No project description provided
Project description
PyLaia
PyLaia is a device agnostic, PyTorch based, deep learning toolkit for handwritten document analysis.
It is also a successor to Laia.
Get started by having a look at our Documentation!
Installation
To install PyLaia from PyPi:
pip install pylaia
The following Python scripts will be installed in your system:
pylaia-htr-create-model
: Create a VGG-like model with BLSTMs on top for handwriting text recognition. The script has different options to customize the model. The architecture is based on the paper "Are Multidimensional Recurrent Layers Really Necessary for Handwritten Text Recognition?" (2017) by J. Puigcerver.pylaia-htr-train-ctc
: Train a model using the CTC algorithm and a set of text-line images and their transcripts.pylaia-htr-decode-ctc
: Decode text line images using a trained model and the CTC algorithm. It can also output the char/word segmentation boundaries of the symbols recognized.pylaia-htr-netout
: Dump the output of the model for a set of text-line images in order to decode using an external language model.
Contributing
If you want to contribute new feature or found a text that is incorrectly segmented using pySBD, then please head to CONTRIBUTING.md to know more and follow these steps.
- Fork it ( https://gitlab.teklia.com/atr/pylaia/-/forks/new )
- Create your feature branch (
git checkout -b my-new-feature
) - Commit your changes (
git commit -am 'Add some feature'
) - Push to the branch (
git push origin my-new-feature
) - Create a new Merge Request ( https://gitlab.teklia.com/atr/pylaia/-/merge_requests/new )
Code of conduct
We are committed to providing a friendly, safe and welcoming environment for all. Please read and respect the PyLaia Code of Conduct.
Acknowledgments
Work in this toolkit was financially supported by the Pattern Recognition and Human Language Technology (PRHLT) Research Center.
Citation
- Article describing the latest contributions to PyLaia
@inproceedings{pylaia2024,
author = "Tarride, Solène and Schneider, Yoann and Generali, Marie and Boillet, Melodie and Abadie, Bastien and Kermorvant, Christopher",
title = "Improving Automatic Text Recognition with Language Models in the PyLaia Open-Source Library",
booktitle = "Submitted at ICDAR",
year = "2024"
}
- Original article
@inproceedings{laia2017,
author={Puigcerver, Joan},
booktitle={2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR)},
title={Are Multidimensional Recurrent Layers Really Necessary for Handwritten Text Recognition?},
year={2017},
volume={01},
number={},
pages={67-72},
doi={10.1109/ICDAR.2017.20}}
- GitLab repository
@software{pylaia-teklia,
author = {Teklia},
title = {PyLaia},
year = {2022},
url = {https://gitlab.teklia.com/atr/pylaia/},
version = {1.1.0},
note = {commit SHA}
}
- GitHub repository
@misc{puigcerver2018pylaia,
author = {Joan Puigcerver and Carlos Mocholí},
title = {PyLaia},
year = {2018},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {\url{https://github.com/jpuigcerver/PyLaia/}},
commit = {commit SHA}
}
Contact
🆘 Have a question about PyLaia? Please contact us on support.teklia.com.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
File details
Details for the file pylaia-1.1.2.tar.gz
.
File metadata
- Download URL: pylaia-1.1.2.tar.gz
- Upload date:
- Size: 66.8 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.1.1 CPython/3.10.15
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 873fabd7f382ce7d267cc8af2e0f1848ab6f3382eb2c7e5a0fbfa8c0f576b95a |
|
MD5 | ac8ff69819deb3f05db095397cd619f3 |
|
BLAKE2b-256 | 51b747f07f442c9bd651cef7d36b382cd26856e567e1ab724cd2fe53e5ae0e40 |
File details
Details for the file pylaia-1.1.2-py3-none-any.whl
.
File metadata
- Download URL: pylaia-1.1.2-py3-none-any.whl
- Upload date:
- Size: 93.4 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.1.1 CPython/3.10.15
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 8b894d3a84a8636b58cbd8b5a1e08024b77f3de42fc2a81e772e4710c734399b |
|
MD5 | da3912e93189f62c50551e3e6447ce55 |
|
BLAKE2b-256 | 36d24d2ecc9677eddef508ef4a1671fbcfd1459f904600e8be0edac712d2f7f2 |