Nvidia's new 100M-parameter model tracks eight speakers and tops a diarisation ranking

T2Covered by 1 source · first reported by UploadVR / Road to VR / MIXED at 28 Sept, 13:54 UTC

Nvidia has published Nemotron 3 Diarization, an open-weight model of 100 million parameters that works out who is speaking when, and it handles up to eight speakers where the Nvidia checkpoint it is measured against stopped at four. In VoiceArena's first Diarization-Bench results it ranked first…

hardwareiottelecomxr

Sources

• T2Nvidia's new 100M-parameter model tracks eight speakers and tops a diarisation rankingUploadVR / Road to VR / MIXED28 Sept, 13:54