OCR & Documents
arvindrajan92/DTrOCR
A PyTorch implementation of DTrOCR: Decoder-only Transformer for Optical Character Recognition
PythonMITupdated Oct 23, 2026
A scene text recognition toolbox based on PyTorch
$ git clone https://github.com/Media-Smart/vedastr.gitA PyTorch implementation of DTrOCR: Decoder-only Transformer for Optical Character Recognition
text_recognition_toolbox: The reimplementation of a series of classical scene text recognition papers with Pytorch in a uniform way.
multi-task learning for text recognition with joint CTC-attention
▲ +10 ★ this week
docTR (Document Text Recognition) - a seamless, high-performing & accessible library for OCR-related tasks powered by Deep Learning. Ongoing development and maintenance by t2k.
Data from GitHub · snapshot Nov 16, 2026