Home › AI › Nvidia Releases Nemotron 3 Diarization
AI

Nvidia Releases Nemotron 3 Diarization Model

Hugging Face published details on a new 100M-parameter open-weight model ranked first on VoiceArena's Diarization-Bench leaderboard.

WHAT YOU NEED TO KNOW
  • NVIDIA Nemotron 3 Diarization is a 100M-parameter open-weight model.
  • The model achieved a 14.72% Diarization Error Rate on VoiceArena.
  • Support covers up to eight speakers across live and recorded conversations.

Hugging Face reported the launch of NVIDIA Nemotron 3 Diarization on September 23, 2026. The open-quist, 100M-parameter model classifies who spoke when in live and recorded conversations. It supports up to eight speakers across multiple languages.

The system ranked first on VoiceArena's Diarization-Bench leaderboard. It achieved a 14.72% Diarization Error Rate during evaluations. Earlier models like NVIDIA Streaming Sortformer established this approach for four-speaker diarization.

Model Architecture

Nemotron 3 Diarization accepts 16 kHz single-channel audio and converts it into Mel-spectrogram features. A 31-layer Transformer encoder processes 80 ms frames using rotary positional embeddings. The system uses an Arrival-Order Speaker Cache and a first-in, first-out queue during streaming inference.

Argmax added support for the model in Argmax Pro SDK 3. Baseten and Digital Ocean provide deployment options for production inference and scaling.

Xentir Media
Xentir Media NewsroomSource-backed AI and technology coverage, drafted by Xentir's automated editorial system under fixed human-set rules. See our editorial policy and AI usage policy.
J
Jomon · Founder & EditorFounder and editor of Xentir Media. Sets the editorial rules the newsroom system runs under, and is accountable for its corrections. About Jomon · [email protected]
The Xentir Brief
The developments worth knowing — one useful email.
Get the Brief →