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
Войдите, чтобы добавить комментарий
Другие сообщения в этой группе
Article URL: https://isomorphism.xyz/blog/2024/steam-deck/
Article URL: https://github.com/awslabs/mcp
Comments URL: https://news.ycombinator.com/i
Ditch Burp Suite’s bloat for zxc, a Rust-built, terminal-based proxy that uses tmux and Vim to intercept HTTP/S and WebSocket traffic. It captures requests for debugging, security testing, or twea
Article URL: https://www.esa.int/Space_Safety/Space_Debris
