y, sr = librosa.load('speechdft-16-8-mono-5secs.wav', sr=16000)
# ------------------------------------------------- # 3️⃣ Compute the DFT (via FFT) – only the positive frequencies # ------------------------------------------------- N = len(audio_float) # number of samples = 5 s × 16 kHz = 80 000 fft_vals = np.fft.rfft(audio_float) # real‑valued FFT → N/2+1 points fft_mag = np.abs(fft_vals) / N # normalise magnitude
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)
# Compute 13 MFCCs (typical default) mfccs = librosa.feature.mfcc(y=y, sr=sr_lib, n_mfcc=13, n_fft=512, hop_length=256)