Update app.py

app.py

@@ -70,7 +70,7 @@ We train the models on the same datasets for 660k steps using batch size = 16 an
 
 
 ## Evaluation results
-We evaluate the model on the same 505 validation Nahuatl sentences for a fair comparison. Finally, we report the results using chrf and sacrebleu hugging face metrics:
+We evaluate the models on the same 505 validation Nahuatl sentences for a fair comparison. Finally, we report the results using chrf and sacrebleu hugging face metrics:
 
 | English-Spanish pretraining  | Validation loss | BLEU | Chrf   |
 |:----------------------------:|:---------------:|:-----|-------:|