Streaming models for speech-to-text, with VAD. Plus models include speaker segmentation and verification for cascaded diarization.
-
Client-side Speech Recognition with asr4all
🎙1Streaming speech recognition, in your browser
-
futo-org/asr4all-l
Automatic Speech Recognition • 97M • Updated • 669 • 5 -
futo-org/asr4all-m
Automatic Speech Recognition • 55.8M • Updated • 449 • 4 -
futo-org/asr4all-s
Automatic Speech Recognition • 28.2M • Updated • 647 • 3