Update app.py

app.py

@@ -8,6 +8,7 @@ import os
 from tensorflow.keras.models import load_model
 from faster_whisper import WhisperModel
 import random
+from textblob import TextBlob  # Added for sentiment analysis
 
 # Load the emotion prediction model
 def load_emotion_model(model_path):
@@ -66,6 +67,27 @@ def predict_emotion_from_audio(wav_filepath):
         print("Error predicting emotion:", e)
         return "Prediction error"
 
+# Function to analyze sentiment from text
+def analyze_sentiment(text):
+    try:
+        if not text or text.strip() == "":
+            return "No text to analyze", 0.0
+            
+        analysis = TextBlob(text)
+        polarity = analysis.sentiment.polarity
+        
+        if polarity > 0.1:
+            sentiment = "positive"
+        elif polarity < -0.1:
+            sentiment = "negative"
+        else:
+            sentiment = "neutral"
+            
+        return sentiment, polarity
+    except Exception as e:
+        print("Error analyzing sentiment:", e)
+        return "sentiment analysis error", 0.0
+
 api_key = os.getenv("DeepAI_api_key")
 
 # Function to generate an image using DeepAI Text to Image API
@@ -118,10 +140,13 @@ def get_predictions(audio_input):
     # Handle case where emotion_prediction might be None
     if emotion_prediction is None:
         emotion_prediction = "Unknown"
-        
+    
+    # Analyze sentiment of transcribed text
+    sentiment, polarity = analyze_sentiment(transcribed_text)
+    
     image = generate_image(emotion_prediction, transcribed_text)
     
-    return emotion_prediction, transcribed_text, image
+    return emotion_prediction, transcribed_text, f"Sentiment: {sentiment} (Polarity: {polarity:.2f})", image
 
 # Create the Gradio interface
 interface = gr.Interface(
@@ -130,10 +155,11 @@ interface = gr.Interface(
     outputs=[
         gr.Label(label="Acoustic Prediction"),
         gr.Label(label="Transcribed Text"),
+        gr.Label(label="Sentiment Analysis"),  # Added sentiment analysis output
         gr.Image(type='pil', label="Generated Image")
     ],
     title="Affective Virtual Environments",
-    description="Create an AVE using your voice."
+    description="Create an AVE using your voice. Get emotion prediction, transcription, sentiment analysis, and a generated image."
 )
 
 interface.launch()