Whisper
lastmod 2026-07-02created 2022-09-2314 edits
A multilingual automatic speech recognition (ASR) system released as open source by OpenAI
Features
- Reaches human-level accuracy in English speech recognition
- Trained on 680,000 hours of multilingual data
- A large and diverse dataset improves robustness to accents, background noise, and technical language
Categories
- yt-whisper - Tool that generates subtitles for YouTube videos with OpenAI Whisper
- WhisperX - Whisper-based ASR with improved timestamp accuracy
- transcribe-anything - Making subtitles with OpenAI Whisper
- Whisper.cpp - High-performance C/C++ implementation of OpenAI Whisper
- Universal Speech Model - Model for speech recognition in every language (Google)
- Cheetah - Open-source AI assistant for remote interviews
- DeepSpeed Chat - Framework for training ChatGPT-like models with RLHF
- Subs AI - Automatically generating video subtitles with OpenAI Whisper
- Whispering - Open-source speech transcription app
- faster-whisper
- meeting_minutes_pipeline.py
- whisper-diarization
See also
Documentation
- Robust Speech Recognition via Large-Scale Weak Supervision
- https://cdn.openai.com/papers/whisper.pdf