utils/pitch_utils.py

#########
# world
##########
import librosa
import numpy as np
import torch

# gamma = 0
# mcepInput = 3  # 0 for dB, 3 for magnitude
# alpha = 0.45
# en_floor = 10 ** (-80 / 20)
# FFT_SIZE = 2048




def f0_to_coarse(f0,hparams):
    f0_bin = hparams['f0_bin']
    f0_max = hparams['f0_max']
    f0_min = hparams['f0_min']
    is_torch = isinstance(f0, torch.Tensor)
    f0_mel_min = 1127 * np.log(1 + f0_min / 700)
    f0_mel_max = 1127 * np.log(1 + f0_max / 700)
    f0_mel = 1127 * (1 + f0 / 700).log() if is_torch else 1127 * np.log(1 + f0 / 700)
    f0_mel[f0_mel > 0] = (f0_mel[f0_mel > 0] - f0_mel_min) * (f0_bin - 2) / (f0_mel_max - f0_mel_min) + 1

    f0_mel[f0_mel <= 1] = 1
    f0_mel[f0_mel > f0_bin - 1] = f0_bin - 1
    f0_coarse = (f0_mel + 0.5).long() if is_torch else np.rint(f0_mel).astype(int)
    assert f0_coarse.max() <= 255 and f0_coarse.min() >= 1, (f0_coarse.max(), f0_coarse.min())
    return f0_coarse


def norm_f0(f0, uv, hparams):
    is_torch = isinstance(f0, torch.Tensor)
    if hparams['pitch_norm'] == 'standard':
        f0 = (f0 - hparams['f0_mean']) / hparams['f0_std']
    if hparams['pitch_norm'] == 'log':
        f0 = torch.log2(f0) if is_torch else np.log2(f0)
    if uv is not None and hparams['use_uv']:
        f0[uv > 0] = 0
    return f0


def norm_interp_f0(f0, hparams):
    is_torch = isinstance(f0, torch.Tensor)
    if is_torch:
        device = f0.device
        f0 = f0.data.cpu().numpy()
    uv = f0 == 0
    f0 = norm_f0(f0, uv, hparams)
    if sum(uv) == len(f0):
        f0[uv] = 0
    elif sum(uv) > 0:
        f0[uv] = np.interp(np.where(uv)[0], np.where(~uv)[0], f0[~uv])
    uv = torch.FloatTensor(uv)
    f0 = torch.FloatTensor(f0)
    if is_torch:
        f0 = f0.to(device)
    return f0, uv


def denorm_f0(f0, uv, hparams, pitch_padding=None, min=None, max=None):
    if hparams['pitch_norm'] == 'standard':
        f0 = f0 * hparams['f0_std'] + hparams['f0_mean']
    if hparams['pitch_norm'] == 'log':
        f0 = 2 ** f0
    if min is not None:
        f0 = f0.clamp(min=min)
    if max is not None:
        f0 = f0.clamp(max=max)
    if uv is not None and hparams['use_uv']:
        f0[uv > 0] = 0
    if pitch_padding is not None:
        f0[pitch_padding] = 0
    return f0