VikParuchuri / marker

Convert PDF to markdown quickly with high accuracy
https://www.datalab.to
GNU General Public License v3.0
13.97k stars 707 forks source link

[Feature Request] TableBank, ReadingBank, and DocBank Benchmarks #180

Open matt-erhart opened 3 weeks ago

matt-erhart commented 3 weeks ago

I went looking for a way to compare marker to Azure Document Intelligence (best parser I've used), and found what I assume Microsoft is using: https://github.com/doc-analysis. I'm not sure I'll have time to set this up for myself, but I think it could really help this project get more popular, so I hope someone might try it out. Thanks for helping end the tyranny of the pdf.