I often want to read the contents of YouTube videos but I don’t want to watch them, and YouTube’s captioning leaves a lot to be desired.<p>So I wrote a shell script that takes a URL, downloads the video, transcribes it with whisper, and turns it into a clean HTML page for reading.<p><a href="https://github.com/llimllib/yt-transcribe">https://github.com/llimllib/yt-transcribe</a>
Perhaps skip the whisper step if the video already has decent manual (not auto-generated) captions, like this video: <a href="https://youtu.be/i-BkN3rTK0Q" rel="nofollow">https://youtu.be/i-BkN3rTK0Q</a><p>---<p>Another use case is being able to quickly jump to a specific spot inside a video. Could you add timestamps with links that jump directly to that point in the video?<p>I accomplished something similar by modifying oTranscribe:<p>- <a href="https://otranscribe.netlify.app/?vsl=definedefine" rel="nofollow">https://otranscribe.netlify.app/?vsl=definedefine</a><p>- <a href="https://otranscribe.netlify.app/?vsl=letter" rel="nofollow">https://otranscribe.netlify.app/?vsl=letter</a><p>---<p>Finally, I'm a windows user so a whisper.cpp version would be nice~