Separation with sound event time stamps

Hi ! First of all, thank you for your great tools. I have a question, is there a way to separate audio events with accompanying timestamps? Thank you very much !

The issue does not name any files, tests, models, or entry points. Start by locating the toolkit's source-separation pipeline and checking whether it exposes event timestamps; done would require a defined way to separate audio events while preserving accompanying timestamps.

Written by the indexing model from the issue text.