Nvidia releases Nemotron 3.5 Transcribe, an open-weights speech model

Nvidia released Nemotron 3.5 Transcribe, an open-weights speech transcription model supporting 40 languages with roughly 4.3 billion active parameters. Nvidia says it ranks first among open-weight models on Hugging Face's English transcription leaderboard. The model tracks individual speakers even when they talk over each other.