Update app.py

app.py

@@ -93,42 +93,50 @@ def classify_toxicity(audio_file, classify_anxiety, emo_class, explitive_selecti
         classify_emotion(audio_file)
 
     #### Text classification #####
-
-    device = torch.device("cuda") if torch.cuda.is_available() else torch.device("cpu")
-
-    text_classifier = pipeline("zero-shot-classification", model="facebook/bart-large-mnli")
-
-    sequence_to_classify = transcribed_text
-    print(classify_anxiety, class_options)
-    candidate_labels = class_options.get(classify_anxiety, [])
-    # classification_output = classifier(sequence_to_classify, candidate_labels, multi_label=False)
-    classification_output = text_classifier(sequence_to_classify, candidate_labels, multi_label=True)
-    print("class output ", type(classification_output))
-    # classification_df = pd.DataFrame.from_dict(classification_output)
-    print("keys ", classification_output.keys())
+    if classify_anxiety != None: 
+        device = torch.device("cuda") if torch.cuda.is_available() else torch.device("cpu")
     
-    # formatted_classification_output = "\n".join([f"{key}: {value}" for key, value in classification_output.items()])
-    # label_score_pairs = [(label, score) for label, score in zip(classification_output['labels'], classification_output['scores'])]
-    label_score_dict = {label: score for label, score in zip(classification_output['labels'], classification_output['scores'])}
-    k = max(label_score_dict, key=label_score_dict.get)
-    maxval = label_score_dict[k]
-    if maxval > toxicity_score:
-        if maxval > threshold:
-            print("Toxic")
-            affirm = positive_affirmations()
-            topScore = maxval
+        text_classifier = pipeline("zero-shot-classification", model="facebook/bart-large-mnli")
+    
+        sequence_to_classify = transcribed_text
+        print(classify_anxiety, class_options)
+        candidate_labels = class_options.get(classify_anxiety, [])
+        # classification_output = classifier(sequence_to_classify, candidate_labels, multi_label=False)
+        classification_output = text_classifier(sequence_to_classify, candidate_labels, multi_label=True)
+        print("class output ", type(classification_output))
+        # classification_df = pd.DataFrame.from_dict(classification_output)
+        print("keys ", classification_output.keys())
+        
+        # formatted_classification_output = "\n".join([f"{key}: {value}" for key, value in classification_output.items()])
+        # label_score_pairs = [(label, score) for label, score in zip(classification_output['labels'], classification_output['scores'])]
+        label_score_dict = {label: score for label, score in zip(classification_output['labels'], classification_output['scores'])}
+        k = max(label_score_dict, key=label_score_dict.get)
+        maxval = label_score_dict[k]
+        if maxval > toxicity_score:
+            if maxval > threshold:
+                print("Toxic")
+                affirm = positive_affirmations()
+                topScore = maxval
+            else:
+                print("Not Toxic")
+                affirm = ""
+                topScore = maxval
         else:
-            print("Not Toxic")
-            affirm = ""
-            topScore = maxval
+            if toxicity_score > threshold:
+                affirm = positive_affirmations()
+                topScore = toxicity_score
+            else:
+                print("Not Toxic")
+                affirm = ""
+                topScore = toxicity_score
     else:
-        if toxicity_score > threshold:
+        if toxixity_score > threshold:
             affirm = positive_affirmations()
             topScore = toxicity_score
         else:
-            print("Not Toxic")
             affirm = ""
             topScore = toxicity_score
+        label_score_dict = {"toxicity" : toxicity_score}
 
     return transcribed_text, topScore, label_score_dict, affirm
     # return f"Toxicity Score ({available_models[selected_model]}): {toxicity_score:.4f}"