Calamari OCR

Spec sheet

Purpose

Calamari is a line-based OCR engine based on OCRopy and Kraken, written in Python 3.Read 9 Oct 2026 · github.com

Intended users

The README describes command-line use and modular integration into Python scripts, and asks research-project users to cite its 2020 paper.Read 9 Oct 2026 · github.com

Audience

PyPI classifies the package for developers, education, and science or research, and labels it OS independent.Read 4 Oct 2026 · pypi.org

Support

The project links users to its documentation for further installation and usage instructions.Read 4 Oct 2026 · github.com

License

The GitHub repository identifies its license as GPL-3.0.Read 9 Oct 2026 · github.com

Command line

Calamari is designed to be used from the command line.Read 4 Oct 2026 · github.com

Customization

The engine can be integrated and customized from Python scripts, and the documentation includes a Python API.Read 9 Oct 2026 · github.com

Data formats

The documentation lists plain files, PageXML, Abbyy, and HDF5 dataset formats.Read 4 Oct 2026 · calamari-ocr.readthedocs.io

Input formats

The documentation lists Plain files, PageXML, Abbyy, and HDF5 dataset formats.Read 9 Oct 2026 · calamari-ocr.readthedocs.io

Installation

The README says Calamari is available on PyPI and gives `pip install calamari-ocr` as the installation command.Read 9 Oct 2026 · github.com

Line recognition

The project describes Calamari as a line based text recognition engine.Read 4 Oct 2026 · github.com

Line-level limit

Calamari currently supports OCR on lines; page segmentation and preceding preprocessing require other software.Read 9 Oct 2026 · calamari-ocr.readthedocs.io

Model training

The `calamari-train` command trains new models and supports data augmentation and early stopping.Read 9 Oct 2026 · calamari-ocr.readthedocs.io

Model voting

Calamari supports confidence voting across predictions from multiple models.Read 9 Oct 2026 · calamari-ocr.readthedocs.io

Notable limitation

The command line documentation states that currently only OCR on lines is supported.Read 4 Oct 2026 · github.com

PageXML workflow

For PageXML training, the documentation instructs users to provide page images with corresponding XML files.Read 4 Oct 2026 · calamari-ocr.readthedocs.io

Prediction

The `calamari-predict` command transcribes images of text lines into text.Read 9 Oct 2026 · calamari-ocr.readthedocs.io

Pretrained models

The README links to standard and experimental repositories of pretrained models.Read 9 Oct 2026 · github.com

Training

Its documentation includes commands for training, resuming training, and cross fold training models.Read 4 Oct 2026 · calamari-ocr.readthedocs.io

Where Specifiction places it

• OCR API Software#24 of 297.4