Nvidia releases open-weight Nemotron 3.5 Transcribe speech model
Nvidia on Wednesday released Nemotron 3.5 Transcribe, a free open-weight model that transcribes audio in 40 languages, translates 31 of them to or from English, and tells up to eight speakers apart on recordings up to an hour long. The mixture-of-experts model has about 30 billion parameters with roughly 4 billion active, and runs on a single Nvidia chip from Jetson AGX Thor and DGX Spark up to Blackwell data-center GPUs. Nvidia says it tops open-weight models on Hugging Face's Open ASR Leaderboard. It works on recorded audio only, not livestreams. Nvidia also released Granary v2, its open speech dataset, with fine-tuning recipes for adapting the model to industry jargon.
Source: TechCrunch