app modified

app.py

@@ -267,7 +267,7 @@ class ModeloDataset:
             input_ids = torch.tensor(ids) 
             #model = RobertaForTokenClassification.from_pretrained("BSC-LT/roberta_model_for_anonimization")   
                    
-            model = AutoModelForTokenClassification.from_pretrained("BSC-LT/roberta_model_for_anonimization")
+            model = RobertaForTokenClassification.from_pretrained("BSC-LT/roberta_model_for_anonimization")
             with torch.no_grad():
              logits = model(input_ids).logits
             predicted_token_class_ids = logits.argmax(-1)
@@ -282,7 +282,7 @@ class ModeloDataset:
             #print(round(loss.item(), 2))
         else:
             
-            
+            print('idioma:',idioma)            
             tokenizer = AutoTokenizer.from_pretrained("FacebookAI/xlm-roberta-large-finetuned-conll03-english")
             tokenized_text=[tokenizer.tokenize(sentence) for sentence in _sentences]
         
@@ -291,7 +291,7 @@ class ModeloDataset:
             ids=pad_sequences(ids,maxlen=MAX_LEN,dtype="long",truncating="post", padding="post")
             input_ids = torch.tensor(ids) 
             
-            
+                    
             model = AutoModelForTokenClassification.from_pretrained("FacebookAI/xlm-roberta-large-finetuned-conll03-english")
             with torch.no_grad():
              logits = model(input_ids).logits
@@ -419,7 +419,7 @@ def procesar(texto,archivo):
             for item in df.columns.values:
                 sentences=df[item]
                 model.identificacion_idioma(sentences[0])
-                ides, predicted = modelo.aplicar_modelo(sentences,model.idioma)
+                ides, predicted = modelo.aplicar_modelo(sentences,"en")
                 out=modelo.salida_texto2( ides,predicted)
                 
                 df_new[item] = modelo.unir_array(out)
@@ -434,7 +434,7 @@ def procesar(texto,archivo):
                 for item in df.columns.values:
                     sentences=df[item]
                     print('item antes de aplicar modelo',item)
-                    ides, predicted = modelo.aplicar_modelo(sentences)
+                    ides, predicted = modelo.aplicar_modelo(sentences,"en")
                     print('despues de aplicar modelo')
                     out=modelo.salida_texto2( ides,predicted)