Hey guys, I am looking for a desktop app (Linux) that can translate text in images. I know I can do that with google or some other websites but I was wondering if you have an open source alternative.

  • @mindlight@lemm.ee
    link
    fedilink
    89 months ago

    I don’t have the answer your looking for but maybe a pointer for where to look and what to look for …

    What you want is essentially done in two steps.

    1. Optical Character Recognition - an image consists of pixels. There is no text, just pixels. You need a program that can see the difference between pixels forming an A and an B. Tesseract is a very competent program for this and it’s free. However, it’s command line only but I know there are GUI applications based on Tesseract.

    2. Translate text from one language to another - maybe Dialect?

        • @garrett@lemm.ee
          link
          fedilink
          59 months ago

          Just pointing this out, as there are non-free services that the apps use:

          Frog is awesome, but note that while Frog works offline for OCR, it has TTS (text to speech) which uses an online service. As long as you avoid having it read to you, it’s all done locally.

          And Dialect always uses an online service. Some of the servers are FOSS, but some aren’t. But everything you type or paste into it is sent somewhere else. (This is the case with using translation websites too, of course.) I’m not saying you shouldn’t use it; I’m just saying that you should be aware.

          Hopefully Dialect will add Bergamot (what both Firefox by default & the “translate locally” extension use for translation) at some point. Dialect has a longstanding issue about it, but no forward motion yet. https://github.com/dialect-app/dialect/issues/183

          For something open source that runs completely on your computer for translations, you’d want Speech Note. https://flathub.org/apps/net.mkiol.SpeechNote It’s Qt based, but works well. In addition to translation, it can do text to speech and speech to text too. You do have to download models first (easily available as a click in the app), but everything, including the text you’re working with, is all done locally.

          I use both Frog and Speech Note all the time on my computer (GNOME on Fedora Linux). They’re excellent.

          • @rollingflower
            link
            19 months ago

            Interesting, didnt know the Translation Engine was called Bergamot. Yes this absolutely needs an Android app, a Linux app, and integration everywhere. Its awesome.