Update README.md
Browse files
README.md
CHANGED
|
@@ -30,7 +30,7 @@ The model has been trained using the PyLaia library on the [RIMES](https://tekli
|
|
| 30 |
Training images were resized with a fixed height of 128 pixels, keeping the original aspect ratio.
|
| 31 |
|
| 32 |
| set | lines |
|
| 33 |
-
|
| 34 |
| train | 10,188 |
|
| 35 |
| val | 1,138 |
|
| 36 |
| test | 778 |
|
|
@@ -42,7 +42,7 @@ An external 6-gram character language model can be used to improve recognition.
|
|
| 42 |
The model achieves the following results:
|
| 43 |
|
| 44 |
| set | Language model | CER (%) | WER (%) | lines |
|
| 45 |
-
|
| 46 |
| test | no | 4.53 | 15.06 | 778 |
|
| 47 |
| test | yes | 3.47 | 10.20 | 778 |
|
| 48 |
|
|
|
|
| 30 |
Training images were resized with a fixed height of 128 pixels, keeping the original aspect ratio.
|
| 31 |
|
| 32 |
| set | lines |
|
| 33 |
+
|:----- | ------: |
|
| 34 |
| train | 10,188 |
|
| 35 |
| val | 1,138 |
|
| 36 |
| test | 778 |
|
|
|
|
| 42 |
The model achieves the following results:
|
| 43 |
|
| 44 |
| set | Language model | CER (%) | WER (%) | lines |
|
| 45 |
+
|:------|:---------------| ----------:| -------:|--------:|
|
| 46 |
| test | no | 4.53 | 15.06 | 778 |
|
| 47 |
| test | yes | 3.47 | 10.20 | 778 |
|
| 48 |
|