NVIDIA releases Nemotron 3 Diarization model handling up to 8 overlapping speakers with 100M params
NVIDIAAI · x · 2026-09-23
NVIDIA's new Nemotron 3 Diarization model tracks who spoke when, even with overlapping voices. It supports up to eight speakers, has only 100M parameters, and is now available on Hugging Face.
More from Models
- Xiaomi MiMo-V2.6 open release tops open-source models with AA index score of 46 — inductionheads · 2026-09-23
- "Don't trust benchmarks" is no excuse when 99% of them show zero improvement or regression — Angaisb_ · 2026-09-23
- Gemini 3.8 Flash TTS priced at $32.98/1M chars, pricier than its predecessor — ArtificialAnlys · 2026-09-23
- 214 API calls later: Ling-3.0-flash-VL spots a 30-yuan receipt error and shines on video detail — alifcoder · 2026-09-23
- Audio8 ASR Infinite open-sourced: ultra-low latency 24/7 streaming ASR with no drift — TheMoonMidas · 2026-09-23
- 'Intelligence will get cheaper'? Devs mock rising AI subscription bills — zeeg · 2026-09-23