NVIDIA Releases Nemotron 3 Diarization: A 100M-Parameter Open-Weight Model That Tracks 8 Speakers in Real Time
NVIDIA released Nemotron 3 Diarization, a 100M open-weight model tracking up to eight overlapping speakers.
NVIDIA released Nemotron 3 Diarization, a 100-million-parameter open-weight speaker diarization model on Hugging Face under the OpenMDW License 1.1, which permits commercial use. One checkpoint tracks up to eight speakers, including overlapping speech, for both offline recordings and real-time streaming, doubling the four-speaker limit of Streaming Sortformer. On Voice Arena’s initial Diarization-Bench of 139 English conversations totaling about 22 hours, it ranked first among 12 systems with 14.72% DER versus 19.3% for the next system. It runs through NVIDIA NeMo on Ampere, Ada Lovelace, Hopper, or Blackwell GPUs; more than eight speakers, heavy noise, or far-field audio can raise error rates.