Update

app.py

@@ -11,7 +11,7 @@ model = AutoModelForAudioClassification.from_pretrained("./")
 feature_extractor = ASTFeatureExtractor.from_pretrained("./")
 
 def plot_waveform(waveform, sr):
-    plt.figure(figsize=(12, 3))  # Larger figure size
+    plt.figure(figsize=(12, 4))  # Slightly larger plot for better visibility
     plt.title('Waveform')
     plt.ylabel('Amplitude')
     plt.plot(np.linspace(0, len(waveform) / sr, len(waveform)), waveform)
@@ -21,7 +21,7 @@ def plot_waveform(waveform, sr):
 def plot_spectrogram(waveform, sr):
     S = librosa.feature.melspectrogram(y=waveform, sr=sr, n_mels=128)
     S_DB = librosa.power_to_db(S, ref=np.max)
-    plt.figure(figsize=(12, 4))  # Larger figure size
+    plt.figure(figsize=(12, 6))  # Slightly larger plot for better visibility
     librosa.display.specshow(S_DB, sr=sr, x_axis='time', y_axis='mel')
     plt.title('Mel Spectrogram')
     plt.colorbar(format='%+2.0f dB')
@@ -53,29 +53,27 @@ def predict_voice(audio_file_path):
         label = model.config.id2label[predicted_index.item()]
         confidence = torch.softmax(logits, dim=1).max().item() * 100
         
-        prediction_text = (f"The model predicts the voice as '{label}'. "
-                           f"Confidence level: {confidence:.2f}%")
-        
         waveform_plot = plot_waveform(waveform, sample_rate)
         spectrogram_plot = plot_spectrogram(waveform, sample_rate)
         
-        return prediction_text, waveform_plot, spectrogram_plot
+        return (
+            f"The voice is classified as '{label}' with a confidence of {confidence:.2f}%.",
+            waveform_plot,
+            spectrogram_plot
+        )
     except Exception as e:
         return f"Error during processing: {e}", None, None
 
-# Define the Gradio app layout
 iface = gr.Interface(
     fn=predict_voice,
     inputs=gr.Audio(label="Upload Audio File", type="filepath"),
     outputs=[
-        gr.Textbox(label="Analysis", type="text"),  # Ensure type is correctly set to "text"
+        gr.Textbox(label="Prediction"),
         gr.Plot(label="Waveform"),
         gr.Plot(label="Spectrogram")
     ],
     title="Voice Clone Detection",
-    description="This tool determines whether a voice is real or an AI-generated clone. Audio files judged to be authentic and produced by humans are classified as 'Bonafide'. In contrast, those perceived to be synthetically generated are labeled as 'Spoof'. Upload an audio file for analysis."
-    # Removed the `layout` parameter
+    description="Detects whether a voice is real or an AI-generated clone. Upload an audio file to see the results."
 )
 
-# Assuming css is defined as provided in your message
-iface.launch(css=css)
+iface.launch()