Nvidia releases free Nemotron 3 Diarization model for real-time speaker identification
The model weights are freely available and can process both recordings and live audio streams. It detects overlapping speech and works with adjustable audio buffers ranging from 30.4 down to 0.32 seconds, though shorter buffers reduce accuracy.
Key points
- Identifies up to eight speakers in real time with 14.72% error rate on Diarization-Bench
- Cuts error rate by 41% average versus Streaming Sortformer across eight scenarios
On the Diarization-Bench from VoiceArena, the model achieves a 14.72 percent error rate, placing it first ahead of the next best system at 19.3 percent. The benchmark counts overlapping speech and small misalignments at speaker transitions as errors. Compared to its predecessor Streaming Sortformer, Nemotron 3 Diarization cuts the error rate by an average of 41 percent across eight test scenarios using a 1.04-second buffer. When paired with a speech recognition system like Parakeet, it can produce transcripts with anonymous speaker labels.
The story so far
2 episodes →- Nvidia releases free Nemotron 3 Diarization model for real-time speaker identificationthis story
Nvidia drops a free 100M-parameter model that identifies up to eight speakers in real time
The Decoder · 27 September 2026
Loading the full article…
This text was published by The Decoder and written by Jonathan Kemper. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Generative AI & Models
All →- Apiiro finds 1,122 public GitHub files with secrets saved by Claude Code · 1 src
- Thinking Machines releases Inkling 2 Small, a 594B MoE model with 17B active parameters · 8 src
- OpenAI releases GPT-6 Cyber, a Critical-rated model that outperforms predecessors in vulnerability detection and alignment · 25 src
- Google releases Gemini Omni 1.2 Flash with 15-second video generation and 30% price cut to $0.07 per second · 10 src
- US accuses Chinese executive of allegedly sharing Nvidia chip info with Beijing · 11 src
Comments
via GitHub Discussions