---
library_name: PyLaia
license: mit
tags:
- PyLaia
- PyTorch
- atr
- htr
- ocr
- historical
- printed
metrics:
- CER
- WER
language:
- de
datasets:
- Teklia/NewsEyeAustrian
pipeline_tag: image-to-text
---

# PyLaia - NewsEye Austrian

This model performs Handwritten Text Recognition in Austrian German. 

## Model description

The model has been trained using the PyLaia library on the [NewsEye / READ OCR training dataset from Austrian Newspapers (19th C.)](https://zenodo.org/record/3387369) dataset.

Training images were resized with a fixed height of 128 pixels, keeping the original aspect ratio.

| set | lines |
| :---- | ------: |
| train |  52,834 |
| val   |   4,667 |

An external 6-gram character language model can be used to improve recognition. The language model is trained on the text from the NewsEye training set.

## Evaluation results

The model achieves the following results:

| set   | Language model | CER (%)    | WER (%) | lines   |
|:------|:---------------| ----------:| -------:|----------:|
| val   | no             |  1.82      |   7.77  |     4,667 |
| val   | yes            |  1.77      |   7.01  |     4,667 |

## How to use?

Please refer to the [PyLaia documentation](https://atr.pages.teklia.com/pylaia/usage/prediction/) to use this model.

## Cite us!

```bibtex
@inproceedings{pylaia2024,
    author = {Tarride, Solène and Schneider, Yoann and Generali-Lince, Marie and Boillet, Mélodie and Abadie, Bastien and Kermorvant, Christopher},
    title = {{Improving Automatic Text Recognition with Language Models in the PyLaia Open-Source Library}},
    booktitle = {Document Analysis and Recognition - ICDAR 2024},
    year = {2024},
    publisher = {Springer Nature Switzerland},
    address = {Cham},
    pages = {387--404},
    isbn = {978-3-031-70549-6}
}
```