Update README.md

README.md

@@ -33,7 +33,7 @@ widget:
 This is an uncased <b>BERT</b> <b>[1]</b> model for the <b>Italian</b> language, obtained using the uncased <b>mBERT</b> ([bert-base-multilingual-uncased](https://huggingface.co/bert-base-multilingual-uncased)) as a starting point and focusing it on the Italian language by modifying the embedding layer 
 (as in <b>[2]</b>, computing document-level frequencies over the <b>Wikipedia</b> dataset)
 
-The resulting model has 110M parameters, a vocabulary of 30.785 tokens, and a size of ~430 MB.
+The resulting model has 110M parameters, a vocabulary of 30.154 tokens, and a size of ~430 MB.
 
 <h3>Quick usage</h3>