starride-teklia commited on
Commit
879b1df
1 Parent(s): 40c44e5

Update Readme

Browse files
Files changed (1) hide show
  1. README.md +30 -15
README.md CHANGED
@@ -1,21 +1,36 @@
1
- # PyLaia Rimes
 
 
 
 
 
 
 
 
 
 
 
 
2
 
3
- ## Datasets
4
 
5
- Trained on text-lines from the [Rimes 2011 dataset](https://teklia.com/research/rimes-database/).
6
 
7
- | split | N lines |
8
- |--------|--------:|
9
- | train | 10,188 |
10
- | val | 1,138 |
11
- | test | 778 |
12
 
13
- ## Results
 
14
 
15
- * Fixed line height: 128 pixels
16
- * Language model: 6-gram character model trained on the training set with KenLM
17
 
18
- | Model | val CER | test CER | val WER | test WER |
19
- |:--------------------------------|--------:|---------:|--------:|---------:|
20
- | Model without LM | 4.55 | 4.53 | 14.39 | 15.06 |
21
- | Model with LM (`weight = 1.5`) | 3.68 | 3.47 | 10.01 | 10.20 |
 
 
 
 
 
 
 
 
 
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
+ - fr
13
+ ---
14
 
15
+ # French handwritten text recognition
16
 
17
+ This model performs Handwritten Text Recognition in French.
18
 
19
+ ## Model description
 
 
 
 
20
 
21
+ The model has been trained using the PyLaia library on the [RIMES](https://teklia.com/research/rimes-database/) dataset.
22
+ Training images were resized with a fixed height of 128 pixels, keeping the original aspect ratio.
23
 
 
 
24
 
25
+ ## Evaluation results
26
+
27
+ The model achieves the following results:
28
+
29
+ | set | Language model | CER (%) | WER (%) | N lines |
30
+ |:------|:---------------|:----------:|:-------:|----------:|
31
+ | test | no | 4.53 | 15.06 | 778 |
32
+ | test | yes | 3.47 | 10.20 | 778 |
33
+
34
+ ## How to use
35
+
36
+ Please refer to the [documentation](https://atr.pages.teklia.com/pylaia/).