Search papers, labs, and topics across Lattice.
3
0
4
1
Real-time speaker-attributed ASR is now feasible with VibeVoice-ASR-Streaming, achieving unmatched accuracy while processing speech on-the-fly.
Achieving real-time ASR performance on edge devices, VibeVoice-ASR-BitNet outpaces Whisper.cpp by up to 2.3x while only modestly sacrificing accuracy.
Strong translation quality doesn't guarantee high speech or temporal fidelity, revealing critical gaps in existing evaluation practices for speech translation systems.
