kamilib-light

A light version of KaMI-lib Python package containing only the transcription metrics module (without Kraken).


Keywords
HTR, OCR, Evaluation, framework, metrics, handwritten, text, recognition, optical, character
License
MIT
Install
pip install kamilib-light==0.1.1

Documentation

KaMI-lib (Kraken Model Inspector) - Light version

Python Version

KaMI-lib light CI Version License: MIT

A light version of KaMI-lib containing only the transcription metrics module (without Kraken).

🔌 Installation

User installation

Use pip to install package:

$ pip install kamilib-light

Developer installation

  1. Create a local branch of the kami-lib light project
$ git clone https://github.com/KaMI-tools-project/KaMI-lib-light.git
  1. Create a virtual environment
$ virtualenv -p python3.7 venv

then

$ source kami_venv/bin/activate
  1. Install dependencies with the requirements file
$ pip install -r requirements.txt
  1. Run the tests
$ python -m unittest tests/*.py -v

🔑 Quickstart

Please, follow the documentation of kami-lib and ignore part 2 (with Kraken engine).

Note that instead of importing Kami-lib like this:

from kami.Kami import Kami

Replace by this:

from kami_light.Kami import Kami

Do you have questions, bug report, features request or feedback?

Please use the issue templates:

🪲 Bug report: here

🎆 Features request: here

if aforementioned cases does not apply, feel free to open an issue.

✒️ How to cite

@misc{Kami-lib-light,
    author = "Lucas Terriel (Inria - ALMAnaCH) and Alix Chagué (Inria - ALMAnaCH)",
    title = {Kami-lib - Kraken model inspector, a light version},
    howpublished = {\url{https://github.com/KaMI-tools-project/KaMI-lib-light}},
    year = {2022}
}

🐙 License and contact

Distributed under MIT license. The dependencies used in the project are also distributed under compatible license.

Mail authors and contact: Alix Chagué (alix.chague@inria.fr) and Lucas Terriel (lucas.terriel@inria.fr)

KaMI-lib-light is a part of KaMI-tools-project and developed and maintained by authors (2022) with contributions of ALMAnaCH at Inria Paris.

forthebadge made-with-python