MOSS-Audio Collection An open-source audio understanding model supporting speech recognition, environmental sound analysis, music understanding, time-aware QA, and complex • 7 items • Updated 30 days ago • 61
mrfakename/Qwen3-ASR-Enhanced-v0.1 Automatic Speech Recognition • 2B • Updated 27 days ago • 243 • 11
CohereLabs/cohere-transcribe-03-2026 Automatic Speech Recognition • 2B • Updated 3 days ago • 313k • 967
BreezeASR Collection Automatic Speech Recognition models of the Breeze family • 3 items • Updated Apr 16 • 2
Running on Zero Agents Featured 139 Qwen3-ASR Demo 🎙 139 Transcribe audio to text with timestamps and visualization