Whisper

Robust Speech Recognition via Large-Scale Weak Supervision, capable of transcribing and translating spoken language.

Whisper is built in Python, distributed under the MIT License license, 97.6k GitHub stars from 80 contributors, latest release v20250625.

Stats refreshed

Language
Python
Latest Release
v20250625
License
MIT License

Our Newsletter

Get new AI tools right in your inbox

Get short emails with useful ai projects, releases, and repos worth watching.


Key Features

  • High accuracy transcription
  • Supports multiple languages
  • Large-scale weak supervision
  • Scalable model architecture
  • Open-source

See open-source alternatives to Whisper

Community

Stars
97.6k
Contributors
80
Open Issues
119
Forks
12.0k