Skip to main content

lemmy - Link to source

Baidu open-sourced a peanut-sized OCR that parses entire 100-page PDFs in one shot

baidu/Unlimited-OCR · Hugging Face

We’re on a journey to advance and democratize artificial intelligence through open source and open science.
huggingface.co
#technology
in reply to ☆ Yσɠƚԋσʂ ☆

Alavi
lemmy - Link to source
Alavi
• •
What languages does it support? Any source?
in reply to Alavi

floquant
lemmy - Link to source
floquant
• •
I don't see language being passed in the example code, so it may be agnostic?
in reply to floquant

Alavi
lemmy - Link to source
Alavi
• •
Isn't that almost impossible? It has to be trained on that language afaik
in reply to ☆ Yσɠƚԋσʂ ☆

Zerush
lemmy - Link to source
Zerush
• •
I use the inbuild OCR in ShareX, which works pretty well, without AI. FOSS
in reply to Zerush

ferric_carcinization
lemmy - Link to source
ferric_carcinization
• •
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.
in reply to ferric_carcinization

Zerush
lemmy - Link to source
Zerush
• •
Yes, like my chess computer in the 90th. I don't have any lenguage modell in Windows, nor any other MS crap and services, the first I deleted from Windows. The lenguage pack and fonts are another thing, nothing to do with LLM or AI
This entry was edited (5 days ago)
in reply to Zerush

☆ Yσɠƚԋσʂ ☆
lemmy - Link to source
☆ Yσɠƚԋσʂ ☆
• •
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.
in reply to Marija

☆ Yσɠƚԋσʂ ☆
lemmy - Link to source
☆ Yσɠƚԋσʂ ☆
• •
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.
⇧