Update app.py

app.py

@@ -11,7 +11,7 @@ model = AutoModelForAudioClassification.from_pretrained("./")
 feature_extractor = ASTFeatureExtractor.from_pretrained("./")
 
 def plot_waveform(waveform, sr):
-    plt.figure(figsize=(10, 3))
+    plt.figure(figsize=(12, 3))  # Larger figure size
     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=(10, 4))
+    plt.figure(figsize=(12, 4))  # Larger figure size
     librosa.display.specshow(S_DB, sr=sr, x_axis='time', y_axis='mel')
     plt.title('Mel Spectrogram')
     plt.colorbar(format='%+2.0f dB')
@@ -53,27 +53,41 @@ 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 (
-            f"The voice is classified as '{label}' with a confidence of {confidence:.2f}%.",
-            waveform_plot,
-            spectrogram_plot
-        )
+        return prediction_text, 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="Prediction"),
+        gr.Textbox(label="Analysis", type="auto"),
         gr.Plot(label="Waveform"),
         gr.Plot(label="Spectrogram")
     ],
-    title="Voice Authenticity Detection",
-    description="Detects whether a voice is real or AI-generated. Upload an audio file to see the results."
+    layout="vertical",
+    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."
 )
 
-iface.launch()
+# Customize the CSS to adjust the layout and component sizes
+css = """
+      .gradio-container {
+        max-width: 960px; /* Adjust the maximum width as needed */
+      }
+      .input-container {
+        width: 25%; /* Smaller input area */
+      }
+      .output-container {
+        width: 74%; /* Larger output area */
+      }
+      """
+
+iface.launch(css=css)