Cohere launches an open-source voice model specifically for...

partage un lien

2026-03-26 14:00:48

Cohere launches an open-source voice model specifically for transcription

Relatively light at just 2 billion parameters, the model is meant for use with consumer-grade GPUs for those who want to self-host it. It currently supports 14 languages.

0 Commentaires 0 Parts 31 Vue