Speechdft-16-8-mono-5secs.wav -

S = librosa.feature.melspectrogram(y=y, sr=sr, n_fft=n_fft, hop_length=hop_len, n_mels=n_mels, fmax=sr/2) log_S = librosa.power_to_db(S, ref=np.max)

import numpy as np from scipy.io import wavfile import matplotlib.pyplot as plt speechdft-16-8-mono-5secs.wav

# ------------------------------------------------- # 2️⃣ Convert 8‑bit unsigned PCM to float [-1, 1] # ------------------------------------------------- # 8‑bit PCM in wav files is typically unsigned (0‑255) audio_float = (audio_int.astype(np.float32) - 128) / 128.0 # now in [-1, 1] S = librosa

y, sr = librosa.load('speechdft-16-8-mono-5secs.wav', sr=16000) S = librosa.feature.melspectrogram(y=y