| import gradio as gr | |
| from transformers import pipeline | |
| # Load the model using pipeline | |
| pipe = pipeline("audio-classification", model="MelodyMachine/Deepfake-audio-detection-V2") | |
| # Define the prediction function | |
| def predict(audio): | |
| print("Audio file received:", audio) # Debugging statement | |
| try: | |
| result = pipe(audio) | |
| print("Raw prediction result:", result) # Debugging statement | |
| # Convert the result to the expected format | |
| output = {item['label']: item['score'] for item in result} | |
| print("Formatted prediction result:", output) # Debugging statement | |
| return output | |
| except Exception as e: | |
| print("Error during prediction:", e) # Debugging statement | |
| return {"error": str(e)} | |
| # Create the Gradio interface | |
| iface = gr.Interface( | |
| fn=predict, | |
| inputs=gr.Audio(type="filepath"), | |
| outputs=gr.Label(), | |
| title="Testing Deepfake Audio Detection Simple Interface", | |
| description="Upload an audio file or record your voice to detect if the audio is a deepfake." | |
| ) | |
| # Launch the interface | |
| iface.launch() | |