output fixed

app.py

@@ -24,6 +24,17 @@ backends = [
 ]
 
 emotion_pipeline = pipeline("text-classification", model="cardiffnlp/twitter-roberta-base-emotion")
+sentiment_pipeline = pipeline("sentiment-analysis", model="distilbert-base-uncased-finetuned-sst-2-english")
+
+model = load_learner("gaze-recognizer-v3.pkl")
+
+def analyze_emotion(text):
+    result = emotion_pipeline(text)
+    return result
+
+def analyze_sentiment(text):
+    result = sentiment_pipeline(text)
+    return result
 
 def getTranscription(path):
     # Insert Local Video File Path
@@ -49,13 +60,6 @@ def getTranscription(path):
     transcription = processor.batch_decode(predicted_ids, skip_special_tokens=True)
     
     return transcription[0]
-    
-
-model = load_learner("gaze-recognizer-v3.pkl")
-
-def analyze_emotion(text):
-    result = emotion_pipeline(text)
-    return result
 
 def video_processing(video_file, encoded_video):
     angry = 0
@@ -82,7 +86,9 @@ def video_processing(video_file, encoded_video):
     print(transcription)
     text_emotion = analyze_emotion(transcription)
     print(text_emotion)
-    
+    text_sentiment = analyze_sentiment(transcription)
+    print(text_sentiment)
+
     video_capture = cv2.VideoCapture(video_file)
     on_camera = 0
     off_camera = 0
@@ -189,7 +195,8 @@ def video_processing(video_file, encoded_video):
     print(f'total sad percentage = {sad}')
     print(f'total surprise percentage = {surprise}')
     print(f'total neutral percentage = {neutral}')
-    return str(gaze_percentage)
+    final_result = "Gaze = "+str(gaze_percentage)+"Text Emotion"+str(text_emotion)+"Text transcription"+str(transcription)+"Text sentiment"+str(text_sentiment)
+    return final_result
 
 
 demo = gr.Interface(fn=video_processing,