Beautiful work. this has massive potential. I like the video aspect - it's almost as how people learned languages back then by listening to CDs and Tape. but now you can read someone's lips
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!