Update app.py

app.py

@@ -1,35 +1,16 @@
 import gradio as gr
 from audioseal import AudioSeal
 import torch
-import numpy as np
-import traceback
+import torchaudio
 
-def detect_watermark(audio_data):
+def detect_watermark(audio_filepath):
     try:
-        # Ensure that audio_data is a tuple with two elements
-        if not (isinstance(audio_data, tuple) and len(audio_data) == 2):
-            return f"Invalid input: expected a tuple with two elements, got {type(audio_data)} with length {len(audio_data)}"
-        
-        # Ensure the first element of the tuple is a NumPy array
-        audio_array, sample_rate = audio_data
-        if not isinstance(audio_array, np.ndarray):
-            return f"Invalid input: expected the first element of the tuple to be a np.ndarray, got {type(audio_array)}"
-        
-        # Ensure the second element of the tuple is an integer (sample rate)
-        if not isinstance(sample_rate, int):
-            return f"Invalid input: expected the second element of the tuple to be an int (sample rate), got {type(sample_rate)}"
-
-        # Now we can proceed with the assurance that audio_array is an np.ndarray and sample_rate is an int
-        # Ensure audio_array is 2D (channels, samples). If it's mono, add an axis.
-        if audio_array.ndim == 1:
-            audio_array = np.expand_dims(audio_array, axis=0)
-
-        # Convert NumPy array to tensor
-        waveform = torch.tensor(audio_array, dtype=torch.float32)
-
-        # Ensure waveform is 3D (batch, channels, samples) for AudioSeal
+        # Load the audio file using torchaudio
+        waveform, sample_rate = torchaudio.load(audio_filepath)
+
+        # Ensure waveform is 2D (channels, samples). If it's mono, add an axis.
         if waveform.ndim == 2:
-            waveform = waveform.unsqueeze(0)
+            waveform = waveform.unsqueeze(0)  # Add batch dimension
 
         # Initialize and use the AudioSeal detector
         detector = AudioSeal.load_detector("audioseal_detector_16bits")
@@ -40,14 +21,13 @@ def detect_watermark(audio_data):
         return f"This audio is likely {detection_result} based on watermark detection."
 
     except Exception as e:
-        # Capture the full traceback in case of an error and return it as a string
-        error_traceback = traceback.format_exc()
-        return f"Error occurred: {str(e)}\n\n{error_traceback}"
+        # Return the error message directly
+        return f"Error occurred: {e}"
 
 # Define Gradio interface
 interface = gr.Interface(
     fn=detect_watermark,
-    inputs=gr.Audio(label="Upload your audio", type="numpy"),
+    inputs=gr.Audio(label="Upload your audio", type="filepath"),
     outputs="text",
     title="Deep Fake Defender: AI Voice Cloning Detection",
     description="Upload an audio file to check if it's AI-generated or genuine."
@@ -55,3 +35,4 @@ interface = gr.Interface(
 
 if __name__ == "__main__":
     interface.launch()
+