Spaces:
Sleeping
Sleeping
File size: 6,580 Bytes
c7f3ffb | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 | import math
import torch
import torch.nn as nn
import torch.nn.functional as F
from .layers import LayerNorm, Embedding
class LambdaLayer(nn.Module):
def __init__(self, lambd):
super(LambdaLayer, self).__init__()
self.lambd = lambd
def forward(self, x):
return self.lambd(x)
def init_weights_func(m):
classname = m.__class__.__name__
if classname.find("Conv1d") != -1:
torch.nn.init.xavier_uniform_(m.weight)
def get_norm_builder(norm_type, channels, ln_eps=1e-6):
if norm_type == 'bn':
norm_builder = lambda: nn.BatchNorm1d(channels)
elif norm_type == 'in':
norm_builder = lambda: nn.InstanceNorm1d(channels, affine=True)
elif norm_type == 'gn':
norm_builder = lambda: nn.GroupNorm(8, channels)
elif norm_type == 'ln':
norm_builder = lambda: LayerNorm(channels, dim=1, eps=ln_eps)
else:
norm_builder = lambda: nn.Identity()
return norm_builder
def get_act_builder(act_type):
if act_type == 'gelu':
act_builder = lambda: nn.GELU()
elif act_type == 'relu':
act_builder = lambda: nn.ReLU(inplace=True)
elif act_type == 'leakyrelu':
act_builder = lambda: nn.LeakyReLU(negative_slope=0.01, inplace=True)
elif act_type == 'swish':
act_builder = lambda: nn.SiLU(inplace=True)
else:
act_builder = lambda: nn.Identity()
return act_builder
class ResidualBlock(nn.Module):
"""Implements conv->PReLU->norm n-times"""
def __init__(self, channels, kernel_size, dilation, n=2, norm_type='bn', dropout=0.0,
c_multiple=2, ln_eps=1e-12, act_type='gelu'):
super(ResidualBlock, self).__init__()
norm_builder = get_norm_builder(norm_type, channels, ln_eps)
act_builder = get_act_builder(act_type)
self.blocks = [
nn.Sequential(
norm_builder(),
nn.Conv1d(channels, c_multiple * channels, kernel_size, dilation=dilation,
padding=(dilation * (kernel_size - 1)) // 2),
LambdaLayer(lambda x: x * kernel_size ** -0.5),
act_builder(),
nn.Conv1d(c_multiple * channels, channels, 1, dilation=dilation),
)
for i in range(n)
]
self.blocks = nn.ModuleList(self.blocks)
self.dropout = dropout
def forward(self, x):
nonpadding = (x.abs().sum(1) > 0).float()[:, None, :]
for b in self.blocks:
x_ = b(x)
if self.dropout > 0 and self.training:
x_ = F.dropout(x_, self.dropout, training=self.training)
x = x + x_
x = x * nonpadding
return x
class ConvBlocks(nn.Module):
"""Decodes the expanded phoneme encoding into spectrograms"""
def __init__(self, hidden_size, out_dims, dilations, kernel_size,
norm_type='ln', layers_in_block=2, c_multiple=2,
dropout=0.0, ln_eps=1e-5,
init_weights=True, is_BTC=True, num_layers=None, post_net_kernel=3, act_type='gelu'):
super(ConvBlocks, self).__init__()
self.is_BTC = is_BTC
if num_layers is not None:
dilations = [1] * num_layers
self.res_blocks = nn.Sequential(
*[ResidualBlock(hidden_size, kernel_size, d,
n=layers_in_block, norm_type=norm_type, c_multiple=c_multiple,
dropout=dropout, ln_eps=ln_eps, act_type=act_type)
for d in dilations],
)
norm = get_norm_builder(norm_type, hidden_size, ln_eps)()
self.last_norm = norm
self.post_net1 = nn.Conv1d(hidden_size, out_dims, kernel_size=post_net_kernel,
padding=post_net_kernel // 2)
if init_weights:
self.apply(init_weights_func)
def forward(self, x, nonpadding=None):
"""
:param x: [B, T, H]
:return: [B, T, H]
"""
if self.is_BTC:
x = x.transpose(1, 2)
if nonpadding is None:
nonpadding = (x.abs().sum(1) > 0).float()[:, None, :]
elif self.is_BTC:
nonpadding = nonpadding.transpose(1, 2)
x = self.res_blocks(x) * nonpadding
x = self.last_norm(x) * nonpadding
x = self.post_net1(x) * nonpadding
if self.is_BTC:
x = x.transpose(1, 2)
return x
class TextConvEncoder(ConvBlocks):
def __init__(self, dict_size, hidden_size, out_dims, dilations, kernel_size,
norm_type='ln', layers_in_block=2, c_multiple=2,
dropout=0.0, ln_eps=1e-5, init_weights=True, num_layers=None, post_net_kernel=3):
super().__init__(hidden_size, out_dims, dilations, kernel_size,
norm_type, layers_in_block, c_multiple,
dropout, ln_eps, init_weights, num_layers=num_layers,
post_net_kernel=post_net_kernel)
self.embed_tokens = Embedding(dict_size, hidden_size, 0)
self.embed_scale = math.sqrt(hidden_size)
def forward(self, txt_tokens):
"""
:param txt_tokens: [B, T]
:return: {
'encoder_out': [B x T x C]
}
"""
x = self.embed_scale * self.embed_tokens(txt_tokens)
return super().forward(x)
class ConditionalConvBlocks(ConvBlocks):
def __init__(self, hidden_size, c_cond, c_out, dilations, kernel_size,
norm_type='ln', layers_in_block=2, c_multiple=2,
dropout=0.0, ln_eps=1e-5, init_weights=True, is_BTC=True, num_layers=None):
super().__init__(hidden_size, c_out, dilations, kernel_size,
norm_type, layers_in_block, c_multiple,
dropout, ln_eps, init_weights, is_BTC=False, num_layers=num_layers)
self.g_prenet = nn.Conv1d(c_cond, hidden_size, 3, padding=1)
self.is_BTC_ = is_BTC
if init_weights:
self.g_prenet.apply(init_weights_func)
def forward(self, x, cond, nonpadding=None):
if self.is_BTC_:
x = x.transpose(1, 2)
cond = cond.transpose(1, 2)
if nonpadding is not None:
nonpadding = nonpadding.transpose(1, 2)
if nonpadding is None:
nonpadding = x.abs().sum(1)[:, None]
x = x + self.g_prenet(cond)
x = x * nonpadding
x = super(ConditionalConvBlocks, self).forward(x) # input needs to be BTC
if self.is_BTC_:
x = x.transpose(1, 2)
return x
|