openai/whisper
General-purpose speech recognition and translation model
- Chart
- Not on a chart right now
- Stars
- 113k
What it is
Whisper is a general-purpose speech recognition model trained on a large dataset of diverse audio. A single Transformer sequence-to-sequence model handles multilingual speech recognition, speech translation, language identification, and voice activity detection.
Who it is for
Developers and researchers building transcription, subtitling, or speech translation into their applications use it.
Why it is trending
It gained 723 stars today, reaching 112,995 total stars, with its latest v20250625 release. It provides six model sizes from tiny to large and turbo alongside a CLI and Python API under the MIT license.
Main features
- Multilingual speech recognition and translation to English
- Automatic spoken language identification and voice activity detection
- Six model sizes including tiny, base, small, medium, large, and turbo
- Command-line interface and Python API for audio transcription
Summarized on November 18, 2026 from the README and repository data. It can be wrong; check the source before relying on it. Report a wrong summary