distil-whisper
Distilled variant of Whisper for speech recognition. 6x faster, 50% smaller, within 1% word error rate.
Recognize speech quickly and accurately using a smaller, faster version of the Whisper model.
Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.
Get an email alert on its next release or when it starts trending — never miss the moment.
Free · no card · unsubscribe anytimeDistilled variant of Whisper for speech recognition. 6x faster, 50% smaller, within 1% word error rate.
distil-whisper has 4.1k stars on GitHub. It has been forked 353 times. distil-whisper is written mainly in Python. It has been in active development since 2023. distil-whisper is available under the MIT license. Its main topics are audio, speech-recognition, whisper.
What is distil-whisper?
Distilled variant of Whisper for speech recognition. 6x faster, 50% smaller, within 1% word error rate.
Is distil-whisper open source?
distil-whisper is an open-source project. It is released under the MIT license.
Is distil-whisper free?
Yes. distil-whisper is free and open source — you can use, modify and self-host it.
What license does distil-whisper use?
distil-whisper is available under the MIT license.
What language is distil-whisper written in?
distil-whisper is written mainly in Python.
Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.
[](https://olud.ai/project/huggingface-distil-whisper.html)
Measured from GitHub topics shared by both projects, weighted by how rare each topic is.