Wav2Vec2-BERT STT

Wav2Vec2-BERT speech-to-text inference server.
Server status: checking…

  

REST upload (audio ≤ 15s)


  

WebSocket live streaming

disconnected

VAD segments speech into utterances. Partials update every ~1 s while you speak; a final is emitted when you pause (or on Stop & finalize) and is run through the denoiser before transcription.

Partial:

    
Final: