10, 20, 30ms VAD model

[siriusht]

❓ Questions and Help

The VAD model used in your example is based on 64ms.
there are two questions:

1. Can I input 10ms or 20ms or 30ms audio data into this model?
2. Could you please share 30ms model?
3. Does it support speech language Chinese?

[snakers4]

Hi,

Can I input 10ms or 20ms or 30ms audio data into this model?
Could you please share 30ms model?

The preferred chunk sizes are described here:

silero-vad/utils_vad.py

Lines 205 to 208 in 563106e

	window_size_samples: int (default - 1536 samples)
	Audio chunks of window_size_samples size are fed to the silero VAD model.
	WARNING! Silero VAD models were trained using 512, 1024, 1536 samples for 16000 sample rate and 256, 512, 768 samples for 8000 sample rate.
	Values other than these may affect model perfomance!!

Does it support speech language Chinese?

It should be language agnostic, and I believe Chinese was in the train dataset, albeit a small amount of data.

[siriusht]

I got it, thanks.