speech_to_text / requirements.txt
GoodResearch's picture
Upload 2 files
a52af1d verified
raw
history blame contribute delete
180 Bytes
gradio==4.29.0
git+https://github.com/openai/whisper.git
ffmpeg-python
setuptools-rust
# PyAnnote 音频说话人分离(推荐 pin 版本)
pyannote.audio>=2.1.1
soundfile