src/preprocess_local.py

#this is the actual preprocess file. it is being replaced with a Huggging Face friendly one. if needed revert to this.

import librosa
import numpy as np

SAMPLE_RATE = 22050  
DURATION = 1.0       
SAMPLES_PER_SLICE = int(SAMPLE_RATE * DURATION)
N_MELS = 128         

def audio_to_spectrograms(file_path):
    try:
        y, sr = librosa.load(file_path, sr=SAMPLE_RATE)
        num_slices = len(y) // SAMPLES_PER_SLICE
        if num_slices < 1: return None

        spectrograms = []
        for i in range(num_slices):
            y_slice = y[i*SAMPLES_PER_SLICE : (i+1)*SAMPLES_PER_SLICE]
            spec = librosa.feature.melspectrogram(y=y_slice, sr=sr, n_mels=N_MELS)
            log_spec = librosa.power_to_db(spec, ref=np.max)
            norm_spec = np.clip((log_spec + 80) / 80, 0, 1)
            spectrograms.append(norm_spec[..., np.newaxis])
            
        return np.array(spectrograms)
    except Exception as e:
        print(f"Error: {e}")
        return None