MODELS
pyannote/speaker-diarization-3.1
by pyannote
Overview
pyannote/speaker-diarization-3.1 is a Hugging Face-hosted speaker diarization pipeline from pyannote, with usage documented via pyannote.audio and Pipeline.from_pretrained.
Details
pyannote/speaker-diarization-3.1 is a model entry hosted on Hugging Face under the pyannote publisher. The supplied sources identify pyannote.audio as the official open-source Python toolkit for speaker diarization, with pretrained models and pipelines hosted on Hugging Face. A pyannote GitHub mirror for hf.co/pyannote/speaker-diarization-3.1 documents the 3.1 pipeline requirements and usage through Pipeline.from_pretrained.
When to Use
Use when evaluating a pyannote speaker diarization pipeline hosted on Hugging Face. Use when building workflows around the official pyannote.audio Python toolkit and its pretrained pipelines. Use when you need source-backed review of the pyannote/speaker-diarization-3.1 model entry before adopting it.
Getting Started
- Open the Hugging Face model page for pyannote/speaker-diarization-3.1.
- Review the pyannote/hf-speaker-diarization-3.1 mirror README for requirements and Pipeline.from_pretrained usage.
- Review the official pyannote/pyannote-audio repository for the toolkit context and pipeline documentation.
- Run a small trial before relying on the pipeline in production.
Key Features
- •Speaker diarization pipeline published by pyannote on Hugging Face.
- •Uses pyannote.audio, described by the official repository as an open-source Python toolkit for speaker diarization.
- •Pretrained models and pipelines are hosted on Hugging Face according to the official pyannote.audio repository metadata.
- •The dedicated GitHub mirror documents speaker-diarization-3.1 requirements and Pipeline.from_pretrained usage.
Capabilities
- •speaker-diarization
- •pretrained-pipeline
- •python-toolkit
- •hugging-face-model
Last updated Jun 4, 2026