clovaai/donut
Official Implementation of OCR-free Document Understanding Transformer (Donut) and Synthetic Document Generator (SynthDoG), ECCV 2022
This tool helps businesses and organizations automatically understand and classify various documents without needing traditional Optical Character Recognition (OCR). You feed it images of documents like receipts, train tickets, or invoices, and it extracts key information (like line items or dates) or classifies the document type. It's ideal for anyone who regularly processes large volumes of scanned or digital documents and needs to automate data extraction or categorization.
6,815 stars. No commits in the last 6 months.
Use this if you need to extract specific information from images of documents or classify documents by type, especially when traditional OCR struggles with document layouts or specific languages.
Not ideal if your primary need is simply to convert document images into editable text, as this tool focuses on understanding structure and content beyond basic text recognition.
Stars
6,815
Forks
554
Language
Python
License
MIT
Category
Last pushed
Jul 11, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/clovaai/donut"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
deepdoctection/deepdoctection
A Repo For Document AI
deanmalmgren/textract
extract text from any document. no muss. no fuss.
eikek/docspell
Assist in organizing your piles of documents, resulting from scanners, e-mails and other sources...
zzzDavid/ICDAR-2019-SROIE
ICDAR 2019 Robust Reading Challenge on Scanned Receipts OCR and Information Extraction
axa-group/Parsr
Transforms PDF, Documents and Images into Enriched Structured Data