Live data from Hacker News

VLC tops 6B downloads, previews AI-generated subtitles

techcrunch.com

51–60 of 163 posts

Re: VLC tops 6B downloads, previews AI-generated subtitles

#52
There's an art to subtitling that goes beyond mere speech-to-text processing. Sometimes it's better to paraphrase dialog to reduce the amount of text that needs to be read. Sometimes you need to name a voice as unknown, to avoid spoilers. Sometimes the positioning on the screen matters. I hope the model can be made to understand all this.

Re: VLC tops 6B downloads, previews AI-generated subtitles

#53

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.

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.

Re: VLC tops 6B downloads, previews AI-generated subtitles

#54
I wonder if VLC tracks their downloads per day or region. Similar to Pornhub Trends, it'd be interesting to correlate a spike of downloads with events like Netflix hiking up their prices/enforcing anti-password-sharing policies, dropping some series from their catalogue, or some hyped-up movie being released...

Re: VLC tops 6B downloads, previews AI-generated subtitles

#55

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.

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?

Re: VLC tops 6B downloads, previews AI-generated subtitles

#56
post #52

There's an art to subtitling that goes beyond mere speech-to-text processing. Sometimes it's better to paraphrase dialog to reduce the amount of text that needs to be read. Sometimes you need to name a voice as unknown, to avoid spoilers. Sometimes the positioning on the screen matters. I hope the model can be made to understand all this.

> Sometimes it's better to paraphrase dialog to reduce the amount of text that needs to be read.

Questionable. It drives me crazy to have subtitles that are paraphrase in a way that changes the meaning of statements.

Re: VLC tops 6B downloads, previews AI-generated subtitles

#57

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.

How do you do this in a privacy preserving way?

Run the model on your PC. Done?

Re: VLC tops 6B downloads, previews AI-generated subtitles

#60

I recently used some subtitles that I later found out had been AI generated. The experience wasn't really good to be honest - the text was technically correct but the way multiline phrases were split made them somehow extremely hard to parse. The only reason I learned AI was involved is that it was bad enough for me to stop viewing and check what was wrong. Hopefully it's an implementation detail and we'll see better…

I had exactly the same experience. Human expertise in subtitle makes the experience really better
Post reply on HN