starride-teklia
commited on
Commit
•
f7c489c
1
Parent(s):
c4cd9ff
Update README.md
Browse files
README.md
CHANGED
@@ -29,7 +29,7 @@ Training images were resized with a fixed height of 128 pixels, keeping the orig
|
|
29 |
| train | 52,834 |
|
30 |
| val | 4,667 |
|
31 |
|
32 |
-
An external 6-gram character language model can be used to improve recognition. The language model is trained on the text from the
|
33 |
|
34 |
## Evaluation results
|
35 |
|
|
|
29 |
| train | 52,834 |
|
30 |
| val | 4,667 |
|
31 |
|
32 |
+
An external 6-gram character language model can be used to improve recognition. The language model is trained on the text from the NewsEye training set.
|
33 |
|
34 |
## Evaluation results
|
35 |
|