Update app.py

app.py

@@ -21,11 +21,11 @@ def predict_voice(audio_file):
     Returns:
         A string with the prediction and confidence level.
     """
+    # Gradio passes the audio file as a tuple (file_name, file_path). We only need the file_path.
+    audio_file_path = audio_file[1]
+
     # Convert the input audio file to model's expected format.
-    # The following code assumes your audio file is a numpy array.
-    # You may need to modify this depending on how the audio file is being read.
-    waveform = np.array(audio_file)
-    inputs = extractor(waveform, return_tensors="pt", sampling_rate=extractor.sampling_rate)
+    inputs = extractor(audio_file_path, return_tensors="pt", sampling_rate=extractor.sampling_rate)
     
     # Generate predictions from the model.
     with torch.no_grad():  # Ensure no gradients are calculated
@@ -48,7 +48,7 @@ def predict_voice(audio_file):
 # Setting up the Gradio interface
 iface = gr.Interface(
     fn=predict_voice,
-    inputs=gr.Audio(source="upload", type="file", label="Upload Audio File"),
+    inputs=gr.Audio(type="filepath", label="Upload Audio File"),  # Corrected usage
     outputs=gr.Textbox(label="Prediction"),
     title="Voice Authenticity Detection",
     description="Detects whether a voice is real or AI-generated. Upload an audio file to see the results.",