Update app.py

app.py

@@ -36,15 +36,15 @@ pipe = pipeline("automatic-speech-recognition", model="openai/whisper-large")
 def slider_logic(slider):
     threshold = 0
     if slider == 1:
-        threshold = .98
-    elif slider == 2:
         threshold = .88
+    elif slider == 2:
+        threshold = .78
     elif slider == 3:
-        threshold = .77
+        threshold = .67
     elif slider == 4:
-        threshold = .66
+        threshold = .56
     elif slider == 5:
-        threshold = .55
+        threshold = .45
     else:
         threshold = []
     return threshold
@@ -96,29 +96,11 @@ def classify_toxicity(audio_file, selected_sounds, slider):
                 affirm = f"Threshold exceeded for class '{selected_class_name}': Score = {score:.4f}"
             else:
                 affirm = ""
-
-
-
-    '''
-    for class_name, score in class_score_dict.items():
-        if score > threshold:
-            print(f"Threshold exceeded for class '{class_name}': Score = {score:.4f}")
-    '''   
-    holder1 = {class_name: score for class_name, score in zip(class_names, scores)}
+                
     # miso_label_dict = {label: score for label, score in classify_anxiety[0].items()}
 
     return {class_name: score for class_name, score in zip(class_names, scores)}, affirm
     
-def positive_affirmations():
-    affirmations = [
-        "I have survived my anxiety before and I will survive again now",
-        "I am not in danger; I am just uncomfortable; this too will pass",
-        "I forgive and release the past and look forward to the future",
-        "I can't control what other people say but I can control my breathing and my response"
-    ]
-    selected_affirm = random.choice(affirmations)
-    return selected_affirm
-    
 with gr.Blocks() as iface:
     with gr.Column():
         miso_sounds = gr.CheckboxGroup(["chewing", "breathing", "mouthsounds", "popping", "sneezing", "yawning", "smacking", "sniffling", "panting"])