Better python example

[PavelPanjaya]

The current Python example only returns chunk indexes and probabilities, which makes it hard to test the VAD model end-to-end on an actual audio file.
It would be great to have a simple code snippet that takes an audio file as input and returns voice activity timestamps — something like:

speech_timestamps = get_speech_timestamps(wav, model...)

Silero VAD has great quick start examples:
https://github.com/snakers4/silero-vad

[Ziyi6]

Hi. We currently do not have plan to detect the voice activity timestamps of an audio file. I think it's just about smoothing of the VAD result and finding the start and end of the segment. We encourage developers to contribute the code for detection of the timestamps.