Update app.py

app.py

@@ -76,7 +76,7 @@ However, if only unanswerable questions are taken into account, the model with t
 As future work, the following experiments could be carried out:
 
 <ul>
-<li>Use Biomedical masked-language models that werw not generated from scratch from a Biomedical corpus but have been adapted from a general model, so as not to lose words and features of Spanish that are also present in biomedical questions and articles.
+<li>Use Biomedical masked-language models that were not generated from scratch from a Biomedical corpus but have been adapted from a general model, so as not to lose words and features of Spanish that are also present in Biomedical questions and articles.
 <li>Create a Biomedical training dataset with SQUAD v2 format..
 <li>Generate a new and  bigger validation dataset based on questions and contexts generated directly in Spanish and not translated as in SQUAD_Es v2.
 <li>Ensamble different models.