Downloads · 30 days
0
Teklia/pylaia-casia-hwdb2
pylaia-casia-hwdb2 is a image-to-text model from Teklia. Use it when you need a caption or text from an image. It is set up for PyLaia. The card lists the license as mit.
This model performs Handwritten Text Recognition in Chinese.
Downloads · 30 days
0
Access
Public
Updated Sep 10, 2024
Repo size
65.2 MB
Likes
7
Public
Click a slice to open those files.
.ckpt53.3 MB · 82%
From the Hugging Face model README
This model performs Handwritten Text Recognition in Chinese.
The model was trained using the PyLaia library on the CASIA-HWDB2 dataset.
Training images were resized with a fixed height of 128 pixels, keeping the original aspect ratio.
| set | lines |
|---|---|
| train | 33,425 |
| val | 8,325 |
| test | 10,449 |
An external 6-gram character language model can be used to improve recognition. The language model is trained on the text from the CASIA-HWDB2 training set.
The model achieves the following results:
| set | Language model | CER (%) | lines |
|---|---|---|---|
| test | no | 4.61 | 10,449 |
| test | yes | 1.53 | 10,449 |
Please refer to the PyLaia documentation to use this model.
@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}
}