D
donut
clovaai/donut
Official Implementation of OCR-free Document Understanding Transformer (Donut) and Synthetic Document Generator (SynthDoG), ECCV 2022
★6.9kstars
Python
MIT
Updated: 1d ago
📋 Project at a Glance
Tap to expand
What's this?Models project leveraging computer-vision and document-ai, built with Python, open-source
Who made it?Maintained by clovaai team, 6.9K⭐ on GitHub, #223 out of 3201 in Models
Why does it exist?With the growing demand for computer-vision and document-ai in Models, clovaai created donut as a streamlined solution.
What can it do?Key use cases: eccv-2022, multimodal-pre-trained-model, nlp
How to install with AI?Use an AI coding assistant (Claude Code, Cursor, Copilot) to automatically set up pip dependencies and virtual env. Follow the README — the AI handles the rest.
🔗 github.com/clovaai/donut | 官网 https://arxiv.org/abs/2111.15664
🔗 github.com/clovaai/donut | 官网 https://arxiv.org/abs/2111.15664
Topics
computer-visiondocument-aieccv-2022multimodal-pre-trained-modelnlpocr