Spaces:
Runtime error
Runtime error
| import gradio as gr | |
| from audioseal import AudioSeal | |
| import torch | |
| import numpy as np | |
| import traceback | |
| # Function to handle audio data as NumPy arrays | |
| def detect_watermark(audio_data, sample_rate): | |
| try: | |
| # Extract the audio array from the tuple (audio_data, sample_rate) | |
| audio_array, _ = audio_data | |
| # 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 2D (batch, channels, samples) for AudioSeal | |
| if waveform.ndim == 2: | |
| waveform = waveform.unsqueeze(0) | |
| # Initialize and use the AudioSeal detector | |
| detector = AudioSeal.load_detector("audioseal_detector_16bits") | |
| result, message = detector.detect_watermark(waveform, message_threshold=0.5) | |
| # Interpret and return the detection result | |
| detection_result = "AI-generated" if result else "genuine" | |
| return f"This audio is likely {detection_result} based on watermark detection." | |
| except Exception as e: | |
| error_message = f"An error occurred: {str(e)}" | |
| traceback_str = ''.join(traceback.format_tb(e.__traceback__)) | |
| full_error_message = f"{error_message}\n{traceback_str}" | |
| return full_error_message | |
| interface = gr.Interface(fn=detect_watermark, | |
| inputs=[gr.Audio(label="Upload your audio", type="numpy"), | |
| gr.Number(label="Sample Rate", value=44100, visible=False)], | |
| outputs="text", | |
| title="Deep Fake Defender: AI Voice Cloning Detection", | |
| description="Upload an audio file to check if it's AI-generated or genuine.") | |
| if __name__ == "__main__": | |
| interface.launch(debug=True) | |