Can anyone recommend similar for removing ums etc. in videos? IIRC there is a workflow in some professional software, but being able to train and throw the algorithim right at the video itself (especially locally) would be useful.
For single camera floating head style videos where you're continuously talking about 1 topic it's going to be very jarring if you start cutting out filler words. You'll end up with a bunch of jump cuts where it looks like video frames are dropped.
That will change in Q2, when I add support for video.