Robust Speech Recognition via Large-Scale Weak Supervision https://github.com/openai/whisper

fish 2b1a9485e4 0 2 months ago
README.md 2b1a9485e4 0 2 months ago
loader_model.py 2b1a9485e4 0 2 months ago
main.py 2b1a9485e4 0 2 months ago
requirements.txt 2b1a9485e4 0 2 months ago

README.md

whisper

Robust Speech Recognition via Large-Scale Weak Supervision

多国语言语音识别以及翻译,可以识别嘈杂环境下各种声音,音乐的歌声,包括视频字幕生成。

sudo apt update && sudo apt install ffmpeg

pip install setuptools-rust
pip install -U openai-whisper

# mp3音频
whisper audio.flac audio.mp3 audio.wav --model medium

支持模型:

  • tiny
  • tiny.en
  • base
  • base.en
  • small
  • small.en
  • medium
  • medium.en
  • large
  • large-v2

Reference

https://github.com/openai/whisper