13
Baidu open-sourced a peanut-sized OCR that parses entire 100-page PDFs in one shot (huggingface.co)
submitted 3 months ago by to c/technology@midwest.social
comment fedilink hide all child comments

no comments (yet)

sorted by: hot top controversial new old
there doesn't seem to be anything here
11 comments in c/technology@lemmy.ml view that post
[–] 13 points 3 months ago (1 child)

Tiny specialized models are really interesting.

  • permalink
  • fedilink
  • source
  • hideshow 1 child comment
    •
  • [–] [S] 5 points 3 months ago

    Aside from agentic coding, this seems to be the most interesting niche to me. There are now lots of models for doing stuff like tts, stt, ocr, and it's really handy for sifting through documents, extracting transcripts, etc. And it's all stuff you can run locally on moderate hardware.

  • permalink
  • fedilink
  • source
  • parent
    • [–] 10 points 3 months ago

    o7 Farewell, Tesseract

  • permalink
  • fedilink
  • source
    •
    [–] 7 points 3 months ago (2 children)

    What languages does it support? Any source?

  • permalink
  • fedilink
  • source
  • hideshow 2 child comments
    •
    • [–] -1 points 3 months ago (4 children)

    I use the inbuild OCR in ShareX, which works pretty well, without AI. FOSS

  • permalink
  • fedilink
  • source
  • hideshow 4 child comments
    •
  • [–] [S] 10 points 3 months ago

    I find traditional OCR apps are just qualitatively worse. This tool understands complex tables, extracts mathematical formulas, predicts reading order, and outputs nicely formatted Markdown. So, it's not just blindly scraping flat text from a document.

  • permalink
  • fedilink
  • source
  • parent
  • [–] 5 points 3 months ago (2 children)

    Why do you think that it doesn't use AI? It uses Wndows' own OCR APIs, requiring Windows language packs for support for different scripts & languages. OCR has used AI for a long time now.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 2 child comments
    •