| import numpy as np | |
| import torch | |
| f0_bin = 256 | |
| f0_max = 1100.0 | |
| f0_min = 50.0 | |
| f0_mel_min = 1127 * np.log(1 + f0_min / 700) | |
| f0_mel_max = 1127 * np.log(1 + f0_max / 700) | |
| def coarse_to_f0(coarse): | |
| uv = coarse == 1 | |
| f0_mel = (coarse - 1) * (f0_mel_max - f0_mel_min) / (f0_bin - 2) + f0_mel_min | |
| f0 = ((f0_mel / 1127).exp() - 1) * 700 | |
| f0[uv] = 0 | |
| return f0 | |
| def f0_to_coarse(f0): | |
| is_torch = isinstance(f0, torch.Tensor) | |
| 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(np.int_) | |
| assert f0_coarse.max() <= 255 and f0_coarse.min() >= 1, (f0_coarse.max(), f0_coarse.min(), f0.min(), f0.max()) | |
| 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 + 1e-8) if is_torch else np.log2(f0 + 1e-8) | |
| if uv is not None and hparams['use_uv']: | |
| f0[uv > 0] = 0 | |
| return f0 |