FICHA · MANJARO

python-openai-whisper

Robust speech recognition via large-scale weak supervision

  • Library
  • Dev
  • AUDIO
  • SCIENCE
  • Dependency only
official+codex · reviewed · May 28, 2026 description in en

Description

Provides Whisper speech-recognition models and tooling for transcribing or translating audio with Python. It helps applications process recordings, media files, captions, and voice datasets.

Audio can contain private conversations or identifiable voices, and transcripts can be wrong. Get appropriate permission, protect recordings, and review text before relying on it.

Permissions

Permissions not analysed for this source yet.