Will this detect the speech segments in any scenario?

[StanSilas]

In case I have an audio with
tring_tring ... hold music... speaker_1 ... speaker_2 ... ... speaker_1 .... hold_music end_of_conversation.

If I were to pass the above above audio to this library,
Will this library ignore all music and extract just the speaker_1 speaker_2 segments?
If so how is this to be accomplished?

[wiseman]

I think there's a good chance it will work, as long as the hold music doesn't contain singing or other speech.

You can try it by running the example.py script and giving it a sample audio file.