Looks real nice. I'll be using it. If you could map spacebar to pause/unpause the video by default (without focusing on the YouTube window first) that would be great.
Every video is transcribed to get much better transcripts than the closed captions. I filter on high quality transcripts, and afterwards a LLM selects only plausible segments for the exercises. This seems to work well for quality control and seems to be reliable enough for these short exercises.
Would love your thoughts!