Update README.md

README.md

@@ -87,7 +87,7 @@ The was trained on a combination of the following datasets:
 
 #### Tokenization
 
- All data is tokenized using sentencepiece, using 50 thousand token sentencepiece model  learned from the combination of all filtered training data. This model is included.  
+ All data is tokenized using sentencepiece, with 50 thousand token sentencepiece model  learned from the combination of all filtered training data. This model is included.  
 
 #### Hyperparameters
 
@@ -130,7 +130,7 @@ Below are the evaluation results on the machine translation from Catalan to Chin
 | Test set             | SoftCatalà | Google Translate | mt-aina-ca-es |
 |----------------------|------------|------------------|---------------|
 | Spanish Constitution | 66,2       | **77,1**         | 75,5          |
-| United Nations       | 72         | 84,3             | **86,3**      |
+| United Nations       | 72,0       | 84,3             | **86,3**      |
 | aina_aapp            | 78,1       | 80,8             | **81,8**      |
 | Flores 101 dev       | 23,8       | 24               | **24,1**      |
 | Flores 101 devtest   | 23,9       | 24,2             | **24,4**      |