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.
- 100M-parameter open-weight model tracks up to eight overlapping speakers.
- One checkpoint covers offline use and streaming down to 0.32 seconds.
- It ranked first on initial Diarization-Bench at 14.72% DER.
- OpenMDW-1.1 permits commercial use through NVIDIA NeMo on NVIDIA GPUs.
- More than eight speakers, noise, or far-field audio raise errors.
- Vendors
- NVIDIA
- Products
- NeMo
- Organizations
- NVIDIAHugging FaceDavid AI
From the original article
4 min read at marktechpost.com
NVIDIA has released Nemotron 3 Diarization, an open-weight speaker diarization model on Hugging Face. It answers one question about any conversation: who spoke when. The 100M-parameter model tracks up to 8 speakers, including when voices overlap.
By Asif Razzaq · marktechpost.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.