import math import numpy as np import librosa import vocoder.wavernn.hparams as hp from scipy.signal import lfilter import soundfile as sf def label_2_float(x, bits) : return 2 * x / (2**bits - 1.) - 1. def float_2_label(x, bits) : assert abs(x).max() <= 1.0 x = (x + 1.) * (2**bits - 1) / 2 return x.clip(0, 2**bits - 1) def load_wav(path) : return librosa.load(str(path), sr=hp.sample_rate)[0] def save_wav(x, path) : sf.write(path, x.astype(np.float32), hp.sample_rate) def split_signal(x) : unsigned = x + 2**15 coarse = unsigned // 256 fine = unsigned % 256 return coarse, fine def combine_signal(coarse, fine) : return coarse * 256 + fine - 2**15 def encode_16bits(x) : return np.clip(x * 2**15, -2**15, 2**15 - 1).astype(np.int16) mel_basis = None def linear_to_mel(spectrogram): global mel_basis if mel_basis is None: mel_basis = build_mel_basis() return np.dot(mel_basis, spectrogram) def build_mel_basis(): return librosa.filters.mel(hp.sample_rate, hp.n_fft, n_mels=hp.num_mels, fmin=hp.fmin) def normalize(S): return np.clip((S - hp.min_level_db) / -hp.min_level_db, 0, 1) def denormalize(S): return (np.clip(S, 0, 1) * -hp.min_level_db) + hp.min_level_db def amp_to_db(x): return 20 * np.log10(np.maximum(1e-5, x)) def db_to_amp(x): return np.power(10.0, x * 0.05) def spectrogram(y): D = stft(y) S = amp_to_db(np.abs(D)) - hp.ref_level_db return normalize(S) def melspectrogram(y): D = stft(y) S = amp_to_db(linear_to_mel(np.abs(D))) return normalize(S) def stft(y): return librosa.stft(y=y, n_fft=hp.n_fft, hop_length=hp.hop_length, win_length=hp.win_length) def pre_emphasis(x): return lfilter([1, -hp.preemphasis], [1], x) def de_emphasis(x): return lfilter([1], [1, -hp.preemphasis], x) def encode_mu_law(x, mu) : mu = mu - 1 fx = np.sign(x) * np.log(1 + mu * np.abs(x)) / np.log(1 + mu) return np.floor((fx + 1) / 2 * mu + 0.5) def decode_mu_law(y, mu, from_labels=True) : if from_labels: y = label_2_float(y, math.log2(mu)) mu = mu - 1 x = np.sign(y) / mu * ((1 + mu) ** np.abs(y) - 1) return x