Update app.py

app.py

@@ -22,38 +22,15 @@ def transcribe_long_form(filepath):
     return output["text"]
 
 ner = pipeline("ner",
-                   model="mrm8488/bert-spanish-cased-finetuned-ner",  # Modelo preentrenado para NER en español
-                   #tokenizer="mrm8488/bert-spanish-cased-finetuned-ner", 
-                   #aggregation_strategy="simple"  # Esto combina las etiquetas en entidades completas
-                   #max_length=512
+               model="mrm8488/bert-spanish-cased-finetuned-ner",
 )
 
-def merge_tokens(tokens):
-    merged_tokens = []
-    for token in tokens:
-        if merged_tokens and token['entity'].startswith('I-') and merged_tokens[-1]['entity'].endswith(token['entity'][2:]):
-            # If current token continues the entity of the last one, merge them
-            last_token = merged_tokens[-1]
-            last_token['word'] += token['word'].replace('##', '')
-            last_token['end'] = token['end']
-            last_token['score'] = (last_token['score'] + token['score']) / 2
-        else:
-            # Otherwise, add the token to the list
-            merged_tokens.append(token)
-
-    return merged_tokens
-
 def get_ner(input_text):
     if input_text is None:
         gr.Warning("No transcription found, please retry.")
         return {"text": "", "entities": ""}
-    print(input_text)
-    #output = get_ner(input_text, max_length=128)
     output = ner(input_text)
-    print(output)
-    merged_tokens = merge_tokens(output)
-    print(merged_tokens)
-    return {"text": input_text, "entities": merged_tokens}
+    return {"text": input_text, "entities": output}
 
 def main(filepath):
     transcription = transcribe_long_form(filepath)