TNW | Artificial-intelligence
Nvidia releases an open speech model that transcribes 40 languages
Nemotron 3.5 Transcribe can also translate, label speakers and answer questions about audio, and is free for commercial use.
By TNW | Artificial-intelligence
Excerpt shared by Lazyfounder
·Excerpt
Nvidia released Nemotron 3.5 Transcribe, an open-weight model that transcribes 40 languages, translates 31 and labels up to eight speakers in recordings of up to an hour. It came with Granary v2, a free dataset of 463,062 hours of speech in 48 languages.
Nvidia has released Nemotron 3.5 Transcribe, a free, open-weight AI model that turns speech into text in 40…
Courtesy
This story was originally published by TNW | Artificial-intelligence. All rights belong to the original publisher.
Read the original on thenextweb.com ↗