openai-whisper ☆
« Back to VersTracker
Description:
General-purpose speech recognition model
Type: Formula  |  Latest Version: 20250625@2  |  Tracked Since: Dec 10, 2025
Links: Homepage  |  GitHub  |  @OpenAI  |  formulae.brew.sh
Stars: 92,427  |  Forks: 11,579  |  Language: Python  |  Category: Ai ml
Tags: speech-recognition ai transcription python machine-learning
Install: brew install openai-whisper
About:
OpenAI Whisper is a state-of-the-art automatic speech recognition (ASR) system trained on a massive, diverse dataset of multilingual and multitask supervised data. It enables robust transcription and translation from speech to text, handling various accents, background noise, and technical language with high accuracy.
Key Features:
  • Multilingual speech recognition
  • Speech translation to English
  • Robust performance in noisy environments
  • Support for multiple model sizes (tiny to large)
  • Open-source and locally runnable
Use Cases:
  • Transcribing podcasts, meetings, and interviews
  • Adding subtitles or captions to video content
  • Real-time speech-to-text for applications
Alternatives:
  • vosk – Offline, lightweight ASR with a focus on embedded and real-time use, but generally less accurate than Whisper for diverse audio.
  • nvidia-nemo – Enterprise-grade ASR toolkit with extensive customization and training capabilities, but more complex to deploy than Whisper.
Version History
Detected Version Rev Change Commit
Dec 20, 2025 11:37pm 20250625 2 VERSION_BUMP 75250d0e
Dec 10, 2025 5:34am 2 VERSION_BUMP 58c9c295
Nov 26, 2024 1:56pm 1 VERSION_BUMP 24afa54e
Nov 18, 2024 10:37am 1 VERSION_BUMP 64f62b37
Nov 17, 2024 7:51pm 1 VERSION_BUMP cfeb3ecb
Sep 28, 2024 5:50pm 0 VERSION_BUMP 0c71ba9e
Sep 28, 2024 12:25pm 0 VERSION_BUMP 396d023d
« Back to VersTracker  |  Browse Packages  |  About