facebookresearch / nougat

Implementation of Nougat Neural Optical Understanding for Academic Documents
https://facebookresearch.github.io/nougat/
MIT License
8.98k stars 567 forks source link

nougat misses the double column pdfs #205

Open qaiwiz opened 9 months ago

qaiwiz commented 9 months ago

For the text I used this paper "Einstein’s Unknown Insight and the Problem of Quantizing Chaos" in physics today. phys_today_Einstein_Quantization.pdf

I tried various versions, trying to convert the PDF as is, or take an image of page in pdf format and then convert. Doesn't matter what I do it only takes the right hand side column and totally ignore the other column.

I have attached a sample mmd where I tried to convert PDF using nogaut base-case

Screen Shot