Live data from Hacker News

VLC tops 6B downloads, previews AI-generated subtitles

techcrunch.com

41–50 of 163 posts

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

#43
post #24
post #9

A while ago I used whisper (or rather an OSS subtitle tool that used whisper, sadly can’t remember the name; it also converted burned in subs to proper ones via OCR) to generate subtitles for a season of a Show (4 season DVD set, 1 had proper subs, 2 burned in subs, 1 no subs -.-), too old and not popular enough to have "scene" subs, it worked impressively well. The most memorable thing for me was that a character’s…

You can setup a bazarr instance to use whisper as a subtitle provider.

Looks like it only works if you use the *arr stack, which I don’t.

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

#44

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?

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

#46
post #34

It's really sad that I'm reading "open source model" and think "hmhm, as if". Maybe they're really using a truly open source model (probably not) but the meaning of the word is muddied already.

https://code.videolan.org/videolan/vlc/-/merge_requests/5155

Here they are working on integrating Whisper.cpp

In the search bar it says "Updated 2 weeks ago", like if there were additional recent comments or actions in this thread that we cannot see.

So it could actually be OpenAI Whisper model, for which we have the final binary format (the weights), but not the source training data, but it is the best you can get for free.

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

#48
post #42

Isn't this what YouTube has been doing with automatically generated subtitles for videos for years? I've always found their quality to be somewhat lacking.

Yes and no.

Likely due to cost, Google hasn’t decided to use any LLM model (what basically everybody refers to when they say AI now) to generate the subtitles and by modern standards they aren’t very good.

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

#49
post #34

It's really sad that I'm reading "open source model" and think "hmhm, as if". Maybe they're really using a truly open source model (probably not) but the meaning of the word is muddied already.

The meaning of "AI" and "open source model" have both been muddied enough to be pretty meaningless.
Post reply on HN