I've been working on a little side project that combines Duolingo-like listening comprehension exercises with real content .
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!
Comments URL: https://news.ycombinator.com/item?id=43543235
Points: 19
# Comments: 6
Login to add comment
Other posts in this group
Article URL: https://felix86.com/
Comments URL: https://news.ycombinator.com/item?id=43864800
Article URL: https://w3ctag.github.io/web-without-3p-cookies/
Article URL: https://thereader.mitpress.mit.edu/the-anti-capitalist-case-for-standards/
Comments URL
We’ve built a functional prototype for an operating system layer that rejects the classic trust model.
Every process, network access, and system action is explicitly scope-bound to a signed capa
Article URL: https://developer.chrome.com/blog/dbsc-origin-trial
