Create app.py

app.py

@@ -0,0 +1,126 @@
+"""
+Voice Mood Detector - Simple version for Hugging Face
+"""
+import gradio as gr
+import numpy as np
+from transformers import pipeline
+import warnings
+warnings.filterwarnings("ignore")
+
+# Initialize the emotion detection model
+print("Loading emotion detection model...")
+try:
+    # Try the main model first
+    pipe = pipeline(
+        "audio-classification", 
+        model="ehcalabres/wav2vec2-lg-xlsr-en-speech-emotion-recognition"
+    )
+except:
+    # Fallback model if first fails
+    pipe = pipeline(
+        "audio-classification",
+        model="superb/wav2vec2-base-superb-ers"
+    )
+
+print("Model loaded successfully!")
+
+def analyze_audio(audio):
+    """
+    Analyze audio and return mood with confidence
+    audio: tuple of (sample_rate, audio_data) from Gradio
+    """
+    if audio is None:
+        return "🎤 No audio", "0%", "Please record or upload audio first"
+    
+    try:
+        # Get sample rate and audio data
+        sample_rate, audio_data = audio
+        
+        # Convert to mono if stereo
+        if len(audio_data.shape) > 1:
+            audio_data = np.mean(audio_data, axis=0)
+        
+        # Run prediction
+        predictions = pipe({
+            "raw": audio_data,
+            "sampling_rate": sample_rate
+        })
+        
+        # Get top result
+        top = predictions[0]
+        mood = top['label'].upper()
+        confidence = f"{top['score']*100:.1f}%"
+        
+        # Mood emoji mapping
+        emoji_map = {
+            "ANGER": "😠 Anger",
+            "DISGUST": "🤢 Disgust", 
+            "FEAR": "😨 Fear",
+            "HAPPY": "😊 Happy",
+            "NEUTRAL": "😐 Neutral",
+            "SADNESS": "😢 Sad",
+            "SURPRISE": "😲 Surprise"
+        }
+        
+        mood_display = emoji_map.get(mood, f"🎤 {mood}")
+        
+        # Create details
+        details = "All Predictions:\n"
+        for i, pred in enumerate(predictions[:5], 1):
+            details += f"{i}. {pred['label'].upper()}: {pred['score']*100:.1f}%\n"
+        
+        return mood_display, confidence, details
+        
+    except Exception as e:
+        return f"❌ Error", "0%", f"Analysis failed: {str(e)}"
+
+# Create Gradio interface
+with gr.Blocks(title="Voice Mood Detector", theme=gr.themes.Soft()) as demo:
+    gr.Markdown("# 🎤 Voice Mood Detector")
+    gr.Markdown("Record your voice or upload audio to detect emotional state")
+    
+    with gr.Row():
+        with gr.Column():
+            audio_input = gr.Audio(
+                sources=["microphone", "upload"],
+                type="numpy",
+                label="Speak or Upload Audio",
+                waveform_options={"show_controls": True}
+            )
+            btn = gr.Button("Analyze Mood 🎯", variant="primary")
+        
+        with gr.Column():
+            mood_output = gr.Textbox(label="Detected Mood", interactive=False)
+            confidence_output = gr.Textbox(label="Confidence", interactive=False)
+            details_output = gr.Textbox(
+                label="Detailed Results", 
+                lines=6,
+                interactive=False
+            )
+    
+    # Instructions
+    with gr.Accordion("📖 Instructions", open=False):
+        gr.Markdown("""
+        **How to use:**
+        1. Click microphone icon and speak for 3-5 seconds
+        2. OR upload an audio file (WAV/MP3)
+        3. Click "Analyze Mood"
+        4. View your emotional state
+        
+        **Tips for best results:**
+        - Speak clearly in English
+        - Keep background noise minimal
+        - Optimal length: 3-5 seconds
+        - Use mono audio if possible
+        """)
+    
+    # Set up button action
+    btn.click(
+        fn=analyze_audio,
+        inputs=audio_input,
+        outputs=[mood_output, confidence_output, details_output]
+    )
+
+# Launch the app
+if __name__ == "__main__":
+    demo.launch(debug=True)