theaicatalog
Hugging Face ยท Models

NVIDIA releases open Nemotron 3.5 Transcribe speech model

NVIDIA has released Nemotron 3.5 Transcribe, an open-weight speech model that transcribes recordings, labels speakers, translates speech, and answers questions about audio. The model handles 40 languages, translates 31 of them to or from English, and labels up to eight speakers in recordings up to an hour long. NVIDIA says it ranks first among open-weight models on the Hugging Face Open ASR Leaderboard for English and processes 100 hours of audio in under three minutes on one RTX PRO 6000 Blackwell GPU. NVIDIA also released Granary v2, a multilingual speech dataset of 463,062 hours across 48 languages, with a curation pipeline and fine-tuning tools.