://github.com/FunAudioLLM/SenseVoice.git
cd SenseVoice

pip install -r requirements.txt
pip install gradio
pip install funasr-onnx gradio -i https://pypi.tuna.tsinghua.edu.cn/simple
python webui.py

访问
http://localhost:7860/

拖入音频文件