Update app.py

app.py

@@ -1,56 +1,110 @@
 import gradio as gr
 import torch
-import torchaudio
-from torchaudio.transforms import Resample
-from transformers import AutoFeatureExtractor, AutoModelForAudioClassification
+from transformers import pipeline
 
-# Load the HF feature extractor and model
-feature_extractor = AutoFeatureExtractor.from_pretrained(
-    "MelodyMachine/Deepfake-audio-detection-V2"
-)
-model = AutoModelForAudioClassification.from_pretrained(
-    "MelodyMachine/Deepfake-audio-detection-V2"
-)
+# Initialize the pipeline
+pipe = pipeline("audio-classification", model="MelodyMachine/Deepfake-audio-detection-V2")
 
-TARGET_SR = feature_extractor.sampling_rate  # should be 16000
+def detect_deepfake(audio_file):
+    """
+    Detect if an audio file is deepfake or real
+    """
+    try:
+        if audio_file is None:
+            return "Please upload an audio file"
+        
+        # Run the classification
+        result = pipe(audio_file)
+        
+        # Format the results
+        predictions = {}
+        confidence_text = ""
+        
+        for item in result:
+            label = item['label']
+            score = item['score']
+            predictions[label] = score
+            confidence_text += f"{label}: {score:.4f} ({score*100:.2f}%)\n"
+        
+        # Determine the prediction
+        top_prediction = max(predictions, key=predictions.get)
+        confidence = predictions[top_prediction]
+        
+        # Create a more readable result
+        if 'fake' in top_prediction.lower() or 'deepfake' in top_prediction.lower():
+            main_result = f"⚠️ **DEEPFAKE DETECTED** (Confidence: {confidence*100:.1f}%)"
+            color = "red"
+        else:
+            main_result = f"✅ **REAL AUDIO** (Confidence: {confidence*100:.1f}%)"
+            color = "green"
+        
+        detailed_results = f"**Detailed Results:**\n{confidence_text}"
+        
+        return f"{main_result}\n\n{detailed_results}"
+        
+    except Exception as e:
+        return f"Error processing audio: {str(e)}"
 
-def detect_deepfake_audio(audio_path: str) -> str:
-    # Load audio file
-    waveform, orig_sr = torchaudio.load(audio_path)
-
-    # Mix to mono if necessary
-    if waveform.shape[0] > 1:
-        waveform = torch.mean(waveform, dim=0, keepdim=True)
-
-    # Resample if not already 16 kHz
-    if orig_sr != TARGET_SR:
-        resampler = Resample(orig_sr, TARGET_SR)
-        waveform = resampler(waveform)
-
-    # Prepare inputs
-    inputs = feature_extractor(
-        waveform, sampling_rate=TARGET_SR, return_tensors="pt"
+# Create the Gradio interface
+with gr.Blocks(title="Audio Deepfake Detection", theme=gr.themes.Soft()) as app:
+    gr.Markdown(
+        """
+        # 🎵 Audio Deepfake Detection
+        
+        Upload an audio file to detect if it's artificially generated (deepfake) or real.
+        
+        **Supported formats:** WAV, MP3, FLAC, M4A
+        """
     )
-    with torch.no_grad():
-        outputs = model(**inputs)
-
-    # Compute probabilities
-    probs = torch.softmax(outputs.logits, dim=-1)[0]
-    idx = torch.argmax(probs).item()
-    label = model.config.id2label[idx]
-    confidence = probs[idx].item()
-
-    return f"The audio is classified as **{label}** with confidence **{confidence:.2f}**"
-
-# Build the Gradio Blocks interface
-with gr.Blocks() as demo:
-    gr.Markdown("# Audio Deepfake Detection")
-    gr.Markdown("Upload an audio clip to check for deepfake content.")
-    audio_in = gr.Audio(type="filepath", label="Select Audio File")
-    txt_out = gr.Textbox(label="Result")
-    gr.Button("Detect").click(
-        fn=detect_deepfake_audio, inputs=audio_in, outputs=txt_out
+    
+    with gr.Row():
+        with gr.Column():
+            audio_input = gr.Audio(
+                label="Upload Audio File",
+                type="filepath",
+                sources=["upload"]
+            )
+            
+            detect_btn = gr.Button(
+                "🔍 Analyze Audio", 
+                variant="primary",
+                size="lg"
+            )
+        
+        with gr.Column():
+            output_text = gr.Textbox(
+                label="Detection Results",
+                lines=8,
+                max_lines=10,
+                interactive=False
+            )
+    
+    # Set up the event handler
+    detect_btn.click(
+        fn=detect_deepfake,
+        inputs=audio_input,
+        outputs=output_text
+    )
+    
+    # Also trigger on audio upload
+    audio_input.change(
+        fn=detect_deepfake,
+        inputs=audio_input,
+        outputs=output_text
+    )
+    
+    gr.Markdown(
+        """
+        ---
+        
+        **Note:** This model analyzes audio characteristics to detect artificial generation. 
+        Results are probabilities, not definitive proof.
+        """
     )
 
 if __name__ == "__main__":
-    demo.launch()
+    app.launch(
+        server_name="0.0.0.0",
+        server_port=7860,
+        share=False
+    )