Update app.py

app.py

@@ -1,35 +1,36 @@
 import gradio as gr
+import numpy as np
 from audio_features import extract_features_with_time_series
 from model_utils import load_model, prepare_input_for_model, interpret_prediction
 
-MODEL_PATH = "your_model.keras"
+MODEL_PATH = "best_audio_model.keras"
+
+# Load model once when the app starts
+
 model = load_model(MODEL_PATH)
 
-def predict(audio_filepath):
+def predict_audio(file_path):
 try:
-if audio_filepath is None:
-return {"error": "No audio file provided."}
+features = extract_features_with_time_series(file_path)
+if features is None:
+return {"Error": "Feature extraction failed. Please check the audio."}
 
 ```
-    feats = extract_features_with_time_series(audio_filepath)
-    if feats is None:
-        return {"error": "Feature extraction failed."}
-
-    X = prepare_input_for_model(feats, model)
-    raw_pred = model.predict(X)
-    return interpret_prediction(raw_pred)
-
+    input_data = prepare_input_for_model(features, model)
+    raw_pred = model.predict(input_data)
+    result = interpret_prediction(raw_pred)
+    return result
 except Exception as e:
-    return {"error": f"Prediction error: {e}"}
+    return {"Error": str(e)}
 ```
 
 iface = gr.Interface(
-fn=predict,
-inputs=gr.Audio(source="upload", type="filepath", label="Upload audio file"),
-outputs=gr.Label(num_top_classes=2, label="Prediction (probabilities)"),
-title="Deepfake Audio Detector",
-description="Upload an audio file (wav/mp3). The app extracts MFCC/LFCC/etc. features, then runs your .keras model."
+fn=predict_audio,
+inputs=gr.Audio(type="filepath", label="Upload an audio file"),
+outputs=gr.Label(num_top_classes=2, label="Prediction"),
+title="Audio Deepfake Detection",
+description="Upload an audio clip to detect whether it is Real or Fake using a Keras model."
 )
 
 if **name** == "**main**":
-iface.launch()
+iface.launch(server_name="0.0.0.0", server_port=7860)