←Back to NewsAI News/AudionewsAudioOpen SourceNVIDIA's Nemotron 3 Beats 12 Rivals With a 14.72% Speaker Error RateNVIDIA's 100M-parameter Nemotron 3 Diarization tracks up to 8 speakers in overlapping conversations, topping Voice Arena's benchmark with 14.72% DER.SourceNVIDIA AIPublishedSep 23, 2026, 3:02 PMAuthorAlphaSignal NewsroomRead1 min readNVIDIA's 100M-parameter Nemotron 3 Diarization tracks up to 8 speakers in overlapping conversations, topping Voice Arena's benchmark with 14.72% DER.Reporting is indexed from AlphaSignal. Rights remain with the original publisher and cited sources.Read original report ↗Next readsTencent Hy · repoTencent's AuK Handles 16 Audio Tasks From a Single PromptTencent Hy · newsTencent's AuK Replaces 16 Speech Tools With One Open-Source ModelAlphaSignal · modelYuE2-3B Beats Suno Generating Editable Full Songs on a Single GPU
