Update app.py

app.py

@@ -110,15 +110,27 @@ def classify_toxicity(audio_file, classify_anxiety, emo_class, explitive_selecti
     # 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'])}
-
-    # plot.update(x=classification_df["labels"], y=classification_df["scores"])
-    if toxicity_score > threshold:
-        print("threshold exceeded!! Launch intervention")
-        affirm = positive_affirmations()
+    k = max(label_score_dict, value=label_score_dict.get)
+    maxval = label_score_dict[k]
+    if maxval > tox_score:
+        if maxval > threshold:
+            print("Toxic")
+            affirm = positive_affirmations()
+            topScore = maxval
+        else:
+            print("Not Toxic")
+            affirm = ""
+            topScore = maxval
     else:
-        affirm = ""
-
-    return transcribed_text, toxicity_score, label_score_dict, affirm
+        if tox_score > threshold:
+            affirm = positive_affirmations()
+            topScore = toxicity_score
+        else:
+            print("Not Toxic")
+            affirm = ""
+            topScore = toxicity_score
+
+    return transcribed_text, topScore, label_score_dict, affirm
     # return f"Toxicity Score ({available_models[selected_model]}): {toxicity_score:.4f}"
     
 def positive_affirmations():