Hacker News Reader

Comment by TheAceOfHearts | Hacker News Reader

AI subtitle generation seems like a useful feature. Hopefully they'll integrate with a subtitle sharing service so we don't have computers repeatedly duplicating work.

In the ideal case you'd probably generate a first pass of subtitles with AI, have a human review and tweak it as needed, and then share that. There's no reason for people to be repeatedly generating their own subtitles in most cases.

View on HN

Android and iOS already support live captions and AI Accelerators are becoming more common in PC hardware. If you can generate it with little compute at home, then there is no need to set up a share system.

You also want local generation in a lot of cases. If you have your own videos you need to generate them yourself. For Accessibility it's fantastic if they can have subtitles on every Video.

If generating your own is fast and good enough and takes little compute, then it isn't needed to share them. Having subtitles generated by the best models and optimized by humans is better, but not needed in most cases.

A system like that would be pretty nice as long as it wasn't a privacy problem. You wouldn't really need LLMs to do the subtitles as all then though, for any video common enough to be sharable the subtitles probably already exist from the original source.

How do you do this in a privacy preserving way?

The only feasible way I can think of is a locally run model. Perhaps whisper?

I think they meant the sharing

Whoopsie, good point. I agree.

Run the model on your PC. Done?

Reply on news.ycombinator.com