Update README.md
Browse files
README.md
CHANGED
@@ -18,28 +18,26 @@ This model performs Handwritten Text Recognition in Norwegian. It was developed
|
|
18 |
|
19 |
## Model description
|
20 |
|
21 |
-
The model has been trained using the PyLaia library on the [NorHand](https://zenodo.org/record/6542056) document images.
|
|
|
22 |
Training images were resized with a fixed height of 128 pixels, keeping the original aspect ratio.
|
23 |
|
24 |
-
|
|
|
|
|
|
|
|
|
25 |
|
26 |
-
The model
|
27 |
-
|
28 |
-
| set | CER (%) | WER (%) |
|
29 |
-
| ----- | ---------- | --------- |
|
30 |
-
| train | 2.17 | 7.65 |
|
31 |
-
| val | 8.78 | 24.93 |
|
32 |
-
| test | 7.94 | 24.04 |
|
33 |
|
|
|
34 |
|
35 |
-
|
36 |
-
The language model is trained on [this text corpus](https://www.nb.no/sprakbanken/en/resource-catalogue/oai-nb-no-sbr-73/) published by the National Library of Norway.
|
37 |
|
38 |
-
| set | CER (%) | WER (%) |
|
39 |
-
|
40 |
-
|
|
41 |
-
|
|
42 |
-
| test | 6.55 | 18.2 |
|
43 |
|
44 |
|
45 |
## How to use
|
@@ -48,6 +46,15 @@ Please refer to the [documentation](https://atr.pages.teklia.com/pylaia/).
|
|
48 |
|
49 |
# Cite us!
|
50 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
51 |
```bibtex
|
52 |
@inproceedings{10.1007/978-3-031-06555-2_27,
|
53 |
author = {Maarand, Martin and Beyer, Yngvil and K\r{a}sen, Andre and Fosseide, Knut T. and Kermorvant, Christopher},
|
|
|
18 |
|
19 |
## Model description
|
20 |
|
21 |
+
The model has been trained using the PyLaia library on the [NorHand v1](https://zenodo.org/record/6542056) document images.
|
22 |
+
|
23 |
Training images were resized with a fixed height of 128 pixels, keeping the original aspect ratio.
|
24 |
|
25 |
+
| split | N horizontal lines |
|
26 |
+
| ----- | ------: |
|
27 |
+
| train | 19,653 |
|
28 |
+
| val | 2,286 |
|
29 |
+
| test | 1,793 |
|
30 |
|
31 |
+
An external 6-gram character language model can be used to improve recognition. The language model is trained on the text from the NorHand v1 training set.
|
|
|
|
|
|
|
|
|
|
|
|
|
32 |
|
33 |
+
## Evaluation results
|
34 |
|
35 |
+
The model achieves the following results:
|
|
|
36 |
|
37 |
+
| set | Language model | CER (%) | WER (%) | N lines |
|
38 |
+
|:------|:---------------|:----------:|:-------:|----------:|
|
39 |
+
| test | no | 7.94 | 24.04 | 1,793 |
|
40 |
+
| test | yes | 6.55 | 18.20 | 1,793 |
|
|
|
41 |
|
42 |
|
43 |
## How to use
|
|
|
46 |
|
47 |
# Cite us!
|
48 |
|
49 |
+
```bibtex
|
50 |
+
@inproceedings{pylaia-lib,
|
51 |
+
author = "Tarride, Solène and Schneider, Yoann and Generali, Marie and Boillet, Melodie and Abadie, Bastien and Kermorvant, Christopher",
|
52 |
+
title = "Improving Automatic Text Recognition with Language Models in the PyLaia Open-Source Library",
|
53 |
+
booktitle = "Submitted at ICDAR2024",
|
54 |
+
year = "2024"
|
55 |
+
}
|
56 |
+
```
|
57 |
+
|
58 |
```bibtex
|
59 |
@inproceedings{10.1007/978-3-031-06555-2_27,
|
60 |
author = {Maarand, Martin and Beyer, Yngvil and K\r{a}sen, Andre and Fosseide, Knut T. and Kermorvant, Christopher},
|