Keeping the same formatting as the input scanned pdf

facebookresearch / nougat

Implementation of Nougat Neural Optical Understanding for Academic Documents

https://facebookresearch.github.io/nougat/

MIT License

8.81k stars 561 forks source link

Closed AKRking closed 1 year ago

AKRking commented 1 year ago

Can nougat preserve formatting and layout such as indentation,layout,columns of texts as it is on the original source?any workaround for this?

lukas-blecher commented 1 year ago

No, nougat was specifically designed to produce a linear text output for all layouts.