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.

Total
0
Shares
Leave a Reply

Your email address will not be published. Required fields are marked *

Previous Post

Enterprises Are Shipping AI Code Faster: Are Your Release Controls Keeping Up?

Next Post

Conntour raises $7M from General Catalyst, YC to build an AI search engine for security video systems

Related Posts