Kraken

Spec sheet

Purpose

Kraken is an open-source automatic text recognition system optimized for historical documents and non-Latin scripts.Read 4 Oct 2026 · kraken.re

Product

Kraken is an open-source, turn-key automatic text recognition system optimized for historical and non-Latin-script writing.Read 5 Oct 2026 · kraken.re

Intended users

Kraken is designed for humanities digitization, including work with low-resource languages and diverse, non-conventional scripts.Read 4 Oct 2026 · kraken.re

Free plan

YesRead 23 Sep 2026 · kraken.re

Integrations

The documentation lists eScriptorium, OCR4all, the OCR-D suite, and arkindex by Teklia as applications or suites integrated with Kraken.Read 5 Oct 2026 · kraken.re

Support

The project welcomes feedback, pull requests, bug reports, and feature suggestions through its GitHub repository.Read 5 Oct 2026 · kraken.re

Configuration

Kraken supports configurable recognition through a network specification language and a plugin system.Read 5 Oct 2026 · kraken.re

Extensibility

Kraken’s plugin system lets developers add commands, model types, and tasks through Python entry points.Read 4 Oct 2026 · kraken.re

Handwriting OCR

YesRead 23 Sep 2026 · kraken.re

Installation

The documentation says Kraken can be installed on Linux or Mac OS X, on x64 and ARM, using pip or Anaconda.Read 5 Oct 2026 · kraken.re

Interfaces

Kraken provides a customizable command-line interface and an API for building custom workflows and integrating it into other projects.Read 5 Oct 2026 · kraken.re

Layout and recognition

Kraken supports trainable layout analysis, reading order, and character recognition.Read 5 Oct 2026 · kraken.re

License and development

Kraken is provided under the Apache 2.0 License and is developed at Inria and École Pratique des Hautes Études, Université PSL.Read 4 Oct 2026 · kraken.re

Model repository

Kraken provides a public repository of freely available models, accessed through its command-line tools.Read 4 Oct 2026 · kraken.re

Model requirement

Kraken requires a model for document processing, and the documentation says a model trained on similar material performs best.Read 4 Oct 2026 · kraken.re

Models

Kraken provides a public repository of model files through HTRMoPo.Read 5 Oct 2026 · kraken.re

Optional input support

Direct PDF and multi-image TIFF/JPEG2000 support requires installing the PDF extras package.Read 4 Oct 2026 · kraken.re

Output formats

Kraken can output ALTO, PageXML, AbbyyXML, and hOCR.Read 5 Oct 2026 · kraken.re

Primary platform

desktopRead 23 Sep 2026 · kraken.re

Python API

The Python API includes task-oriented classes for segmentation, recognition, and forced alignment.Read 4 Oct 2026 · kraken.re

Recognition details

Kraken supports word bounding boxes and character cuts.Read 5 Oct 2026 · kraken.re

Script direction

Kraken supports right-to-left, bidirectional, and top-to-bottom scripts.Read 5 Oct 2026 · kraken.re

Script directions

Kraken supports right-to-left, bidirectional, and top-to-bottom scripts.Read 4 Oct 2026 · kraken.re

Supported inputs

bothRead 23 Sep 2026 · kraken.re

Trainable tasks

Its features include trainable layout analysis, reading order, and character recognition.Read 4 Oct 2026 · kraken.re

Use case

Kraken is designed as a universal text recognizer for humanities research, including low-resource languages and diverse scripts.Read 5 Oct 2026 · kraken.re

Word export

NoRead 23 Sep 2026 · kraken.re

Where Specifiction places it

• OCR API Software#22 of 297.5
• OCR software#36 of 407.3