Skip to main content

Diarization Model Selection

Feature Request

I would love to see other ways of automatically diarizing the transcripts. The current implementation works if the audio is great, however there are other approaches existing already (e.g., https://huggingface.co/nvidia/diar_sortformer_4spk-v1). It would be nice to be able to switch between models, similar to the way one can switch the models for transcribing locally.

Posted by L-Ter ·
Status: In Progress2 comments

Log in to comment and vote

Comments2

  • Anton

    Team•

    Feb 16

    Thanks for you suggestion. We are actually working on adding sortformer to QuickWhsiper right now. You can expect it to be available in the next couple releases.

    • L-Ter

      •

      Feb 16

      That is great! Looking forward to testing it. Thank you for your effort :)