Update app.py

app.py

@@ -19,7 +19,23 @@ model = AutoModelForTokenClassification.from_pretrained("d4data/biomedical-ner-a
 
 biomed_ner_pipe = pipeline("ner", model=model, tokenizer=tokenizer, aggregation_strategy="simple") # pass device=0 if using gpu
 
-
+def parse_ber(text):
+    raw = biomed_ner_pipe(text)
+    ner_content = {
+        "text": text,
+        "entities": [
+            {
+                "entity": x["entity_group"],
+                "word": x["word"],
+                "score": x["score"],
+                "start": x["start"],
+                "end": x["end"],
+            }
+            for x in raw
+        ]
+    }
+    return ner_content
+    
 def translate_and_classify(audio):
     
     print("""
@@ -44,8 +60,7 @@ def translate_and_classify(audio):
     print("Transcript: " + transcription.text)  
     print("Translated: " + translation.text)
     
-    result = biomed_ner_pipe(translation.text)
-    detected_ner = result
+    detected_ner = parse_ner(translation.text)
     print("Detected Named Entities: ", detected_ner)
     return transcription.text, detected_ner