Update app.py

app.py

@@ -42,9 +42,14 @@ class_options = {
 
 pipe = pipeline("automatic-speech-recognition", model="openai/whisper-large")
 
+toxicity_module = evaluate.load("toxicity",  "facebook/roberta-hate-speech-dynabench-r4-target")
+emotion_classifier = foreign_class(source="speechbrain/emotion-recognition-wav2vec2-IEMOCAP", pymodule_file="custom_interface.py", classname="CustomEncoderWav2vec2Classifier")
+device = torch.device("cuda") if torch.cuda.is_available() else torch.device("cpu")
+text_classifier = pipeline("zero-shot-classification", model="facebook/bart-large-mnli")
+
 def classify_emotion(audio):
     #### Emotion classification ####
-    emotion_classifier = foreign_class(source="speechbrain/emotion-recognition-wav2vec2-IEMOCAP", pymodule_file="custom_interface.py", classname="CustomEncoderWav2vec2Classifier")
+    # EMO MODEL LINE emotion_classifier = foreign_class(source="speechbrain/emotion-recognition-wav2vec2-IEMOCAP", pymodule_file="custom_interface.py", classname="CustomEncoderWav2vec2Classifier")
     out_prob, score, index, text_lab = emotion_classifier.classify_file(audio)
     return  emo_dict[text_lab[0]]
 
@@ -80,22 +85,23 @@ def classify_toxicity(audio_file, classify_anxiety, emo_class, explitive_selecti
     
     #### Toxicity Classifier ####
         
-    toxicity_module = evaluate.load("toxicity",  "facebook/roberta-hate-speech-dynabench-r4-target")
+    # TOX MODEL LINE 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")
 
     toxicity_results = toxicity_module.compute(predictions=[transcribed_text])
  
     toxicity_score = toxicity_results["toxicity"][0]
     print(toxicity_score)
+    
     # emo call
     if emo_class != None:
         classify_emotion(audio_file)
 
     #### Text classification #####
     if classify_anxiety != None: 
-        device = torch.device("cuda") if torch.cuda.is_available() else torch.device("cpu")
+        # DEVICE LINE device = torch.device("cuda") if torch.cuda.is_available() else torch.device("cpu")
     
-        text_classifier = pipeline("zero-shot-classification", model="facebook/bart-large-mnli")
+        # CLASSIFICATION LINE text_classifier = pipeline("zero-shot-classification", model="facebook/bart-large-mnli")
     
         sequence_to_classify = transcribed_text
         print(classify_anxiety, class_options)