NVIDIA ships Nemotron-3-Diarization: 8 speakers, 21 languages, 15000 RTFx, top-ranked
kuchaev · x · 2026-09-25
NVIDIA's team released Nemotron-3-Diarization, the top-ranked speaker diarization model on Voice Arena Diarization.
Key specs:
- Supports up to 8 speakers across 21 languages
- Speeds up to 15000 RTFx
- Works offline and online, with variable latency down to 0.32s
- Licensed for both commercial and non-commercial use
Related event: NVIDIA Open-Sources Nemotron 3 Diarization, Tops Benchmark(16 posts)→
More from Multimodal
- Simulating a drop of blood with Gemini 4 Carbon and Antigravity Science skills — AI_Andrew · 2026-11-11
- Dev ports POE2's radiance cascade technique for dramatic voxel city lighting — mflux · 2026-11-11
- AI a cappella fix: swap vowel from 'a' to 'o' to tame the high notes — rickasaurus · 2026-11-11
- MiniMax H3 Image day-one tips: one checkpoint for t2i and edits — ggbro_itsover · 2026-11-11
- MiniMax H3-Image tested: 8.41MP images in ~35s on a 16GB GPU — mininuvixi · 2026-11-11
- Martine benchmark debuts for multi-view 3D surface reconstruction across viewpoints and lighting — ssh4net · 2026-11-11