Update app.py

app.py

@@ -5,82 +5,103 @@ import torch
 def load_models():
     """Load and verify models with error checking"""
     try:
-        # Check CUDA availability
         device = "cuda" if torch.cuda.is_available() else "cpu"
         print(f"Using device: {device}")
         
-        # Load a smaller Whisper model for better compatibility
+        # Load Whisper for speech recognition
         transcriber = pipeline(
             "automatic-speech-recognition",
             model="openai/whisper-tiny",
             device=device
         )
         
-        # Load a simpler sentiment model
-        sentiment = pipeline(
-            "sentiment-analysis",
-            model="distilbert-base-uncased-finetuned-sst-2-english",
+        # Load emotion recognition model
+        emotion_analyzer = pipeline(
+            "text-classification",
+            model="j-hartmann/emotion-english-distilroberta-base",
             device=device
         )
         
-        return transcriber, sentiment
+        return transcriber, emotion_analyzer
     except Exception as e:
         print(f"Error loading models: {str(e)}")
         return None, None
 
 def analyze_audio(audio_path):
     """
-    Analyze audio tone with robust error handling
+    Analyze audio for emotional content with detailed output
     """
     if audio_path is None:
-        return "Please provide an audio input", "No audio detected"
+        return "Please provide audio", "No audio detected"
         
     try:
         # Load models
-        transcriber, sentiment = load_models()
-        if transcriber is None or sentiment is None:
+        transcriber, emotion_analyzer = load_models()
+        if transcriber is None or emotion_analyzer is None:
             return "Error loading models", "Model initialization failed"
             
-        # Transcribe with error checking
+        # Transcribe speech
         try:
             result = transcriber(audio_path)
             text = result["text"]
             if not text.strip():
                 return "No speech detected", "Empty transcription"
+            print(f"Transcribed text: {text}")  # Debug output
         except Exception as e:
             return f"Transcription error: {str(e)}", "Failed to process audio"
             
-        # Analyze sentiment
+        # Analyze emotion
         try:
-            sentiment_result = sentiment(text)[0]
-            tone = sentiment_result["label"]
-            confidence = f"{sentiment_result['score']:.2%}"
-            return tone, confidence
+            emotion_result = emotion_analyzer(text)[0]
+            emotion = emotion_result["label"].title()  # Capitalize emotion
+            confidence = f"{emotion_result['score']:.2%}"
+            
+            # Map technical emotion labels to more natural descriptions
+            emotion_mapping = {
+                "Joy": "Happy/Joyful",
+                "Sadness": "Sad/Melancholic",
+                "Anger": "Angry/Frustrated",
+                "Fear": "Anxious/Fearful",
+                "Surprise": "Surprised/Astonished",
+                "Love": "Warm/Affectionate",
+                "Neutral": "Neutral/Calm"
+            }
+            
+            display_emotion = emotion_mapping.get(emotion, emotion)
+            return display_emotion, confidence
+            
         except Exception as e:
-            return f"Sentiment analysis error: {str(e)}", "Analysis failed"
+            return f"Emotion analysis error: {str(e)}", "Analysis failed"
             
     except Exception as e:
         return f"Unexpected error: {str(e)}", "Process failed"
 
-# Create interface with simplified components
+# Create interface with better labeling
 interface = gr.Interface(
     fn=analyze_audio,
     inputs=gr.Audio(
         sources=["microphone", "upload"],
         type="filepath",
+        label="Record or Upload Audio"
     ),
     outputs=[
-        gr.Textbox(label="Tone"),
-        gr.Textbox(label="Confidence Level")
+        gr.Textbox(label="Detected Emotion"),
+        gr.Textbox(label="Confidence Score")
     ],
-    title="Simple Speech Tone Analyzer",
-    description="Record or upload audio to analyze its tone. The analysis may take a few moments.",
-    examples=None,
-    cache_examples=False,
-    theme=gr.themes.Base(),
+    title="Speech Emotion Analyzer",
+    description="""
+    This tool analyzes the emotional tone of speech, detecting emotions like:
+    - Happy/Joyful
+    - Sad/Melancholic
+    - Angry/Frustrated
+    - Anxious/Fearful
+    - Surprised/Astonished
+    - Warm/Affectionate
+    - Neutral/Calm
+    """,
+    theme=gr.themes.Base()
 )
 
-# Launch with specific parameters for better stability
 if __name__ == "__main__":
     interface.launch(
         debug=True,