-
Notifications
You must be signed in to change notification settings - Fork 619
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Release Vevo pre-trained models (#374)
- Loading branch information
Showing
26 changed files
with
3,486 additions
and
12 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -6,6 +6,7 @@ | |
| .vs | ||
| .vscode | ||
| .cache | ||
| pyrightconfig.json | ||
|
|
||
| # GitHub files | ||
| .github | ||
|
|
||
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,108 @@ | ||
| # Copyright (c) 2023 Amphion. | ||
| # | ||
| # This source code is licensed under the MIT license found in the | ||
| # LICENSE file in the root directory of this source tree. | ||
|
|
||
| import torch | ||
| import pyworld as pw | ||
| import numpy as np | ||
| import soundfile as sf | ||
| import os | ||
| from torchaudio.functional import pitch_shift | ||
| import librosa | ||
| from librosa.filters import mel as librosa_mel_fn | ||
| import torch.nn as nn | ||
| import torch.nn.functional as F | ||
| import tqdm | ||
|
|
||
|
|
||
| def dynamic_range_compression(x, C=1, clip_val=1e-5): | ||
| return np.log(np.clip(x, a_min=clip_val, a_max=None) * C) | ||
|
|
||
|
|
||
| def dynamic_range_decompression(x, C=1): | ||
| return np.exp(x) / C | ||
|
|
||
|
|
||
| def dynamic_range_compression_torch(x, C=1, clip_val=1e-5): | ||
| return torch.log(torch.clamp(x, min=clip_val) * C) | ||
|
|
||
|
|
||
| def dynamic_range_decompression_torch(x, C=1): | ||
| return torch.exp(x) / C | ||
|
|
||
|
|
||
| def spectral_normalize_torch(magnitudes): | ||
| output = dynamic_range_compression_torch(magnitudes) | ||
| return output | ||
|
|
||
|
|
||
| def spectral_de_normalize_torch(magnitudes): | ||
| output = dynamic_range_decompression_torch(magnitudes) | ||
| return output | ||
|
|
||
|
|
||
| class MelSpectrogram(nn.Module): | ||
| def __init__( | ||
| self, | ||
| n_fft, | ||
| num_mels, | ||
| sampling_rate, | ||
| hop_size, | ||
| win_size, | ||
| fmin, | ||
| fmax, | ||
| center=False, | ||
| ): | ||
| super(MelSpectrogram, self).__init__() | ||
| self.n_fft = n_fft | ||
| self.hop_size = hop_size | ||
| self.win_size = win_size | ||
| self.sampling_rate = sampling_rate | ||
| self.num_mels = num_mels | ||
| self.fmin = fmin | ||
| self.fmax = fmax | ||
| self.center = center | ||
|
|
||
| mel_basis = {} | ||
| hann_window = {} | ||
|
|
||
| mel = librosa_mel_fn( | ||
| sr=sampling_rate, n_fft=n_fft, n_mels=num_mels, fmin=fmin, fmax=fmax | ||
| ) | ||
| mel_basis = torch.from_numpy(mel).float() | ||
| hann_window = torch.hann_window(win_size) | ||
|
|
||
| self.register_buffer("mel_basis", mel_basis) | ||
| self.register_buffer("hann_window", hann_window) | ||
|
|
||
| def forward(self, y): | ||
| y = torch.nn.functional.pad( | ||
| y.unsqueeze(1), | ||
| ( | ||
| int((self.n_fft - self.hop_size) / 2), | ||
| int((self.n_fft - self.hop_size) / 2), | ||
| ), | ||
| mode="reflect", | ||
| ) | ||
| y = y.squeeze(1) | ||
| spec = torch.stft( | ||
| y, | ||
| self.n_fft, | ||
| hop_length=self.hop_size, | ||
| win_length=self.win_size, | ||
| window=self.hann_window, | ||
| center=self.center, | ||
| pad_mode="reflect", | ||
| normalized=False, | ||
| onesided=True, | ||
| return_complex=True, | ||
| ) | ||
| spec = torch.view_as_real(spec) | ||
|
|
||
| spec = torch.sqrt(spec.pow(2).sum(-1) + (1e-9)) | ||
|
|
||
| spec = torch.matmul(self.mel_basis, spec) | ||
| spec = spectral_normalize_torch(spec) | ||
|
|
||
| return spec |
Oops, something went wrong.