Nvidia releases Nemotron 3.5 Transcribe and Granary v2
The open-weight model handles up to 40 languages and can be customized for industry jargon.
Models#06
40
languages transcribed by the open model
Image: Hugging Face
40languages transcribed by the open model
The short version
- Nvidia released Nemotron 3.5 Transcribe, a free, open-weight model that transcribes audio in up to 40 languages.
- The company also released version 2 of Granary, its open source speech dataset.
- Nvidia says the model can translate 31 languages to and from English, handle recordings up to an hour long, and tell up to eight speakers apart.
- The model has 30 billion parameters and can run on a single chip, from Jetson AGX Thor to Blackwell datacenter chips.
Why it matters
The tools target developers building apps for business meetings and medical transcription. Developers can use the model, the updated Granary dataset, and NeMo Speech tools to adapt recognition to industry jargon in each language. Transcribe works with recorded audio, not livestreams.
“One drawback: Transcribe works with recorded audio, not livestreams.”