GoKawiilNvidia releases open-weight Nemotron 3.5 Transcribe speech model
Nvidia has launched Nemotron 3.5 Transcribe, an open-weight ASR model combining transcription, speaker diarization, translation and audio Q&A in one checkpoint, now available on Hugging Face and ModelScope. It transcribes 40 languages, translates 31 to or from English, identifies up to eight speakers across 13 languages, and handles recordings up to an hour long. Nvidia also released the Granary v2 training dataset and fine-tuning recipes via NeMo Speech tools to help developers adapt the model.