donut
Official Implementation of OCR-free Document Understanding Transformer (Donut) and Synthetic Document Generator (SynthDoG), ECCV 2022
Understand documents visually without needing text recognition, using a specialized AI model.
Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.
Get an email alert on its next release or when it starts trending — never miss the moment.
Free · no card · unsubscribe anytimeOfficial Implementation of OCR-free Document Understanding Transformer (Donut) and Synthetic Document Generator (SynthDoG), ECCV 2022
donut has 6.9k stars on GitHub. It has been forked 564 times. donut is written mainly in Python. It has been in active development since 2022. donut is available under the MIT license. Its main topics are computer-vision, document-ai, eccv-2022, multimodal-pre-trained-model.
What is donut?
Official Implementation of OCR-free Document Understanding Transformer (Donut) and Synthetic Document Generator (SynthDoG), ECCV 2022
Is donut open source?
donut is an open-source project. It is released under the MIT license.
Is donut free?
Yes. donut is free and open source — you can use, modify and self-host it.
What license does donut use?
donut is available under the MIT license.
What language is donut written in?
donut is written mainly in Python.
Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.
[](https://olud.ai/project/clovaai-donut.html)
Measured from GitHub topics shared by both projects, weighted by how rare each topic is.