---
library_name: PyLaia
license: mit
tags:
- PyLaia
- PyTorch
- Handwritten text recognition
metrics:
- CER
- WER
language:
- ge
datasets:
- Teklia/NewsEyeAustrian
---

# Fraktur handwritten text recognition

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.

## Evaluation results

The model achieves the following results:

| Split   |   CER (%) |   WER (%) |   Support |
|---------|-----------|-----------|-----------|
| train   |      1.62 |      5.63 |     38891 |
| val     |      1.82 |      7.77 |      3282 |

Results can be improved by combining PyLaia with a n-gram language model. 

## How to use

Please refer to the [documentation](https://atr.pages.teklia.com/pylaia/).

## Cite us

```bibtex
@inproceedings{pylaia-lib,
    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 ICDAR2024",
    year = "2024"
}
```