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.
schedule
13:30
visibility
84 views
Source: TechCrunch
Read original article →
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.
Al Jazeera 
