SoMarkAI /
OXR
An open-source document parsing model with SOTA accuracy and speed, using an RSI loop during post-training.
#2 in PDF & OCR Python 2,858 stars Spotted by Upstar at 257 stars 
Badge for your README
Updated 5 min ago
Maintain this repo? Add this badge to your README.
Why now
Upstar spotted OXR 10 days ago.
+1,941 stars gained this week
×11.1 since Upstar spotted it
Stars gained each day, last 30 days
Oct 4Oct 19Today
This week Before
In short
An open-source 1.3B-parameter document parsing model that turns PDFs and document images into Markdown or JSON with layout coordinates, for developers building agent pipelines. Its layout analysis module can be swapped for a custom one.
Summary written by AI from the repository’s description and README.
SoMarkAI / OXR
View on GitHub(opens in new tab)