yinruiqing/pyannote-whisper
A Python tool that runs OpenAI Whisper for speech-to-text and pyannote.audio for speaker diarization, outputting transcripts with speaker labels and timestamps.

The project integrates Whisper, an automatic speech recognition model, with pyannote.audio, a speaker diarization pipeline, into a unified transcription workflow. Users can run it via command line or import it as a Python module. The output pairs transcribed sentences with identified speakers and their corresponding time segments, making it suitable for meeting summarization and multi-speaker transcription tasks.
Frequently asked
- What is yinruiqing/pyannote-whisper?
- A Python tool that runs OpenAI Whisper for speech-to-text and pyannote.audio for speaker diarization, outputting transcripts with speaker labels and timestamps.
- Is pyannote-whisper open source?
- Yes — yinruiqing/pyannote-whisper is an open-source project tracked on heatdrop.
- What language is pyannote-whisper written in?
- yinruiqing/pyannote-whisper is primarily written in Python.
- How popular is pyannote-whisper?
- yinruiqing/pyannote-whisper has 675 stars on GitHub.
- Where can I find pyannote-whisper?
- yinruiqing/pyannote-whisper is on GitHub at https://github.com/yinruiqing/pyannote-whisper.