Whisper, faster-whisper and whisper.cpp

OpenAI's open speech-recognition model and faster re-implementations.

Intermediate

from faster_whisper import WhisperModel
for seg in WhisperModel("small").transcribe("talk.mp3")[0]:
    print(seg.start, seg.text)

Spotted a mistake or want to add detail? Suggest an improvement — Content Contributors' edits are reviewed by editors before they go live.

Discussion (0)