Speaker Diarization 3.1
Speaker Diarization 3.1 by pyannote: a free, openly licensed speech recognition model on Hugging Face (MIT).
FreeOpen source
What you get
Speaker Diarization 3.1 is an open speech recognition model published on Hugging Face by pyannote.
Task: speech recognition
License: MIT (free to use, check the model card for conditions)
Likes on Hugging Face: 4,535
Downloads last month: 6,844,269
How to use it: open the model page on Hugging Face, read the model card and try it with the Transformers library, Ollama, or a hosted inference provider. HEEEXY lists trending open models in the Lab.
More for speech recognition
- Speaker Diarization Community 1: Speaker Diarization Community 1 by pyannote: a free, openly licensed speech recognition model on Hugging Face (CC-BY-4.0).
- Whistle: Whistle by Cactus-Compute: a free, openly licensed speech recognition model on Hugging Face (APACHE-2.0).
- Phonon 2: Phonon 2 by FermionResearch: a free, openly licensed speech recognition model on Hugging Face (CC-BY-4.0).