Update app.py

app.py

@@ -3,6 +3,7 @@ from transformers import AutoFeatureExtractor, AutoModelForAudioClassification
 import numpy as np
 import torch
 from torch.nn.functional import softmax
+import librosa
 import soundfile as sf
 
 # Path to the local directory where the model files are stored within the Space
@@ -17,14 +18,18 @@ def predict_voice(audio_file_path):
     Predicts whether a voice is real or spoofed from an audio file.
     
     Args:
-        audio_file_path: The file path of the uploaded audio file to be classified.
+        audio_file_path: The path to the input audio file to be classified.
     
     Returns:
         A string with the prediction and confidence level.
     """
     
-    # Load the audio file. Adjust the loading mechanism based on your audio file format.
-    waveform, sample_rate = sf.read(audio_file_path)
+    # Load the audio file. librosa automatically resamples to the target sample rate if needed.
+    waveform, sample_rate = librosa.load(audio_file_path, sr=16000)  # Force resampling to 16000 Hz
+
+    # Ensure waveform is mono
+    if len(waveform.shape) > 1:
+        waveform = np.mean(waveform, axis=0)
 
     # Convert the input audio file to model's expected format.
     inputs = extractor(waveform, return_tensors="pt", sampling_rate=sample_rate)
@@ -47,14 +52,17 @@ def predict_voice(audio_file_path):
     result = f"The voice is classified as '{label}' with a confidence of {confidence:.2f}%."
     return result
 
+# Setting up the Gradio interface
 iface = gr.Interface(
     fn=predict_voice,
-    inputs=gr.Audio(type="filepath", label="Upload Audio File"),  # Ensure filepath is passed
+    inputs=gr.Audio(source="upload", type="filepath", label="Upload Audio File"),
     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.",
     theme="huggingface"
 )
 
-# Run the Gradio interface
+# Run the Gradio interface with share=True for creating a public link
+iface.launch(share=True)
+io interface
 iface.launch()