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

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

# ------------------------------------------------- # 1️⃣ Load the wav file # ------------------------------------------------- sr, audio_int = wavfile.read('speechdft-16-8-mono-5secs.wav') print(f'Sample rate: sr Hz') print(f'Data type: audio_int.dtype, shape: audio_int.shape') speechdft-16-8-mono-5secs.wav

# ------------------------------------------------- # 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 y, sr = librosa

# Parameters n_fft = 1024 hop_len = 512 n_mels = 40 sr = librosa.load('speechdft-16-8-mono-5secs.wav'