I tried the japanese version. I like that you are using real Japanese language YouTube videos. You can see the kanji on the videos though so it kind of defeated the point. Hide the video? Great idea though and very fun too.
replies(1):
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!