ten-vad

Caution

Please see its license at

https://github.com/TEN-framework/ten-vad/blob/main/LICENSE

before you use it commercially.

如果你需要把它用于商业目的，请先阅读它的 协议 。

Our support of ten-vad uses https://github.com/TEN-framework/ten-vad/pull/36 as a reference, which use 0 for the pitch feature. It may degrade the performance, but it greatly simplifies the implementation.

Download models files

We have added some meta data to the original ten-vad.onnx, so please use the model files from the following table:

	Model size	Download URL
ten-vad.onnx	324 KB	Download
ten-vad.int8.onnx	126 KB	Download

If you use the model from https://github.com/TEN-framework/ten-vad/blob/main/src/onnx_model/ten-vad.onnx in sherpa-onnx, you will get runtime errors.

Note that ten-vad supports only 16k Hz samples.

Android examples

	Source	Pre-built APK URL
Pure VAD	Address	Download
VAD + non-streaming ASR	Address	Download
VAD + real-time ASR	Address	Download

For pure VAD, please see https://k2-fsa.github.io/sherpa/onnx/vad/apk.html and https://github.com/k2-fsa/sherpa-onnx/tree/master/android/SherpaOnnxVad

WebAssembly examples

	URL
Huggingface space	Address
ModelScope space	Address

Source code is available at https://github.com/k2-fsa/sherpa-onnx/tree/master/wasm/vad

For WebAssembly with VAD + ASR, please see https://github.com/k2-fsa/sherpa-onnx/tree/master/wasm/vad-asr

C API examples

Filename	Comment
vad-moonshine-c-api.c	ten-vad with moonshine for speech recognition with a very long file
vad-sense-voice-c-api.c	ten-vad with SenseVoice for speech recognition with a very long file
vad-whisper-c-api.c	ten-vad with Whisper for speech recognition with a very long file

For APIs of different programming languages, please see https://github.com/k2-fsa/sherpa-onnx