Pandora’s Box is already open. Might as well make use of it.
While I hate the capitalist A-apocalypse with a passion I think this is great news for accessibility.
If it’s opt in/opt out then am fine with that.
Not only is it opt in, it’s also running fully locally on your machine.
Ohh I assume it’s Mistral cause Llama uses a Incompatible license.
It’s not an LLM, just a subtitles generator for video.
It’s Whisper.
OHHH okay
My biggest issue with that is the amount of bloat a full local LLM implementation would add.
But if it’s an optional module that you can choose to add (or choose not to add) after the fact, I have no complaint.
Yup. Easy uninstall otherwise.
If youtube transcriptions is anything to go by this won’t be great. But I’m optimistic
They’re helpful to my deaf ears, even when they’re wrong (50% of the words) they do give me a solid idea of what is being said together with what the audio sounds like.
With it, I get almost everything correct. Without it, I understand near to nothing.
This only goes for English spoken by Americans and sometimes London Britons, sadly, nothing else get detected nearly as good enough, so I can’t enjoy YouTube in my native language (Dutch), but being able to consume English YouTube already helps a lot!
That is very true. It’s hard to find local subtitles to a lot of stuff. And the whole deaf angle :)
I’ve been messing with more recent open-source AI Subtitling models via Subtitle Editor which has a nice GUI for it. Quality is much better these days, at least for English. It still makes mistakes, but the mistakes are on the level of “I misheard what they said and had little context for the conversation” or “the speaker has an accent which makes it hard to understand what they’re saying” mistakes, which is way better than most YouTube Auto Transriptions I’ve seen.
Youtube transcriptions are suprisingly abysmal considering what technology google already has at hand.
I actually disagree.
I’m consistently impressed whenever I have auto-subtitles turned on on Youtube.
I’m not impressed by the subtitles themselves (they’re just ok) but rather by how accessible it is. Like it being an option rather than it being a “tool for creators” or limited to premium or something
Or maybe youtube has added so much dogshit features recently (like ai overviews, automatically adding info cards for anyone mentioned, and highlighting seemingly random words in comments to search it outside of context) that it makes me appreciate these things more lol
I find them pretty good for English spoken by native speakers. For anything else it’s horrible.
It’s not every day that you see actually useful applications of AI, but this might be one.
I’ve seen some pretty piss poor implementations on streaming apps but if anyone can get it right it’s VLC
Do one thing and do it well. Oh well…
“Do one thing well” is what gives you software like mutt, which requires several other programs to be actually useful, all of which have to be configured separately to work together, with wildly different syntax.
And enables modular workflows and flexiblity.
VLC always had a ton of applications, network device playback, TV, streaming server, files, physical media, music player, effects, recording, AV format conversion, subtitles, plugins and so on.
This means that they most likely went for lighter AI models that use fewer resources, so that they run smoothly without putting too much strain on the machine.
Pretty good. Captions are one of the legitimate uses of “AI”.
It is probably good that OS community are exploring this however I’m not sure the technology is ready (or will ever be maybe) and it potentially undermines the labour intensive activity of producing high quality subtitling for accessibility.
I use them quite a lot and I’ve noticed they really struggle on key things like regional/national dialects, subject specific words and situations where context would allow improvement (e.g. a word invented solely in the universe of the media). So it’s probably managing 95% accuracy which is that danger zone where its good enough that no one checks it but bad enough that it can be really confusing if you are reliant on then. If we care about accessibility we need to care about it being high quality.
While good quality subtitles are essential VLC can’t ensure that, it’s the responsibility of the production studio. AI subtitles on vlc are for those videos which doesn’t have any sub (which are a lot). The pushback shouldn’t be for vlc implementing AI, but production studios replacing translators or transcriber with AI (like crunchyroll tried last year).
Also while transcribing and subtitle editing is a labour intensive job, use of AI to help the editors shouldn’t be discouraged, it can increase their productivity by automating repeatative tasks so that they can focus on better quality.
Aaaaaand I drop VLC. Fucking shame.
Braindead comment
You’re right! Your comment has added a tremendous amount of value to this thread.
You know AI can mean more than generative AI slop ?
Why would you need to do that if it’s off by default and locally processed?
Is it off, or is it an optional module that doesn’t have to be adding bloat to my system if I don’t want to use it?
LLMs can take up a pretty big storage footprint.
Why don’t you ask them? They’re very responsive to their community of users.
I just took a spin through their news blog and changelog and didn’t see anything about it in the latest release, so it’s probably not out yet.
Cause we can no longer sit back and allow AI infiltration, AI indoctrination, AI subversion and the international AI conspiracy to sap and impurify all of our precious bodily fluids.
Because triggered and hate circlejerk.
Nuance is deader than Elvis.
uh huh-huh.
I’m ready to deactivate it if it comes with any active component.
What do you mean by active component? Is processing the audio being played back to add subtitles active?
Is processing the audio being played back to add subtitles active?
Not sure where you are confused. If any part of this feature is active by default I will disable it.
The way you wrote this, I thought you meant that if it required a cloud service you would turn it off. But now I think you’re just saying you wouldn’t use this feature.
I share the confusion over your definition of “active”. You got all defensive when someone asked, so now no one really knows what you meant.
Even non-AI subtitles are off by default, what exactly are you expecting to be on?
Find someone else to argue with.
Exactly this makes no sense. Which tool would force subtitles
Sending the audio to an LLM in the sky. But I assume it would be local?
It says pretty explicitly that it only runs on the user’s machine.
This is not by default bad thing, if it is something you only use when you decide to do so, when you don’t have other subtitles available tbh. I hate AI slop too but people just go to monkey brain rage mode when they read AI and stop processing any further information.
I’d still always prefer human translated subtitles if possible. However, right now I’m looking into translating entire book via LLM cause it would be only way to read that book, as it is not published in any language I speak. I speak English well enough, so I don’t really need subtitles, just like to have them on so I won’t miss anything.
For English language movies, I’d probably just watch them without subtitles if those were AI, as I don’t really need them, more like nice to have in case I miss something. For languages I don’t understand, it might be good, although I wager it will be quite bad for less common languages.
There’s a difference between LLM slop (“write me an article about foo”) and using an LLM for something that’s actually useful (“listen to the audio from this file and transcribe everything that sounds like human speech”).
Exactly. I know someone who is really smart and works in machine learning and when I listen to him in isolation, AI sounds like actually useful thing. Most people just are not smart like that, and most applications for AI are not very useful.
One of the things I often think is that AI makes it possible to do things that shouldn’t be done very easily and fast, that would had previously been too much effort or craft for some people, like now they can easily make website for whatever grift they are pushing.
I wonder how good it is.
Does it translate from audio or from text?
Does it translate multiple languages, if video has a, b, c languages does it translate all to x.
Does user need to set input language?
Meh, I’ll just stick with
mpv.How is MPVs impementation? Does it work fairly well?
Its a command line multimedia player. It’s implementation is ideal for minimalists, and easily understood by reading the man pages.
Hold on to your butts!
