search

SkalskiP / awesome-foundation-and-multimodal-models

👁️ + 💬 + 🎧 = 🤖 Curated list of top foundation and multimodal models! [Paper + Code + Examples + Tutorials]
538 stars 41 forks source link

OCR-free Document Understanding Transformer #2

Open mit1280 opened 8 months ago

mit1280 commented 8 months ago

Hi @SkalskiP,

OCR-free Document Understanding Transformer is one of the best open source multi model for OCR. It's good for QA, Classification.

Code/ repo link: https://github.com/clovaai/donut, https://arxiv.org/pdf/2111.15664.pdf Date: 06 Oct 2022

I think this can be added to the list. Let me know your thought?

SkalskiP commented 8 months ago

Looks awesome! will ad it!