VAD+ASR: Next-gen Kaldi
Click the Start button to play speech-to-text with Next-gen Kaldi.
\n
\n\n\n
The source code and pre-trained models are publicly available.
Please see https://github.com/k2-fsa/sherpa-onnx for details.
\n\n
Speech recognition with Next-gen Kaldi using VAD and non-streaming ASR models.
Start
Stop