Step 2 of 4 · ProjectsAutomations

All projectsAutomations

docTR

Deep-learning OCR library for detecting and recognising text in documents.

What it does

Python OCR library that finds and reads the words in PDFs and images in two stages (detection, then recognition), with optional page layout detection (titles, tables, headers) and a key-information extraction mode; results export to JSON. It needs Python 3.11+ and PyTorch, installs with pip, and GPU-ready Docker images exist. A general OCR tool, not tax-specific, now maintained by t2k GmbH.

Where it fits on the map

In the processes

Similar projects

Of the same kind, for a shared jurisdiction or tax area. Not a ranking.

Maintain this project?

Link to this page from your README, so readers find the facts, the notes and where it fits. The badge is a small SVG served from this site.

Listed on tax-oss.com

[![Listed on tax-oss.com](https://tax-oss.com/badge.svg)](https://tax-oss.com/projects/doctr/)
Next · Step 3 of 4The gapsThe activities with no open project yet, and the partly covered ones, with what to build on.