Skip to content

Instantly share code, notes, and snippets.

@wenboown

wenboown/whisper-diarization-notes.md

Last active November 23, 2025 02:42
Show Gist options

  • Select an option

    Learn more about clone URLs
  • Save wenboown/08b2e8aa63ec72ec24d5d491b0467d94 to your computer and use it in GitHub Desktop.

Select an option

Learn more about clone URLs
Save wenboown/08b2e8aa63ec72ec24d5d491b0467d94 to your computer and use it in GitHub Desktop.
Download ZIP
whisper-diarization
Raw
whisper-diarization-notes.md

need to install FFmpeg and Cython on the system

RHEL 9

  1. need to install cuda and set path properly
  2. need to install a proper working Perl version for the https://github.com/isi-nlp/uroman to work.
  3. need to use Python > 3.10

use the Turbo model:

It is supported, use "deepdml/faster-whisper-large-v3-turbo-ct2" as the model name (ref: MahmoudAshraf97/whisper-diarization#238 (comment))

python diarize.py --whisper-model deepdml/faster-whisper-large-v3-turbo-ct2 -a AUDIO_FILE_NAME
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment