Update app.py

app.py

@@ -30,7 +30,7 @@ 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, 6))
-    librosa.display.specshow(S_DB, sr=sr, x_axis='time', y_axis='mel')
+    librosa.display.specshow(S_DB, sr=sr, x_axis='time', y_axis='mel', cmap='inferno')
     plt.title('Mel Spectrogram')
     plt.colorbar(format='%+2.0f dB')
     plt.tight_layout()
@@ -94,18 +94,24 @@ def predict_voice(audio_file_path):
         return f"Error during processing: {e}", None, None, ""
 
 iface = gr.Interface(
-    fn=predict_voice,
-    inputs=gr.Audio(label="Upload Audio File", type="filepath"),
-    outputs=[
-        gr.Textbox(label="Prediction"),
-        gr.Textbox(label="Transcription"),  # Added comma here
-        gr.Image(label="Spectrogram"),
-        gr.Image(label="Waveform"),
-    ],
-    title="Voice Clone Detection",
-    description="Detects whether a voice is real or an AI-generated clone. Upload an audio file to see the results."
-)
+   with gr.Blocks(css="style.css") as demo:
+    gr.Markdown("## Voice Clone Detection")
+    gr.Markdown("Detects whether a voice is real or an AI-generated clone. Upload an audio file to see the results.")
+    
+    with gr.Row():
+        audio_input = gr.Audio(label="Upload Audio File", type="filepath")
 
-iface.launch()
+    with gr.Row():
+        prediction_output = gr.Textbox(label="Prediction")
+        waveform_output = gr.Image(label="Waveform")
+        spectrogram_output = gr.Image(label="Spectrogram")
+        transcription_output = gr.Textbox(label="Transcription")
 
+    detect_button = gr.Button("Detect Voice Clone")
+    detect_button.click(
+        fn=predict_voice,
+        inputs=audio_input,
+        outputs=[prediction_output, waveform_output, spectrogram_output, transcription_output]
+    )
 
+demo.launch()