←back to thread

456 points ph4evers | 2 comments | | HN request time: 0s | source

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!

1. palata ◴[] No.43546898[source]
This is cool!

I'm curious now: how do you transcribe the videos? And how do you align the transcript with the video (in terms of timing)? Are there libraries doing that?

replies(1): >>43550034 #
2. ph4evers ◴[] No.43550034[source]
I'm using AssemblyAI and Deepgram. AssemblyAI for the large languages and Deepgram for the smaller ones.