Update app.py

app.py

@@ -2,110 +2,74 @@ import gradio as gr
 from transformers import pipeline
 import torch
 
-def load_models():
-    """Load and verify models with error checking"""
+def create_analyzers():
+    """Initialize speech and emotion analyzers"""
     try:
-        device = "cuda" if torch.cuda.is_available() else "cpu"
-        print(f"Using device: {device}")
-        
-        # Load Whisper for speech recognition
-        transcriber = pipeline(
+        # Use tiny whisper model for speed and reliability
+        speech_recognizer = pipeline(
             "automatic-speech-recognition",
-            model="openai/whisper-tiny",
-            device=device
+            model="openai/whisper-tiny.en",
+            chunk_length_s=30
         )
         
-        # Load emotion recognition model
-        emotion_analyzer = pipeline(
+        # Use smaller emotion classifier
+        emotion_classifier = pipeline(
             "text-classification",
-            model="j-hartmann/emotion-english-distilroberta-base",
-            device=device
+            model="SamLowe/roberta-base-go_emotions",
+            top_k=1
         )
         
-        return transcriber, emotion_analyzer
+        return speech_recognizer, emotion_classifier
     except Exception as e:
-        print(f"Error loading models: {str(e)}")
+        print(f"Model loading error: {e}")
         return None, None
 
-def analyze_audio(audio_path):
-    """
-    Analyze audio for emotional content with detailed output
-    """
-    if audio_path is None:
-        return "Please provide audio", "No audio detected"
-        
+def analyze_tone(audio_file):
+    """Analyze the emotional tone of speech"""
+    if audio_file is None:
+        return "No input", "N/A"
+    
     try:
-        # Load models
-        transcriber, emotion_analyzer = load_models()
-        if transcriber is None or emotion_analyzer is None:
-            return "Error loading models", "Model initialization failed"
-            
-        # 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"
+        # Get models
+        speech_recognizer, emotion_classifier = create_analyzers()
+        
+        # Transcribe audio
+        transcription = speech_recognizer(audio_file)
+        text = transcription["text"]
+        
+        if not text.strip():
+            return "No speech detected", "N/A"
             
+        print(f"Transcribed text: {text}")  # For debugging
+        
         # Analyze emotion
-        try:
-            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"Emotion analysis error: {str(e)}", "Analysis failed"
-            
+        result = emotion_classifier(text)[0][0]
+        emotion = result['label'].replace('_', ' ').title()
+        confidence = f"{result['score']:.1%}"
+        
+        return emotion, confidence
+        
     except Exception as e:
-        return f"Unexpected error: {str(e)}", "Process failed"
+        print(f"Analysis error: {e}")
+        return f"Error: {str(e)}", "N/A"
 
-# Create interface with better labeling
+# Create minimal interface
 interface = gr.Interface(
-    fn=analyze_audio,
-    inputs=gr.Audio(
-        sources=["microphone", "upload"],
-        type="filepath",
-        label="Record or Upload Audio"
-    ),
+    fn=analyze_tone,
+    inputs=[
+        gr.Audio(
+            sources=["microphone", "upload"],
+            type="filepath",
+            label="Audio Input"
+        )
+    ],
     outputs=[
-        gr.Textbox(label="Detected Emotion"),
-        gr.Textbox(label="Confidence Score")
+        gr.Textbox(label="Emotion"),
+        gr.Textbox(label="Confidence")
     ],
     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()
+    description="Record or upload audio to detect the emotional tone.",
 )
 
 if __name__ == "__main__":
-    interface.launch(
-        debug=True,
-        server_name="0.0.0.0",
-        server_port=7860,
-        share=True
-    )
+    interface.launch(server_name="0.0.0.0", share=True)