NVIDIA Nemotron 3.5 Transcribe adds multilingual transcription, speaker attribution and audio Q&A as open model
NVIDIA Nemotron 3.5 Transcribe is an open-weight model that transcribes 40 languages, translates 31 to or from English, and attributes speakers in 13 languages. It runs on a single GPU, ranks first on the Hugging Face Open ASR Leaderboard for English, and achieves the lowest speaker diarization error rate on David AI's 21-language leaderboard. Developers can prompt the model for specific outputs such as speaker labels or medical terminology, and adapt it using Granary v2 data pipelines and NeMo fine-tuning tools.
The release combines transcription, translation, speaker attribution and audio question-answering in a single promptable model, offering developers a flexible open-weight alternative to proprietary systems while providing tools to adapt the model to domain-specific vocabularies.
Source: Hugging Face Blog · huggingface.co