preprocess.py

import librosa
import torch

def preprocess(audio_file):
    # Load the audio file
    y, sr = librosa.load(audio_file, sr=None)
    mfccs = librosa.feature.mfcc(y=y, sr=sr, n_mfcc=13)
    tensor  = torch.from_numpy(mfccs)[None]
    return tensor