Commit
•
6d64ed9
1
Parent(s):
dffa2e7
Update README
Browse files
README.md
CHANGED
|
@@ -1,3 +1,37 @@
|
|
| 1 |
---
|
|
|
|
| 2 |
license: mit
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
library_name: PyLaia
|
| 3 |
license: mit
|
| 4 |
+
tags:
|
| 5 |
+
- PyLaia
|
| 6 |
+
- PyTorch
|
| 7 |
+
- Handwritten text recognition
|
| 8 |
+
metrics:
|
| 9 |
+
- CER
|
| 10 |
+
- WER
|
| 11 |
+
language:
|
| 12 |
+
- ge
|
| 13 |
---
|
| 14 |
+
|
| 15 |
+
# Fraktur handwritten text recognition
|
| 16 |
+
|
| 17 |
+
This model performs Handwritten Text Recognition in Austrian German.
|
| 18 |
+
|
| 19 |
+
## Model description
|
| 20 |
+
|
| 21 |
+
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.
|
| 22 |
+
Training images were resized with a fixed height of 128 pixels, keeping the original aspect ratio.
|
| 23 |
+
|
| 24 |
+
## Evaluation results
|
| 25 |
+
|
| 26 |
+
The model achieves the following results:
|
| 27 |
+
|
| 28 |
+
| Split | CER (%) | WER (%) | Support |
|
| 29 |
+
|---------|-----------|-----------|-----------|
|
| 30 |
+
| train | 1.62 | 5.63 | 38891 |
|
| 31 |
+
| val | 1.82 | 7.77 | 3282 |
|
| 32 |
+
|
| 33 |
+
Results can be improved by combining PyLaia with a n-gram language model.
|
| 34 |
+
|
| 35 |
+
## How to use
|
| 36 |
+
|
| 37 |
+
Please refer to the PyLaia library page (https://pypi.org/project/pylaia/) and [wiki](https://github.com/jpuigcerver/PyLaia/wiki/inference) to use this model.
|