#Tag (5)

Waterfall Pagination

Microsoft's open-source VibeVoice-ASR: one pass over a 60-minute meeting yields speakers, timestamps and content; 54k GitHub stars

Microsoft's open-source VibeVoice-ASR: one pass over a 60-minute meeting yields speakers, timestamps and content; 54k GitHub stars

@axichuhai · 106 views · 2026-09-30

Voice InteractionASROpen Source

Audio8 ASR Infinite: rolling KV cache enables 24/7 drift-free streaming ASR (Apache 2.0)

Audio8 ASR Infinite: rolling KV cache enables 24/7 drift-free streaming ASR (Apache 2.0)

@_akhaliq · 137 views · 2026-09-30

Audio8 ASR InfiniteStreaming ASRRolling KV Cache

Fish Audio upgrades its ASR model: speaker identification and inline emotion cues such as [laughter]

Fish Audio upgrades its ASR model: speaker identification and inline emotion cues such as [laughter]

@FishAudio · 338 views · 2026-09-28

ASRSpeech RecognitionEmotion Recognition

Nemotron 3 Diarization tested: 100M-param real-time speaker diarization, better than expected locally

Nemotron 3 Diarization tested: 100M-param real-time speaker diarization, better than expected locally

@ouchi · 211 views · 2026-09-27

NVIDIANemotron 3Speaker Diarization

JEV-Speech: Same 24-Layer Encoder, 2.18x Faster Inference

JEV-Speech: Same 24-Layer Encoder, 2.18x Faster Inference

@nrol_ling · 260 views · 2026-09-22

Speech RecognitionInference OptimizationLatency