chore: vendor selva_core from jnwnlee/selva@d7d40a9
Pure PyTorch SelVA source for SelvaModelLoader/FeatureExtractor/Sampler nodes. Imports rewritten from selva.* to selva_core.*. mel_converter.py: replaced librosa.filters.mel with pure-numpy implementation to avoid librosa→numba→NumPy version incompatibility in some ComfyUI environments. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
@@ -0,0 +1,21 @@
|
||||
MIT License
|
||||
|
||||
Copyright (c) 2022 NVIDIA CORPORATION.
|
||||
|
||||
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.
|
||||
@@ -0,0 +1 @@
|
||||
from .bigvgan import BigVGAN
|
||||
@@ -0,0 +1,120 @@
|
||||
# Implementation adapted from https://github.com/EdwardDixon/snake under the MIT license.
|
||||
# LICENSE is in incl_licenses directory.
|
||||
|
||||
import torch
|
||||
from torch import nn, sin, pow
|
||||
from torch.nn import Parameter
|
||||
|
||||
|
||||
class Snake(nn.Module):
|
||||
'''
|
||||
Implementation of a sine-based periodic activation function
|
||||
Shape:
|
||||
- Input: (B, C, T)
|
||||
- Output: (B, C, T), same shape as the input
|
||||
Parameters:
|
||||
- alpha - trainable parameter
|
||||
References:
|
||||
- This activation function is from this paper by Liu Ziyin, Tilman Hartwig, Masahito Ueda:
|
||||
https://arxiv.org/abs/2006.08195
|
||||
Examples:
|
||||
>>> a1 = snake(256)
|
||||
>>> x = torch.randn(256)
|
||||
>>> x = a1(x)
|
||||
'''
|
||||
def __init__(self, in_features, alpha=1.0, alpha_trainable=True, alpha_logscale=False):
|
||||
'''
|
||||
Initialization.
|
||||
INPUT:
|
||||
- in_features: shape of the input
|
||||
- alpha: trainable parameter
|
||||
alpha is initialized to 1 by default, higher values = higher-frequency.
|
||||
alpha will be trained along with the rest of your model.
|
||||
'''
|
||||
super(Snake, self).__init__()
|
||||
self.in_features = in_features
|
||||
|
||||
# initialize alpha
|
||||
self.alpha_logscale = alpha_logscale
|
||||
if self.alpha_logscale: # log scale alphas initialized to zeros
|
||||
self.alpha = Parameter(torch.zeros(in_features) * alpha)
|
||||
else: # linear scale alphas initialized to ones
|
||||
self.alpha = Parameter(torch.ones(in_features) * alpha)
|
||||
|
||||
self.alpha.requires_grad = alpha_trainable
|
||||
|
||||
self.no_div_by_zero = 0.000000001
|
||||
|
||||
def forward(self, x):
|
||||
'''
|
||||
Forward pass of the function.
|
||||
Applies the function to the input elementwise.
|
||||
Snake ∶= x + 1/a * sin^2 (xa)
|
||||
'''
|
||||
alpha = self.alpha.unsqueeze(0).unsqueeze(-1) # line up with x to [B, C, T]
|
||||
if self.alpha_logscale:
|
||||
alpha = torch.exp(alpha)
|
||||
x = x + (1.0 / (alpha + self.no_div_by_zero)) * pow(sin(x * alpha), 2)
|
||||
|
||||
return x
|
||||
|
||||
|
||||
class SnakeBeta(nn.Module):
|
||||
'''
|
||||
A modified Snake function which uses separate parameters for the magnitude of the periodic components
|
||||
Shape:
|
||||
- Input: (B, C, T)
|
||||
- Output: (B, C, T), same shape as the input
|
||||
Parameters:
|
||||
- alpha - trainable parameter that controls frequency
|
||||
- beta - trainable parameter that controls magnitude
|
||||
References:
|
||||
- This activation function is a modified version based on this paper by Liu Ziyin, Tilman Hartwig, Masahito Ueda:
|
||||
https://arxiv.org/abs/2006.08195
|
||||
Examples:
|
||||
>>> a1 = snakebeta(256)
|
||||
>>> x = torch.randn(256)
|
||||
>>> x = a1(x)
|
||||
'''
|
||||
def __init__(self, in_features, alpha=1.0, alpha_trainable=True, alpha_logscale=False):
|
||||
'''
|
||||
Initialization.
|
||||
INPUT:
|
||||
- in_features: shape of the input
|
||||
- alpha - trainable parameter that controls frequency
|
||||
- beta - trainable parameter that controls magnitude
|
||||
alpha is initialized to 1 by default, higher values = higher-frequency.
|
||||
beta is initialized to 1 by default, higher values = higher-magnitude.
|
||||
alpha will be trained along with the rest of your model.
|
||||
'''
|
||||
super(SnakeBeta, self).__init__()
|
||||
self.in_features = in_features
|
||||
|
||||
# initialize alpha
|
||||
self.alpha_logscale = alpha_logscale
|
||||
if self.alpha_logscale: # log scale alphas initialized to zeros
|
||||
self.alpha = Parameter(torch.zeros(in_features) * alpha)
|
||||
self.beta = Parameter(torch.zeros(in_features) * alpha)
|
||||
else: # linear scale alphas initialized to ones
|
||||
self.alpha = Parameter(torch.ones(in_features) * alpha)
|
||||
self.beta = Parameter(torch.ones(in_features) * alpha)
|
||||
|
||||
self.alpha.requires_grad = alpha_trainable
|
||||
self.beta.requires_grad = alpha_trainable
|
||||
|
||||
self.no_div_by_zero = 0.000000001
|
||||
|
||||
def forward(self, x):
|
||||
'''
|
||||
Forward pass of the function.
|
||||
Applies the function to the input elementwise.
|
||||
SnakeBeta ∶= x + 1/b * sin^2 (xa)
|
||||
'''
|
||||
alpha = self.alpha.unsqueeze(0).unsqueeze(-1) # line up with x to [B, C, T]
|
||||
beta = self.beta.unsqueeze(0).unsqueeze(-1)
|
||||
if self.alpha_logscale:
|
||||
alpha = torch.exp(alpha)
|
||||
beta = torch.exp(beta)
|
||||
x = x + (1.0 / (beta + self.no_div_by_zero)) * pow(sin(x * alpha), 2)
|
||||
|
||||
return x
|
||||
@@ -0,0 +1,6 @@
|
||||
# Adapted from https://github.com/junjun3518/alias-free-torch under the Apache License 2.0
|
||||
# LICENSE is in incl_licenses directory.
|
||||
|
||||
from .filter import *
|
||||
from .resample import *
|
||||
from .act import *
|
||||
@@ -0,0 +1,28 @@
|
||||
# Adapted from https://github.com/junjun3518/alias-free-torch under the Apache License 2.0
|
||||
# LICENSE is in incl_licenses directory.
|
||||
|
||||
import torch.nn as nn
|
||||
from .resample import UpSample1d, DownSample1d
|
||||
|
||||
|
||||
class Activation1d(nn.Module):
|
||||
def __init__(self,
|
||||
activation,
|
||||
up_ratio: int = 2,
|
||||
down_ratio: int = 2,
|
||||
up_kernel_size: int = 12,
|
||||
down_kernel_size: int = 12):
|
||||
super().__init__()
|
||||
self.up_ratio = up_ratio
|
||||
self.down_ratio = down_ratio
|
||||
self.act = activation
|
||||
self.upsample = UpSample1d(up_ratio, up_kernel_size)
|
||||
self.downsample = DownSample1d(down_ratio, down_kernel_size)
|
||||
|
||||
# x: [B,C,T]
|
||||
def forward(self, x):
|
||||
x = self.upsample(x)
|
||||
x = self.act(x)
|
||||
x = self.downsample(x)
|
||||
|
||||
return x
|
||||
@@ -0,0 +1,95 @@
|
||||
# Adapted from https://github.com/junjun3518/alias-free-torch under the Apache License 2.0
|
||||
# LICENSE is in incl_licenses directory.
|
||||
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
import torch.nn.functional as F
|
||||
import math
|
||||
|
||||
if 'sinc' in dir(torch):
|
||||
sinc = torch.sinc
|
||||
else:
|
||||
# This code is adopted from adefossez's julius.core.sinc under the MIT License
|
||||
# https://adefossez.github.io/julius/julius/core.html
|
||||
# LICENSE is in incl_licenses directory.
|
||||
def sinc(x: torch.Tensor):
|
||||
"""
|
||||
Implementation of sinc, i.e. sin(pi * x) / (pi * x)
|
||||
__Warning__: Different to julius.sinc, the input is multiplied by `pi`!
|
||||
"""
|
||||
return torch.where(x == 0,
|
||||
torch.tensor(1., device=x.device, dtype=x.dtype),
|
||||
torch.sin(math.pi * x) / math.pi / x)
|
||||
|
||||
|
||||
# This code is adopted from adefossez's julius.lowpass.LowPassFilters under the MIT License
|
||||
# https://adefossez.github.io/julius/julius/lowpass.html
|
||||
# LICENSE is in incl_licenses directory.
|
||||
def kaiser_sinc_filter1d(cutoff, half_width, kernel_size): # return filter [1,1,kernel_size]
|
||||
even = (kernel_size % 2 == 0)
|
||||
half_size = kernel_size // 2
|
||||
|
||||
#For kaiser window
|
||||
delta_f = 4 * half_width
|
||||
A = 2.285 * (half_size - 1) * math.pi * delta_f + 7.95
|
||||
if A > 50.:
|
||||
beta = 0.1102 * (A - 8.7)
|
||||
elif A >= 21.:
|
||||
beta = 0.5842 * (A - 21)**0.4 + 0.07886 * (A - 21.)
|
||||
else:
|
||||
beta = 0.
|
||||
window = torch.kaiser_window(kernel_size, beta=beta, periodic=False)
|
||||
|
||||
# ratio = 0.5/cutoff -> 2 * cutoff = 1 / ratio
|
||||
if even:
|
||||
time = (torch.arange(-half_size, half_size) + 0.5)
|
||||
else:
|
||||
time = torch.arange(kernel_size) - half_size
|
||||
if cutoff == 0:
|
||||
filter_ = torch.zeros_like(time)
|
||||
else:
|
||||
filter_ = 2 * cutoff * window * sinc(2 * cutoff * time)
|
||||
# Normalize filter to have sum = 1, otherwise we will have a small leakage
|
||||
# of the constant component in the input signal.
|
||||
filter_ /= filter_.sum()
|
||||
filter = filter_.view(1, 1, kernel_size)
|
||||
|
||||
return filter
|
||||
|
||||
|
||||
class LowPassFilter1d(nn.Module):
|
||||
def __init__(self,
|
||||
cutoff=0.5,
|
||||
half_width=0.6,
|
||||
stride: int = 1,
|
||||
padding: bool = True,
|
||||
padding_mode: str = 'replicate',
|
||||
kernel_size: int = 12):
|
||||
# kernel_size should be even number for stylegan3 setup,
|
||||
# in this implementation, odd number is also possible.
|
||||
super().__init__()
|
||||
if cutoff < -0.:
|
||||
raise ValueError("Minimum cutoff must be larger than zero.")
|
||||
if cutoff > 0.5:
|
||||
raise ValueError("A cutoff above 0.5 does not make sense.")
|
||||
self.kernel_size = kernel_size
|
||||
self.even = (kernel_size % 2 == 0)
|
||||
self.pad_left = kernel_size // 2 - int(self.even)
|
||||
self.pad_right = kernel_size // 2
|
||||
self.stride = stride
|
||||
self.padding = padding
|
||||
self.padding_mode = padding_mode
|
||||
filter = kaiser_sinc_filter1d(cutoff, half_width, kernel_size)
|
||||
self.register_buffer("filter", filter)
|
||||
|
||||
#input [B, C, T]
|
||||
def forward(self, x):
|
||||
_, C, _ = x.shape
|
||||
|
||||
if self.padding:
|
||||
x = F.pad(x, (self.pad_left, self.pad_right),
|
||||
mode=self.padding_mode)
|
||||
out = F.conv1d(x, self.filter.expand(C, -1, -1),
|
||||
stride=self.stride, groups=C)
|
||||
|
||||
return out
|
||||
@@ -0,0 +1,49 @@
|
||||
# Adapted from https://github.com/junjun3518/alias-free-torch under the Apache License 2.0
|
||||
# LICENSE is in incl_licenses directory.
|
||||
|
||||
import torch.nn as nn
|
||||
from torch.nn import functional as F
|
||||
from .filter import LowPassFilter1d
|
||||
from .filter import kaiser_sinc_filter1d
|
||||
|
||||
|
||||
class UpSample1d(nn.Module):
|
||||
def __init__(self, ratio=2, kernel_size=None):
|
||||
super().__init__()
|
||||
self.ratio = ratio
|
||||
self.kernel_size = int(6 * ratio // 2) * 2 if kernel_size is None else kernel_size
|
||||
self.stride = ratio
|
||||
self.pad = self.kernel_size // ratio - 1
|
||||
self.pad_left = self.pad * self.stride + (self.kernel_size - self.stride) // 2
|
||||
self.pad_right = self.pad * self.stride + (self.kernel_size - self.stride + 1) // 2
|
||||
filter = kaiser_sinc_filter1d(cutoff=0.5 / ratio,
|
||||
half_width=0.6 / ratio,
|
||||
kernel_size=self.kernel_size)
|
||||
self.register_buffer("filter", filter)
|
||||
|
||||
# x: [B, C, T]
|
||||
def forward(self, x):
|
||||
_, C, _ = x.shape
|
||||
|
||||
x = F.pad(x, (self.pad, self.pad), mode='replicate')
|
||||
x = self.ratio * F.conv_transpose1d(
|
||||
x, self.filter.expand(C, -1, -1), stride=self.stride, groups=C)
|
||||
x = x[..., self.pad_left:-self.pad_right]
|
||||
|
||||
return x
|
||||
|
||||
|
||||
class DownSample1d(nn.Module):
|
||||
def __init__(self, ratio=2, kernel_size=None):
|
||||
super().__init__()
|
||||
self.ratio = ratio
|
||||
self.kernel_size = int(6 * ratio // 2) * 2 if kernel_size is None else kernel_size
|
||||
self.lowpass = LowPassFilter1d(cutoff=0.5 / ratio,
|
||||
half_width=0.6 / ratio,
|
||||
stride=ratio,
|
||||
kernel_size=self.kernel_size)
|
||||
|
||||
def forward(self, x):
|
||||
xx = self.lowpass(x)
|
||||
|
||||
return xx
|
||||
@@ -0,0 +1,32 @@
|
||||
from pathlib import Path
|
||||
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
from omegaconf import OmegaConf
|
||||
|
||||
from selva_core.ext.bigvgan.models import BigVGANVocoder
|
||||
|
||||
_bigvgan_vocoder_path = Path(__file__).parent / 'bigvgan_vocoder.yml'
|
||||
|
||||
|
||||
class BigVGAN(nn.Module):
|
||||
|
||||
def __init__(self, ckpt_path, config_path=_bigvgan_vocoder_path):
|
||||
super().__init__()
|
||||
vocoder_cfg = OmegaConf.load(config_path)
|
||||
self.vocoder = BigVGANVocoder(vocoder_cfg).eval()
|
||||
vocoder_ckpt = torch.load(ckpt_path, map_location='cpu', weights_only=True)['generator']
|
||||
self.vocoder.load_state_dict(vocoder_ckpt)
|
||||
|
||||
self.weight_norm_removed = False
|
||||
self.remove_weight_norm()
|
||||
|
||||
@torch.inference_mode()
|
||||
def forward(self, x):
|
||||
assert self.weight_norm_removed, 'call remove_weight_norm() before inference'
|
||||
return self.vocoder(x)
|
||||
|
||||
def remove_weight_norm(self):
|
||||
self.vocoder.remove_weight_norm()
|
||||
self.weight_norm_removed = True
|
||||
return self
|
||||
@@ -0,0 +1,63 @@
|
||||
resblock: '1'
|
||||
num_gpus: 0
|
||||
batch_size: 64
|
||||
num_mels: 80
|
||||
learning_rate: 0.0001
|
||||
adam_b1: 0.8
|
||||
adam_b2: 0.99
|
||||
lr_decay: 0.999
|
||||
seed: 1234
|
||||
upsample_rates:
|
||||
- 4
|
||||
- 4
|
||||
- 2
|
||||
- 2
|
||||
- 2
|
||||
- 2
|
||||
upsample_kernel_sizes:
|
||||
- 8
|
||||
- 8
|
||||
- 4
|
||||
- 4
|
||||
- 4
|
||||
- 4
|
||||
upsample_initial_channel: 1536
|
||||
resblock_kernel_sizes:
|
||||
- 3
|
||||
- 7
|
||||
- 11
|
||||
resblock_dilation_sizes:
|
||||
- - 1
|
||||
- 3
|
||||
- 5
|
||||
- - 1
|
||||
- 3
|
||||
- 5
|
||||
- - 1
|
||||
- 3
|
||||
- 5
|
||||
activation: snakebeta
|
||||
snake_logscale: true
|
||||
resolutions:
|
||||
- - 1024
|
||||
- 120
|
||||
- 600
|
||||
- - 2048
|
||||
- 240
|
||||
- 1200
|
||||
- - 512
|
||||
- 50
|
||||
- 240
|
||||
mpd_reshapes:
|
||||
- 2
|
||||
- 3
|
||||
- 5
|
||||
- 7
|
||||
- 11
|
||||
use_spectral_norm: false
|
||||
discriminator_channel_mult: 1
|
||||
num_workers: 4
|
||||
dist_config:
|
||||
dist_backend: nccl
|
||||
dist_url: tcp://localhost:54341
|
||||
world_size: 1
|
||||
@@ -0,0 +1,18 @@
|
||||
# Adapted from https://github.com/jik876/hifi-gan under the MIT license.
|
||||
# LICENSE is in incl_licenses directory.
|
||||
|
||||
import os
|
||||
import shutil
|
||||
|
||||
|
||||
class AttrDict(dict):
|
||||
def __init__(self, *args, **kwargs):
|
||||
super(AttrDict, self).__init__(*args, **kwargs)
|
||||
self.__dict__ = self
|
||||
|
||||
|
||||
def build_env(config, config_name, path):
|
||||
t_path = os.path.join(path, config_name)
|
||||
if config != t_path:
|
||||
os.makedirs(path, exist_ok=True)
|
||||
shutil.copyfile(config, os.path.join(path, config_name))
|
||||
@@ -0,0 +1,21 @@
|
||||
MIT License
|
||||
|
||||
Copyright (c) 2020 Jungil Kong
|
||||
|
||||
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.
|
||||
@@ -0,0 +1,21 @@
|
||||
MIT License
|
||||
|
||||
Copyright (c) 2020 Edward Dixon
|
||||
|
||||
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.
|
||||
@@ -0,0 +1,201 @@
|
||||
Apache License
|
||||
Version 2.0, January 2004
|
||||
http://www.apache.org/licenses/
|
||||
|
||||
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
||||
|
||||
1. Definitions.
|
||||
|
||||
"License" shall mean the terms and conditions for use, reproduction,
|
||||
and distribution as defined by Sections 1 through 9 of this document.
|
||||
|
||||
"Licensor" shall mean the copyright owner or entity authorized by
|
||||
the copyright owner that is granting the License.
|
||||
|
||||
"Legal Entity" shall mean the union of the acting entity and all
|
||||
other entities that control, are controlled by, or are under common
|
||||
control with that entity. For the purposes of this definition,
|
||||
"control" means (i) the power, direct or indirect, to cause the
|
||||
direction or management of such entity, whether by contract or
|
||||
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
||||
outstanding shares, or (iii) beneficial ownership of such entity.
|
||||
|
||||
"You" (or "Your") shall mean an individual or Legal Entity
|
||||
exercising permissions granted by this License.
|
||||
|
||||
"Source" form shall mean the preferred form for making modifications,
|
||||
including but not limited to software source code, documentation
|
||||
source, and configuration files.
|
||||
|
||||
"Object" form shall mean any form resulting from mechanical
|
||||
transformation or translation of a Source form, including but
|
||||
not limited to compiled object code, generated documentation,
|
||||
and conversions to other media types.
|
||||
|
||||
"Work" shall mean the work of authorship, whether in Source or
|
||||
Object form, made available under the License, as indicated by a
|
||||
copyright notice that is included in or attached to the work
|
||||
(an example is provided in the Appendix below).
|
||||
|
||||
"Derivative Works" shall mean any work, whether in Source or Object
|
||||
form, that is based on (or derived from) the Work and for which the
|
||||
editorial revisions, annotations, elaborations, or other modifications
|
||||
represent, as a whole, an original work of authorship. For the purposes
|
||||
of this License, Derivative Works shall not include works that remain
|
||||
separable from, or merely link (or bind by name) to the interfaces of,
|
||||
the Work and Derivative Works thereof.
|
||||
|
||||
"Contribution" shall mean any work of authorship, including
|
||||
the original version of the Work and any modifications or additions
|
||||
to that Work or Derivative Works thereof, that is intentionally
|
||||
submitted to Licensor for inclusion in the Work by the copyright owner
|
||||
or by an individual or Legal Entity authorized to submit on behalf of
|
||||
the copyright owner. For the purposes of this definition, "submitted"
|
||||
means any form of electronic, verbal, or written communication sent
|
||||
to the Licensor or its representatives, including but not limited to
|
||||
communication on electronic mailing lists, source code control systems,
|
||||
and issue tracking systems that are managed by, or on behalf of, the
|
||||
Licensor for the purpose of discussing and improving the Work, but
|
||||
excluding communication that is conspicuously marked or otherwise
|
||||
designated in writing by the copyright owner as "Not a Contribution."
|
||||
|
||||
"Contributor" shall mean Licensor and any individual or Legal Entity
|
||||
on behalf of whom a Contribution has been received by Licensor and
|
||||
subsequently incorporated within the Work.
|
||||
|
||||
2. Grant of Copyright License. Subject to the terms and conditions of
|
||||
this License, each Contributor hereby grants to You a perpetual,
|
||||
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
||||
copyright license to reproduce, prepare Derivative Works of,
|
||||
publicly display, publicly perform, sublicense, and distribute the
|
||||
Work and such Derivative Works in Source or Object form.
|
||||
|
||||
3. Grant of Patent License. Subject to the terms and conditions of
|
||||
this License, each Contributor hereby grants to You a perpetual,
|
||||
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
||||
(except as stated in this section) patent license to make, have made,
|
||||
use, offer to sell, sell, import, and otherwise transfer the Work,
|
||||
where such license applies only to those patent claims licensable
|
||||
by such Contributor that are necessarily infringed by their
|
||||
Contribution(s) alone or by combination of their Contribution(s)
|
||||
with the Work to which such Contribution(s) was submitted. If You
|
||||
institute patent litigation against any entity (including a
|
||||
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
||||
or a Contribution incorporated within the Work constitutes direct
|
||||
or contributory patent infringement, then any patent licenses
|
||||
granted to You under this License for that Work shall terminate
|
||||
as of the date such litigation is filed.
|
||||
|
||||
4. Redistribution. You may reproduce and distribute copies of the
|
||||
Work or Derivative Works thereof in any medium, with or without
|
||||
modifications, and in Source or Object form, provided that You
|
||||
meet the following conditions:
|
||||
|
||||
(a) You must give any other recipients of the Work or
|
||||
Derivative Works a copy of this License; and
|
||||
|
||||
(b) You must cause any modified files to carry prominent notices
|
||||
stating that You changed the files; and
|
||||
|
||||
(c) You must retain, in the Source form of any Derivative Works
|
||||
that You distribute, all copyright, patent, trademark, and
|
||||
attribution notices from the Source form of the Work,
|
||||
excluding those notices that do not pertain to any part of
|
||||
the Derivative Works; and
|
||||
|
||||
(d) If the Work includes a "NOTICE" text file as part of its
|
||||
distribution, then any Derivative Works that You distribute must
|
||||
include a readable copy of the attribution notices contained
|
||||
within such NOTICE file, excluding those notices that do not
|
||||
pertain to any part of the Derivative Works, in at least one
|
||||
of the following places: within a NOTICE text file distributed
|
||||
as part of the Derivative Works; within the Source form or
|
||||
documentation, if provided along with the Derivative Works; or,
|
||||
within a display generated by the Derivative Works, if and
|
||||
wherever such third-party notices normally appear. The contents
|
||||
of the NOTICE file are for informational purposes only and
|
||||
do not modify the License. You may add Your own attribution
|
||||
notices within Derivative Works that You distribute, alongside
|
||||
or as an addendum to the NOTICE text from the Work, provided
|
||||
that such additional attribution notices cannot be construed
|
||||
as modifying the License.
|
||||
|
||||
You may add Your own copyright statement to Your modifications and
|
||||
may provide additional or different license terms and conditions
|
||||
for use, reproduction, or distribution of Your modifications, or
|
||||
for any such Derivative Works as a whole, provided Your use,
|
||||
reproduction, and distribution of the Work otherwise complies with
|
||||
the conditions stated in this License.
|
||||
|
||||
5. Submission of Contributions. Unless You explicitly state otherwise,
|
||||
any Contribution intentionally submitted for inclusion in the Work
|
||||
by You to the Licensor shall be under the terms and conditions of
|
||||
this License, without any additional terms or conditions.
|
||||
Notwithstanding the above, nothing herein shall supersede or modify
|
||||
the terms of any separate license agreement you may have executed
|
||||
with Licensor regarding such Contributions.
|
||||
|
||||
6. Trademarks. This License does not grant permission to use the trade
|
||||
names, trademarks, service marks, or product names of the Licensor,
|
||||
except as required for reasonable and customary use in describing the
|
||||
origin of the Work and reproducing the content of the NOTICE file.
|
||||
|
||||
7. Disclaimer of Warranty. Unless required by applicable law or
|
||||
agreed to in writing, Licensor provides the Work (and each
|
||||
Contributor provides its Contributions) on an "AS IS" BASIS,
|
||||
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
||||
implied, including, without limitation, any warranties or conditions
|
||||
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
||||
PARTICULAR PURPOSE. You are solely responsible for determining the
|
||||
appropriateness of using or redistributing the Work and assume any
|
||||
risks associated with Your exercise of permissions under this License.
|
||||
|
||||
8. Limitation of Liability. In no event and under no legal theory,
|
||||
whether in tort (including negligence), contract, or otherwise,
|
||||
unless required by applicable law (such as deliberate and grossly
|
||||
negligent acts) or agreed to in writing, shall any Contributor be
|
||||
liable to You for damages, including any direct, indirect, special,
|
||||
incidental, or consequential damages of any character arising as a
|
||||
result of this License or out of the use or inability to use the
|
||||
Work (including but not limited to damages for loss of goodwill,
|
||||
work stoppage, computer failure or malfunction, or any and all
|
||||
other commercial damages or losses), even if such Contributor
|
||||
has been advised of the possibility of such damages.
|
||||
|
||||
9. Accepting Warranty or Additional Liability. While redistributing
|
||||
the Work or Derivative Works thereof, You may choose to offer,
|
||||
and charge a fee for, acceptance of support, warranty, indemnity,
|
||||
or other liability obligations and/or rights consistent with this
|
||||
License. However, in accepting such obligations, You may act only
|
||||
on Your own behalf and on Your sole responsibility, not on behalf
|
||||
of any other Contributor, and only if You agree to indemnify,
|
||||
defend, and hold each Contributor harmless for any liability
|
||||
incurred by, or claims asserted against, such Contributor by reason
|
||||
of your accepting any such warranty or additional liability.
|
||||
|
||||
END OF TERMS AND CONDITIONS
|
||||
|
||||
APPENDIX: How to apply the Apache License to your work.
|
||||
|
||||
To apply the Apache License to your work, attach the following
|
||||
boilerplate notice, with the fields enclosed by brackets "[]"
|
||||
replaced with your own identifying information. (Don't include
|
||||
the brackets!) The text should be enclosed in the appropriate
|
||||
comment syntax for the file format. We also recommend that a
|
||||
file or class name and description of purpose be included on the
|
||||
same "printed page" as the copyright notice for easier
|
||||
identification within third-party archives.
|
||||
|
||||
Copyright [yyyy] [name of copyright owner]
|
||||
|
||||
Licensed under the Apache License, Version 2.0 (the "License");
|
||||
you may not use this file except in compliance with the License.
|
||||
You may obtain a copy of the License at
|
||||
|
||||
http://www.apache.org/licenses/LICENSE-2.0
|
||||
|
||||
Unless required by applicable law or agreed to in writing, software
|
||||
distributed under the License is distributed on an "AS IS" BASIS,
|
||||
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
See the License for the specific language governing permissions and
|
||||
limitations under the License.
|
||||
@@ -0,0 +1,29 @@
|
||||
BSD 3-Clause License
|
||||
|
||||
Copyright (c) 2019, Seungwon Park 박승원
|
||||
All rights reserved.
|
||||
|
||||
Redistribution and use in source and binary forms, with or without
|
||||
modification, are permitted provided that the following conditions are met:
|
||||
|
||||
1. Redistributions of source code must retain the above copyright notice, this
|
||||
list of conditions and the following disclaimer.
|
||||
|
||||
2. Redistributions in binary form must reproduce the above copyright notice,
|
||||
this list of conditions and the following disclaimer in the documentation
|
||||
and/or other materials provided with the distribution.
|
||||
|
||||
3. Neither the name of the copyright holder nor the names of its
|
||||
contributors may be used to endorse or promote products derived from
|
||||
this software without specific prior written permission.
|
||||
|
||||
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
|
||||
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
|
||||
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
|
||||
DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
|
||||
FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
|
||||
DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
|
||||
SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
|
||||
CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
|
||||
OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
||||
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
||||
@@ -0,0 +1,16 @@
|
||||
Copyright 2020 Alexandre Défossez
|
||||
|
||||
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.
|
||||
@@ -0,0 +1,255 @@
|
||||
# Copyright (c) 2022 NVIDIA CORPORATION.
|
||||
# Licensed under the MIT license.
|
||||
|
||||
# Adapted from https://github.com/jik876/hifi-gan under the MIT license.
|
||||
# LICENSE is in incl_licenses directory.
|
||||
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
from torch.nn import Conv1d, ConvTranspose1d
|
||||
from torch.nn.utils.parametrizations import weight_norm
|
||||
from torch.nn.utils.parametrize import remove_parametrizations
|
||||
|
||||
from selva_core.ext.bigvgan import activations
|
||||
from selva_core.ext.bigvgan.alias_free_torch import *
|
||||
from selva_core.ext.bigvgan.utils import get_padding, init_weights
|
||||
|
||||
LRELU_SLOPE = 0.1
|
||||
|
||||
|
||||
class AMPBlock1(torch.nn.Module):
|
||||
|
||||
def __init__(self, h, channels, kernel_size=3, dilation=(1, 3, 5), activation=None):
|
||||
super(AMPBlock1, self).__init__()
|
||||
self.h = h
|
||||
|
||||
self.convs1 = nn.ModuleList([
|
||||
weight_norm(
|
||||
Conv1d(channels,
|
||||
channels,
|
||||
kernel_size,
|
||||
1,
|
||||
dilation=dilation[0],
|
||||
padding=get_padding(kernel_size, dilation[0]))),
|
||||
weight_norm(
|
||||
Conv1d(channels,
|
||||
channels,
|
||||
kernel_size,
|
||||
1,
|
||||
dilation=dilation[1],
|
||||
padding=get_padding(kernel_size, dilation[1]))),
|
||||
weight_norm(
|
||||
Conv1d(channels,
|
||||
channels,
|
||||
kernel_size,
|
||||
1,
|
||||
dilation=dilation[2],
|
||||
padding=get_padding(kernel_size, dilation[2])))
|
||||
])
|
||||
self.convs1.apply(init_weights)
|
||||
|
||||
self.convs2 = nn.ModuleList([
|
||||
weight_norm(
|
||||
Conv1d(channels,
|
||||
channels,
|
||||
kernel_size,
|
||||
1,
|
||||
dilation=1,
|
||||
padding=get_padding(kernel_size, 1))),
|
||||
weight_norm(
|
||||
Conv1d(channels,
|
||||
channels,
|
||||
kernel_size,
|
||||
1,
|
||||
dilation=1,
|
||||
padding=get_padding(kernel_size, 1))),
|
||||
weight_norm(
|
||||
Conv1d(channels,
|
||||
channels,
|
||||
kernel_size,
|
||||
1,
|
||||
dilation=1,
|
||||
padding=get_padding(kernel_size, 1)))
|
||||
])
|
||||
self.convs2.apply(init_weights)
|
||||
|
||||
self.num_layers = len(self.convs1) + len(self.convs2) # total number of conv layers
|
||||
|
||||
if activation == 'snake': # periodic nonlinearity with snake function and anti-aliasing
|
||||
self.activations = nn.ModuleList([
|
||||
Activation1d(
|
||||
activation=activations.Snake(channels, alpha_logscale=h.snake_logscale))
|
||||
for _ in range(self.num_layers)
|
||||
])
|
||||
elif activation == 'snakebeta': # periodic nonlinearity with snakebeta function and anti-aliasing
|
||||
self.activations = nn.ModuleList([
|
||||
Activation1d(
|
||||
activation=activations.SnakeBeta(channels, alpha_logscale=h.snake_logscale))
|
||||
for _ in range(self.num_layers)
|
||||
])
|
||||
else:
|
||||
raise NotImplementedError(
|
||||
"activation incorrectly specified. check the config file and look for 'activation'."
|
||||
)
|
||||
|
||||
def forward(self, x):
|
||||
acts1, acts2 = self.activations[::2], self.activations[1::2]
|
||||
for c1, c2, a1, a2 in zip(self.convs1, self.convs2, acts1, acts2):
|
||||
xt = a1(x)
|
||||
xt = c1(xt)
|
||||
xt = a2(xt)
|
||||
xt = c2(xt)
|
||||
x = xt + x
|
||||
|
||||
return x
|
||||
|
||||
def remove_weight_norm(self):
|
||||
for l in self.convs1:
|
||||
remove_parametrizations(l, 'weight')
|
||||
for l in self.convs2:
|
||||
remove_parametrizations(l, 'weight')
|
||||
|
||||
|
||||
class AMPBlock2(torch.nn.Module):
|
||||
|
||||
def __init__(self, h, channels, kernel_size=3, dilation=(1, 3), activation=None):
|
||||
super(AMPBlock2, self).__init__()
|
||||
self.h = h
|
||||
|
||||
self.convs = nn.ModuleList([
|
||||
weight_norm(
|
||||
Conv1d(channels,
|
||||
channels,
|
||||
kernel_size,
|
||||
1,
|
||||
dilation=dilation[0],
|
||||
padding=get_padding(kernel_size, dilation[0]))),
|
||||
weight_norm(
|
||||
Conv1d(channels,
|
||||
channels,
|
||||
kernel_size,
|
||||
1,
|
||||
dilation=dilation[1],
|
||||
padding=get_padding(kernel_size, dilation[1])))
|
||||
])
|
||||
self.convs.apply(init_weights)
|
||||
|
||||
self.num_layers = len(self.convs) # total number of conv layers
|
||||
|
||||
if activation == 'snake': # periodic nonlinearity with snake function and anti-aliasing
|
||||
self.activations = nn.ModuleList([
|
||||
Activation1d(
|
||||
activation=activations.Snake(channels, alpha_logscale=h.snake_logscale))
|
||||
for _ in range(self.num_layers)
|
||||
])
|
||||
elif activation == 'snakebeta': # periodic nonlinearity with snakebeta function and anti-aliasing
|
||||
self.activations = nn.ModuleList([
|
||||
Activation1d(
|
||||
activation=activations.SnakeBeta(channels, alpha_logscale=h.snake_logscale))
|
||||
for _ in range(self.num_layers)
|
||||
])
|
||||
else:
|
||||
raise NotImplementedError(
|
||||
"activation incorrectly specified. check the config file and look for 'activation'."
|
||||
)
|
||||
|
||||
def forward(self, x):
|
||||
for c, a in zip(self.convs, self.activations):
|
||||
xt = a(x)
|
||||
xt = c(xt)
|
||||
x = xt + x
|
||||
|
||||
return x
|
||||
|
||||
def remove_weight_norm(self):
|
||||
for l in self.convs:
|
||||
remove_parametrizations(l, 'weight')
|
||||
|
||||
|
||||
class BigVGANVocoder(torch.nn.Module):
|
||||
# this is our main BigVGAN model. Applies anti-aliased periodic activation for resblocks.
|
||||
def __init__(self, h):
|
||||
super().__init__()
|
||||
self.h = h
|
||||
|
||||
self.num_kernels = len(h.resblock_kernel_sizes)
|
||||
self.num_upsamples = len(h.upsample_rates)
|
||||
|
||||
# pre conv
|
||||
self.conv_pre = weight_norm(Conv1d(h.num_mels, h.upsample_initial_channel, 7, 1, padding=3))
|
||||
|
||||
# define which AMPBlock to use. BigVGAN uses AMPBlock1 as default
|
||||
resblock = AMPBlock1 if h.resblock == '1' else AMPBlock2
|
||||
|
||||
# transposed conv-based upsamplers. does not apply anti-aliasing
|
||||
self.ups = nn.ModuleList()
|
||||
for i, (u, k) in enumerate(zip(h.upsample_rates, h.upsample_kernel_sizes)):
|
||||
self.ups.append(
|
||||
nn.ModuleList([
|
||||
weight_norm(
|
||||
ConvTranspose1d(h.upsample_initial_channel // (2**i),
|
||||
h.upsample_initial_channel // (2**(i + 1)),
|
||||
k,
|
||||
u,
|
||||
padding=(k - u) // 2))
|
||||
]))
|
||||
|
||||
# residual blocks using anti-aliased multi-periodicity composition modules (AMP)
|
||||
self.resblocks = nn.ModuleList()
|
||||
for i in range(len(self.ups)):
|
||||
ch = h.upsample_initial_channel // (2**(i + 1))
|
||||
for j, (k, d) in enumerate(zip(h.resblock_kernel_sizes, h.resblock_dilation_sizes)):
|
||||
self.resblocks.append(resblock(h, ch, k, d, activation=h.activation))
|
||||
|
||||
# post conv
|
||||
if h.activation == "snake": # periodic nonlinearity with snake function and anti-aliasing
|
||||
activation_post = activations.Snake(ch, alpha_logscale=h.snake_logscale)
|
||||
self.activation_post = Activation1d(activation=activation_post)
|
||||
elif h.activation == "snakebeta": # periodic nonlinearity with snakebeta function and anti-aliasing
|
||||
activation_post = activations.SnakeBeta(ch, alpha_logscale=h.snake_logscale)
|
||||
self.activation_post = Activation1d(activation=activation_post)
|
||||
else:
|
||||
raise NotImplementedError(
|
||||
"activation incorrectly specified. check the config file and look for 'activation'."
|
||||
)
|
||||
|
||||
self.conv_post = weight_norm(Conv1d(ch, 1, 7, 1, padding=3))
|
||||
|
||||
# weight initialization
|
||||
for i in range(len(self.ups)):
|
||||
self.ups[i].apply(init_weights)
|
||||
self.conv_post.apply(init_weights)
|
||||
|
||||
def forward(self, x):
|
||||
# pre conv
|
||||
x = self.conv_pre(x)
|
||||
|
||||
for i in range(self.num_upsamples):
|
||||
# upsampling
|
||||
for i_up in range(len(self.ups[i])):
|
||||
x = self.ups[i][i_up](x)
|
||||
# AMP blocks
|
||||
xs = None
|
||||
for j in range(self.num_kernels):
|
||||
if xs is None:
|
||||
xs = self.resblocks[i * self.num_kernels + j](x)
|
||||
else:
|
||||
xs += self.resblocks[i * self.num_kernels + j](x)
|
||||
x = xs / self.num_kernels
|
||||
|
||||
# post conv
|
||||
x = self.activation_post(x)
|
||||
x = self.conv_post(x)
|
||||
x = torch.tanh(x)
|
||||
|
||||
return x
|
||||
|
||||
def remove_weight_norm(self):
|
||||
print('Removing weight norm...')
|
||||
for l in self.ups:
|
||||
for l_i in l:
|
||||
remove_parametrizations(l_i, 'weight')
|
||||
for l in self.resblocks:
|
||||
l.remove_weight_norm()
|
||||
remove_parametrizations(self.conv_pre, 'weight')
|
||||
remove_parametrizations(self.conv_post, 'weight')
|
||||
@@ -0,0 +1,31 @@
|
||||
# Adapted from https://github.com/jik876/hifi-gan under the MIT license.
|
||||
# LICENSE is in incl_licenses directory.
|
||||
|
||||
import os
|
||||
|
||||
import torch
|
||||
from torch.nn.utils.parametrizations import weight_norm
|
||||
|
||||
|
||||
def init_weights(m, mean=0.0, std=0.01):
|
||||
classname = m.__class__.__name__
|
||||
if classname.find("Conv") != -1:
|
||||
m.weight.data.normal_(mean, std)
|
||||
|
||||
|
||||
def apply_weight_norm(m):
|
||||
classname = m.__class__.__name__
|
||||
if classname.find("Conv") != -1:
|
||||
weight_norm(m)
|
||||
|
||||
|
||||
def get_padding(kernel_size, dilation=1):
|
||||
return int((kernel_size * dilation - dilation) / 2)
|
||||
|
||||
|
||||
def load_checkpoint(filepath, device):
|
||||
assert os.path.isfile(filepath)
|
||||
print("Loading '{}'".format(filepath))
|
||||
checkpoint_dict = torch.load(filepath, map_location=device)
|
||||
print("Complete.")
|
||||
return checkpoint_dict
|
||||
Reference in New Issue
Block a user