Great work! Kudos to NVIDIA. Many real scenarios, like press conferences or earnings calls, usually have more than 8 speakers. I'm looking forward to updates that handle streaming diarization for a higher number of speakers.
Muhammad Ali Abbas
m-aliabbas1
AI & ML interests
NLP, Computer Vision, Reinforcement Learning
Recent Activity
commentedon an article 6 days ago
**Know Who Spoke When: Build Real-Time, Multi-Speaker AI with NVIDIA Nemotron 3 Diarization** commentedon an article 9 months ago
Building Deep Research: How we Achieved State of the Art