edit to clarify a misconception in the comments, this is an instagram post so “caption” refers to the description under the image or video

as an example, this text i am typing now is also a “caption”

just saying because someone started a debate misunderstanding this to be about subtitles (aka “closed captions”) and that’s just not the case 👍

  • Jack@slrpnk.net
    link
    fedilink
    English
    arrow-up
    112
    arrow-down
    1
    ·
    5 days ago

    No, what you are thinking of is speech to text software, it is much older than LLMs and works in a very different way.

      • oplkill@lemmy.world
        link
        fedilink
        English
        arrow-up
        3
        arrow-down
        38
        ·
        5 days ago

        Nope, they still not good. I using YouTube auto gen subs and they 100% need LLM to fix mistakes.

        • AnarchoEngineer@lemmy.dbzer0.com
          link
          fedilink
          English
          arrow-up
          41
          ·
          5 days ago

          Large language models are designed to generate text based on previous text. Translation from audio to text can be done via a neural net but it isn’t a Large Language Model.

          Now, could you combine the two to say reduce error on words that were mumbled by having a generative model predict the words that would fit better in that unclear sentence. However you could likely get away with a much smaller and faster net than an LLM in fact you might be able to get away with using plain-Jane markov chains, no machine learning necessary.

          Point is that there is a difference between LLMs and other neural nets that produce text.

          In the case of audio to text translation, using an LLM would be very inefficient and slow (possibly to the point it isn’t able to keep up with the audio at all), and using a very basic text generation net or even just a probabilistic algorithm would likely do the job just fine.

        • Ziglin (it/they)@lemmy.world
          link
          fedilink
          English
          arrow-up
          17
          arrow-down
          1
          ·
          5 days ago

          How would an llm fix a mistake equivalent to something being misheard? I feel like you’re misunderstanding something and could probably also use some help with your English.

    • thejoker954@lemmy.world
      link
      fedilink
      English
      arrow-up
      12
      arrow-down
      2
      ·
      5 days ago

      While speech to text software indeed predates LLMs - LLMs do it as well. I’ve only tried a few basic (aka free) options so no idea how well they do en masse, but the generated results were at least on par if not better than YouTubes’ auto caption.

      It might not technically be LLMs though. It could be a different type of “ai”. I Just cant stand the “ai” marketing when nothing they are making is actually ai so until they pull their heads out their asses all “ai” models are LLMs to me.

      • Jack@slrpnk.net
        link
        fedilink
        English
        arrow-up
        9
        ·
        5 days ago

        Understandable, AI marketing now is a shitshot, but they are not even AI I think. Just people forget that tech used to do magic before AI existed.

        • LwL@lemmy.world
          link
          fedilink
          English
          arrow-up
          5
          ·
          4 days ago

          It’s kind of the other way around, we’ve always had AI, it used to just basically mean a computer making some decision based on data. Like a thermostat changing the heating in response to a temperature change.

          Then we got LLMs and because they are good at pretending to have complex reasoning ability, AI as a term started to always mean “computer with near human level intelligence” which of course they are absolutely not.

          • Jack@slrpnk.net
            link
            fedilink
            English
            arrow-up
            2
            ·
            4 days ago

            There was a book I can’t remember, the whole thesis was exactly that. “AI is whatever automates the decision making process” not any group of algos

        • ButteryMonkey@piefed.social
          link
          fedilink
          English
          arrow-up
          6
          ·
          5 days ago

          This is a big part of it. Back when ai was first becoming big, my manager said they needed to run all my kb articles through an ai to generate link clouds or some such.

          I was like umm… that’s a service this platform has always offered…? Like just because you don’t know what the kb tools do, or what our rock bottom subscription gets us, doesn’t mean I haven’t looked into it… but that also isn’t worth doing because now we only have a handful of articles in any given category because I’m good at my job…