Update app.py

app.py

@@ -33,7 +33,8 @@ def classify_toxicity(audio_file, text_input, classify_anxiety):
     else:
         transcribed_text = text_input
  
-    # Load the selected toxicity classification model
+    #### Toxicity Classifier ####
+        
     toxicity_module = evaluate.load("toxicity",  "facebook/roberta-hate-speech-dynabench-r4-target")
     #toxicity_module = evaluate.load("toxicity", 'DaNLP/da-electra-hatespeech-detection', module_type="measurement")
 
@@ -42,18 +43,20 @@ def classify_toxicity(audio_file, text_input, classify_anxiety):
     toxicity_score = toxicity_results["toxicity"][0]
     print(toxicity_score)
 
-    # Text classification 
+    #### Text classification #####
 
     device = torch.device("cuda") if torch.cuda.is_available() else torch.device("cpu")
 
-    classifiation_model = pipeline("zero-shot-classification", model="MoritzLaurer/mDeBERTa-v3-base-mnli-xnli")
+    text_classifier = pipeline("zero-shot-classification", model="MoritzLaurer/mDeBERTa-v3-base-mnli-xnli")
     
     sequence_to_classify = transcribed_text
     candidate_labels = classify_anxiety
-    classification_output = classifier(sequence_to_classify, candidate_labels, multi_label=False)
+    # classification_output = classifier(sequence_to_classify, candidate_labels, multi_label=False)
+    classification_output = text_classifier(sequence_to_classify, candidate_labels, multi_label=False)
     print(classification_output)
 
-    # Emotion classification
+    #### Emotion classification ####
+    
     emotion_classifier = foreign_class(source="speechbrain/emotion-recognition-wav2vec2-IEMOCAP", pymodule_file="custom_interface.py", classname="CustomEncoderWav2vec2Classifier")
     out_prob, score, index, text_lab = learner.classify_file(audio_file.name)