https://github.com/ajkdrag/ocrtoolkit

Experiment and integrate with different OCR frameworks seamlessly
https://github.com/ajkdrag/ocrtoolkit

doctr ocr paddleocr pytorch text-detection text-recognition ultralytics

Last synced: 5 months ago
JSON representation

Experiment and integrate with different OCR frameworks seamlessly

• Host: GitHub
• URL: https://github.com/ajkdrag/ocrtoolkit
• Owner: ajkdrag
• License: apache-2.0
• Created: 2024-02-09T12:39:11.000Z (over 2 years ago)
• Default Branch: master
• Last Pushed: 2024-04-10T07:09:55.000Z (about 2 years ago)
• Last Synced: 2025-08-25T06:56:57.000Z (9 months ago)
• Topics: doctr, ocr, paddleocr, pytorch, text-detection, text-recognition, ultralytics
• Language: Jupyter Notebook
• Homepage: https://ajkdrag.github.io/ocrtoolkit/
• Size: 79.8 MB
• Stars: 103
• Watchers: 2
• Forks: 4
• Open Issues: 0
• Metadata Files:
  • Readme: README.rst
  • Changelog: CHANGELOG.rst
  • Contributing: CONTRIBUTING.rst
  • License: LICENSE

Awesome Lists containing this project

README

          
|docs_badge| |pypi_badge|

.. |docs_badge| image:: https://img.shields.io/github/deployments/ajkdrag/ocrtoolkit/github-pages?label=docs

   :alt: GitHub-Pages deployment status

   :target: https://ajkdrag.github.io/ocrtoolkit/ocrtoolkit/

.. |pypi_badge| image:: https://img.shields.io/pypi/v/ocrtoolkit?style=flat&color=green

   :alt: PyPI - Version

   :target: https://pypi.org/project/ocrtoolkit/

ocrtoolkit

############

Versatile Python package for seamlessly integrating and experimenting with various OCR and Object Detection frameworks.

.. contents::

   :local:

Quickstart

==========

ocrtoolkit is available on PyPI and can be installed with `pip `_.

Supports integrations with:

- `DocTR `_

- `PaddleOCR `_

- `Ultralytics `_

- `Google Cloud Vision `_

.. code-block:: console

    $ pip install ocrtoolkit

After installing ocrtoolkit you can use it like any other Python module.

Here is a simple example:

.. code-block:: python

    from ocrtoolkit.models import UL_YOLOV8

    from ocrtoolkit.datasets import FileDS

    from ocrtoolkit.core import detect

    ds = FileDS("some_images_dir")

    mini_ds = ds.sample()

    model = UL_YOLOV8()

    l_results = detect(model, mini_ds, stream=False)

    

Documentation

==============

The `API Reference `_ provides API-level documentation

Notebooks

==========

Refer `notebooks `_ for examples on how to use the modules.

.. include:: CHANGELOG.rst