openai/whisper
Robust Speech Recognition via Large-Scale Weak Supervision
568 best points · 526 comments · 13 Hacker News posts · 112,137 GitHub stars · View on GitHub
Hacker News discussions
- Complete silence is always hallucinated as "ترجمة نانسي قنقر" in Arabic (568 points, 340 comments, by edent, 2025-07-22)
- OpenAI quietly launched Whisper V2 in a GitHub commit (335 points, 126 comments, by fudged71, 2022-12-06)
- OpenAI releases Whisper v3, new generation open source ASR model (117 points, 58 comments, by crakenzak, 2023-11-06)
- Whisper v3 (46 points, 1 comments, by samber, 2023-11-07)
- New OpenAI Whisper model: "turbo" (13 points, 1 comments, by GaggiX, 2024-10-01)
- OpenAI Whisper large-v3-turbo model release (7 points, 0 comments, by swyx, 2024-10-01)
- OpenAI released Whisper large-v3-turbo model (5 points, 0 comments, by stavepan, 2024-10-01)
- Ray: The Free AI media player app that generates and translates subtitles (3 points, 0 comments, by giamma, 2026-03-23)
- Robust Speech Recognition via Large-Scale Weak Supervision – OpenAI (2 points, 0 comments, by modinfo, 2023-01-18)
- WhisperClip: One-Click Audio Transcription UI (2 points, 0 comments, by mv, 2024-02-26)
- Introducing mWhisper-Flamingo for multilingual audio-visual speech recognition (2 points, 0 comments, by gwerbret, 2025-02-05)
- OpenAI Whisper (1 points, 0 comments, by tosh, 2022-12-06)
- OpenAI Whisper large-v3-turbo model release (1 points, 0 comments, by tech234a, 2024-10-02)