84
UDOP
🏃
Generate text from document images
Awesome Document AI
A collection of open-source document AI 📄 📝 📈
-
-
40
Pix2struct
📚Play with all the pix2struct variants in this d
-
24
Compare Docvqa Models
🦀Compare different visual question answering
-
290
DocQuery — Document Query Engine
🦉 -
Nougat Transformers
🍫Nougat: powerful paper transcription powered by transformers
-
81
Donut Docvqa
🍩 -
impira/layoutlm-document-qa
Document Question Answering • Updated • 56.5k • • 1.07k -
google/pix2struct-docvqa-base
Visual Question Answering • Updated • 5.02k • 37 -
google/pix2struct-docvqa-large
Visual Question Answering • Updated • 175 • 31 -
google/pix2struct-infographics-vqa-large
Visual Question Answering • Updated • 230 • 10 -
google/pix2struct-base
Image-to-Text • Updated • 4.17k • • 67 -
google/pix2struct-textcaps-base
Image-to-Text • Updated • 4.45k • 28 -
impira/layoutlm-invoices
Document Question Answering • Updated • 8.13k • • 188 -
microsoft/layoutlm-base-uncased
Updated • 1.6M • 50 -
microsoft/layoutlmv3-large
Updated • 159k • 102 -
microsoft/layoutlmv2-base-uncased
Updated • 1.04M • 63 -
naver-clova-ix/donut-base-finetuned-docvqa
Document Question Answering • Updated • 16.4k • • 215 -
naver-clova-ix/donut-base
Image-to-Text • Updated • 53.8k • • 198 -
facebook/nougat-base
Image-to-Text • Updated • 13.8k • • 163 -
Nougat: Neural Optical Understanding for Academic Documents
Paper • 2308.13418 • Published • 37 -
microsoft/udop-large
Image-Text-to-Text • Updated • 5.01k • 114 -
facebook/nougat-small
Image-to-Text • Updated • 62k • 26 -
microsoft/layoutlmv3-base
Updated • 2.61M • 368 -
LayoutLM: Pre-training of Text and Layout for Document Image Understanding
Paper • 1912.13318 • Published • 2 -
LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking
Paper • 2204.08387 • Published • 2 -
LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding
Paper • 2012.14740 • Published • 1 -
microsoft/layoutlmv3-base-chinese
Updated • 1.72k • 69
