Model reference · open weights

speaker-diarization

speaker-diarization is an open-weight audio or speech model from pyannote.

For self-hosting, compare this build's requirements below with the GPU you plan to rent.

• The speaker-diarization model is an open-source pipeline by pyannote for automatic speaker segmentation in audio.
• It is licensed under the MIT license and relies on pyannote.audio version 2.1.1.
• The pipeline processes audio to identify speakers and can accept parameters for the expected number of speakers.

Summary of the pyannote/speaker-diarization model card, 2026-10-01

Hugging Face ↗Paper ↗