NVIDIA's Nemotron-3-Diarization speaker separation model hits HF trending
nvidia · hf · 2026-09-24
NVIDIA's Nemotron-3-Diarization is trending on Hugging Face. It is an audio frame-classification model for streaming speaker diarization, built on the streaming-sortformer architecture and usable in a voice-activity-detection pipeline to tag speakers in real time. Weights ship in nemo format with safetensors, linked to paper arXiv:2409.06656.
Related event: NVIDIA Open-Sources Nemotron 3 Diarization, Tops Benchmark(16 posts)→
More from Models
- Microsoft research: editing fewer than 10 neurons backdoors any AI agent — DimitrisPapail · 2026-11-11
- Claude ported itself to AMD MI355X in ~3 days, work that took dozens of engineers 6-12 months — AnushElangovan · 2026-11-11
- Qwen4-Max Enters Preview With Stronger Coding and Agentic Capabilities — ChrisGPT · 2026-11-11
- Gemini 4 Carbon reportedly tops CV leaderboards in object detection and OCR, but is slow and costly — gabriberton · 2026-11-11
- Muse Ember sweeps Browser Use benchmark Pareto frontier at 3 cents per task — WenhuChen · 2026-11-11
- Interpretability researcher pleads with Anthropic to stop banning him; screenshot shows claude-opus-5-5 — Sauers_ · 2026-11-11