Update README (#4)

- Update README (270a68c945f05b4066e4e305e94dabbc9765270e)

README.md

@@ -14,35 +14,28 @@ datasets:
 - Teklia/Alcar
 ---
 
-# HOME-Alcar and Himanis handwritten text recognition
+# HOME-Alcar handwritten text recognition
 
-This model performs Handwritten Text Recognition in Latin.
+This model performs Handwritten Text Recognition in Latin on medieval documents.
 
 ## Model description
 
-The model has been trained using the PyLaia library on the [HOME-Alcar](https://zenodo.org/record/5600884) document images.
-The model was trained on images resized to a fixed height of 128 pixels, keeping the original aspect ratio.
+The model was trained using the PyLaia library on two medieval datasets:
+* [Himanis](https://demo.arkindex.org/browse/5000e248-a624-4df1-8679-1b34679817ef?top_level=true&folder=true) (French)
+* [HOME Alcar](https://demo.arkindex.org/browse/46b9b1f4-baeb-4342-a501-e2f15472a276?top_level=true&folder=true) (Latin)
 
-## Evaluation results
-
-The model achieves the following results:
+For training, text-lines were resized with a fixed height of 128 pixels, keeping the original aspect ratio.
 
-Himanis:
-
-| set   | CER (%)    | WER (%)   | support   |
-| ----- | ---------- | --------- | --------- |
-| train | 5.31       | 17.47     |   18503   |
-| val   | 10.37      | 27.63     |    2367   |
-| test  | 9.87       | 28.27     |    2241   |
+An external 6-gram character language model can be used to improve recognition. The language model is trained on the text from the HOME Alcar training set.
 
+## Evaluation results
 
-HOME-Alcar:
+The model achieves the following results:
 
-| set   | CER (%)    | WER (%)   | support   |
-| ----- | ---------- | --------- | --------- |
-| train | 4.74       | 17.29     |   59969   |
-| val   | 7.82       | 23.67     |    7905   |
-| test  | 8.34       | 24.57     |    6932   |
+| set   | Language model | CER (%)    | WER (%) | N lines   |
+|:------|:---------------|:----------:|:-------:|----------:|
+| test  | no             | 8.35       | 26.15   |      6932 |
+| test  | yes            | 7.85       | 23.20   |      6932 |
 
 ## How to use