search

UW-Madison-DataScience / ML-X-Nexus

Nexus is the ML+X community’s centralized hub for sharing machine learning (ML) resources.
https://uw-madison-datascience.github.io/ML-X-Nexus/
5 stars 6 forks source link

OCR with LMMs and/or GPT #30

Open qualiaMachine opened 3 months ago

qualiaMachine commented 3 months ago

Got a recent inquiry from a researcher asking about methods to convert a batch of PDFs to text. A short guide on OCR methods using AI may be warranted.

One possible starting point: https://llava-vl.github.io/blog/2024-01-30-llava-next/