|
|
|
""" |
|
MIT License |
|
|
|
Copyright (c) 2023 Shivam Mehta |
|
|
|
Permission is hereby granted, free of charge, to any person obtaining a copy |
|
of this software and associated documentation files (the "Software"), to deal |
|
in the Software without restriction, including without limitation the rights |
|
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell |
|
copies of the Software, and to permit persons to whom the Software is |
|
furnished to do so, subject to the following conditions: |
|
|
|
The above copyright notice and this permission notice shall be included in all |
|
copies or substantial portions of the Software. |
|
|
|
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR |
|
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, |
|
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE |
|
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER |
|
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, |
|
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE |
|
SOFTWARE. |
|
""" |
|
|
|
import numpy as np |
|
import torch |
|
import torch.utils.data |
|
from librosa.filters import mel as librosa_mel_fn |
|
from scipy.io.wavfile import read |
|
|
|
MAX_WAV_VALUE = 32768.0 |
|
|
|
|
|
def load_wav(full_path): |
|
sampling_rate, data = read(full_path) |
|
return data, sampling_rate |
|
|
|
|
|
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 |
|
|
|
|
|
mel_basis = {} |
|
hann_window = {} |
|
|
|
|
|
def mel_spectrogram(y, n_fft, num_mels, sampling_rate, hop_size, win_size, fmin, fmax, center=False): |
|
if torch.min(y) < -1.0: |
|
print("min value is ", torch.min(y)) |
|
if torch.max(y) > 1.0: |
|
print("max value is ", torch.max(y)) |
|
|
|
global mel_basis, hann_window |
|
if f"{str(fmax)}_{str(y.device)}" not in mel_basis: |
|
mel = librosa_mel_fn(sr=sampling_rate, n_fft=n_fft, n_mels=num_mels, fmin=fmin, fmax=fmax) |
|
mel_basis[str(fmax) + "_" + str(y.device)] = torch.from_numpy(mel).float().to(y.device) |
|
hann_window[str(y.device)] = torch.hann_window(win_size).to(y.device) |
|
|
|
y = torch.nn.functional.pad( |
|
y.unsqueeze(1), (int((n_fft - hop_size) / 2), int((n_fft - hop_size) / 2)), mode="reflect" |
|
) |
|
y = y.squeeze(1) |
|
|
|
spec = torch.view_as_real( |
|
torch.stft( |
|
y, |
|
n_fft, |
|
hop_length=hop_size, |
|
win_length=win_size, |
|
window=hann_window[str(y.device)], |
|
center=center, |
|
pad_mode="reflect", |
|
normalized=False, |
|
onesided=True, |
|
return_complex=True, |
|
) |
|
) |
|
|
|
spec = torch.sqrt(spec.pow(2).sum(-1) + (1e-9)) |
|
|
|
spec = torch.matmul(mel_basis[str(fmax) + "_" + str(y.device)], spec) |
|
spec = spectral_normalize_torch(spec) |
|
|
|
return spec |
|
|
