OCR & Documents
clovaai/donut
Official Implementation of OCR-free Document Understanding Transformer (Donut) and Synthetic Document Generator (SynthDoG), ECCV 2022
🧠 Natural Language Processing
PythonMITupdated Jul 11, 2024
🏆 #6,600 overall#653 of 693 in OCR & Documents
nttmdlab-nlp /SlideVQA
SlideVQA: A Dataset for Document Visual Question Answering on Multiple Images (AAAI2023)
$ git clone https://github.com/nttmdlab-nlp/SlideVQA.gitStars
109
109
This week
—
Forks
8
8
Language
Python
License
Other
Created
Nov 25, 2022
4.0 years old
Last push
Mar 31, 2025
GitHub topics
More in OCR & Documents
OCR & Documents
deepdoctection/deepdoctection
▲ +6 ★ this week
A Repo For Document AI
🧠 Natural Language Processing
PythonApache-2.0updated Oct 21, 2026
OCR & Documents
maxent-ai/ocrpy
OCR, Archive, Index and Search: Implementation agnostic OCR framework.
🔍 Search & Retrieval🧠 Natural Language Processing
Jupyter NotebookMITupdated Nov 3, 2023
OCR & Documents
doc-analysis/ReadingBank
ReadingBank: A Benchmark Dataset for Reading Order Detection
🧠 Natural Language Processing
Otherno licenseupdated Sep 21, 2026
OCR & Documents
clovaai/webvicob
Official Implementation of Web-based Visual Corpus Builder (Webvicob), ICDAR 2023
🧠 Natural Language Processing
PythonApache-2.0updated Oct 24, 2023
OCR & Documents
parz0val0/scan-to-practice
Scan-to-Practice: a field-tested AI skill and methodology for turning scanned learning materials into structured practice products.
OtherMITupdated Aug 12, 2026
Data from GitHub · snapshot Nov 13, 2026