Update README.md
Browse files
README.md
CHANGED
@@ -20,13 +20,13 @@ datasets:
|
|
20 |
pipeline_tag: image-to-text
|
21 |
---
|
22 |
|
23 |
-
# PyLaia - PELLET Casimir Marius
|
24 |
|
25 |
This model performs Handwritten Text Recognition in French. Trained following [Teklia's tutorial](https://doc.arkindex.org/tutorial/).
|
26 |
|
27 |
## Model description
|
28 |
|
29 |
-
The model has been trained using the PyLaia library on the [PELLET Casimir Marius - Line level](Teklia/PELLET-Casimir-Marius-line) dataset.
|
30 |
|
31 |
Training images were resized with a fixed height of 128 pixels, keeping the original aspect ratio.
|
32 |
|
@@ -43,8 +43,8 @@ The model achieves the following results:
|
|
43 |
| set | CER (%) | WER (%) | text_line |
|
44 |
| :---- | ------: | ------: | --------: |
|
45 |
| train | 24.17 | 58.12 | 842 |
|
46 |
-
| val |
|
47 |
-
| test | 18.78 |
|
48 |
|
49 |
## How to use?
|
50 |
|
|
|
20 |
pipeline_tag: image-to-text
|
21 |
---
|
22 |
|
23 |
+
# PyLaia - PELLET Casimir Marius
|
24 |
|
25 |
This model performs Handwritten Text Recognition in French. Trained following [Teklia's tutorial](https://doc.arkindex.org/tutorial/).
|
26 |
|
27 |
## Model description
|
28 |
|
29 |
+
The model has been trained using the PyLaia library on the [PELLET Casimir Marius - Line level](https://huggingface.co/datasets/Teklia/PELLET-Casimir-Marius-line) dataset.
|
30 |
|
31 |
Training images were resized with a fixed height of 128 pixels, keeping the original aspect ratio.
|
32 |
|
|
|
43 |
| set | CER (%) | WER (%) | text_line |
|
44 |
| :---- | ------: | ------: | --------: |
|
45 |
| train | 24.17 | 58.12 | 842 |
|
46 |
+
| val | 22.90 | 58.75 | 125 |
|
47 |
+
| test | 18.78 | 50.00 | 122 |
|
48 |
|
49 |
## How to use?
|
50 |
|