Uses wavekat-vad, a Rust library that provides a unified interface for multiple VAD backends including FireRedVAD. The FireRedVAD ONNX model and CMVN stats are downloaded and embedded in the binary at compile time — no manual model setup needed.
- Pure Rust Mel filterbank + CMVN preprocessing (no C dependencies for audio features)
- Automatic resampling from any sample rate to 16kHz
FrameAdapterhandles frame buffering (feed any chunk size, get correctly sized 10ms frames)- Works with any WAV file format (mono/stereo, any sample rate)
cargo run -- /path/to/audio.wavSample output:
File: audio.wav (16000Hz, 1ch, 16bit)
Duration: 3.50s (56000 samples at 16000Hz)
FireRedVAD — frame: 160 samples (10ms)
0ms 0.000
10ms 0.000
20ms 0.012
30ms 0.008
40ms 0.245
50ms 0.876 ################################### SPEECH
60ms 0.923 #################################### SPEECH
...