File size: 9,819 Bytes
feec0bf |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 |
import os
import json
import copy
import math
from collections import OrderedDict
import torch
import torch.nn as nn
import numpy as np
import torch.nn.functional as F
from utils.tools import get_mask_from_lengths, pad
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
class VarianceAdaptor(nn.Module):
"""Variance Adaptor"""
def __init__(self, preprocess_config, model_config):
super(VarianceAdaptor, self).__init__()
self.duration_predictor = VariancePredictor(model_config)
self.length_regulator = LengthRegulator()
self.pitch_predictor = VariancePredictor(model_config)
self.energy_predictor = VariancePredictor(model_config)
self.pitch_feature_level = preprocess_config["preprocessing"]["pitch"][
"feature"
]
self.energy_feature_level = preprocess_config["preprocessing"]["energy"][
"feature"
]
assert self.pitch_feature_level in ["phoneme_level", "frame_level"]
assert self.energy_feature_level in ["phoneme_level", "frame_level"]
pitch_quantization = model_config["variance_embedding"]["pitch_quantization"]
energy_quantization = model_config["variance_embedding"]["energy_quantization"]
n_bins = model_config["variance_embedding"]["n_bins"]
assert pitch_quantization in ["linear", "log"]
assert energy_quantization in ["linear", "log"]
with open(
os.path.join(preprocess_config["path"]["preprocessed_path"], "stats.json")
) as f:
stats = json.load(f)
pitch_min, pitch_max = stats["pitch"][:2]
energy_min, energy_max = stats["energy"][:2]
if pitch_quantization == "log":
self.pitch_bins = nn.Parameter(
torch.exp(
torch.linspace(np.log(pitch_min), np.log(pitch_max), n_bins - 1)
),
requires_grad=False,
)
else:
self.pitch_bins = nn.Parameter(
torch.linspace(pitch_min, pitch_max, n_bins - 1),
requires_grad=False,
)
if energy_quantization == "log":
self.energy_bins = nn.Parameter(
torch.exp(
torch.linspace(np.log(energy_min), np.log(energy_max), n_bins - 1)
),
requires_grad=False,
)
else:
self.energy_bins = nn.Parameter(
torch.linspace(energy_min, energy_max, n_bins - 1),
requires_grad=False,
)
self.pitch_embedding = nn.Embedding(
n_bins, model_config["transformer"]["encoder_hidden"]
)
self.energy_embedding = nn.Embedding(
n_bins, model_config["transformer"]["encoder_hidden"]
)
def get_pitch_embedding(self, x, target, mask, control):
prediction = self.pitch_predictor(x, mask)
if target is not None:
embedding = self.pitch_embedding(torch.bucketize(target, self.pitch_bins))
else:
prediction = prediction * control
embedding = self.pitch_embedding(
torch.bucketize(prediction, self.pitch_bins)
)
return prediction, embedding
def get_energy_embedding(self, x, target, mask, control):
prediction = self.energy_predictor(x, mask)
if target is not None:
embedding = self.energy_embedding(torch.bucketize(target, self.energy_bins))
else:
prediction = prediction * control
embedding = self.energy_embedding(
torch.bucketize(prediction, self.energy_bins)
)
return prediction, embedding
def forward(
self,
x,
src_mask,
mel_mask=None,
max_len=None,
pitch_target=None,
energy_target=None,
duration_target=None,
p_control=1.0,
e_control=1.0,
d_control=1.0,
):
log_duration_prediction = self.duration_predictor(x, src_mask)
if self.pitch_feature_level == "phoneme_level":
pitch_prediction, pitch_embedding = self.get_pitch_embedding(
x, pitch_target, src_mask, p_control
)
x = x + pitch_embedding
if self.energy_feature_level == "phoneme_level":
energy_prediction, energy_embedding = self.get_energy_embedding(
x, energy_target, src_mask, p_control
)
x = x + energy_embedding
if duration_target is not None:
x, mel_len = self.length_regulator(x, duration_target, max_len)
duration_rounded = duration_target
else:
duration_rounded = torch.clamp(
(torch.round(torch.exp(log_duration_prediction) - 1) * d_control),
min=0,
)
x, mel_len = self.length_regulator(x, duration_rounded, max_len)
mel_mask = get_mask_from_lengths(mel_len)
if self.pitch_feature_level == "frame_level":
pitch_prediction, pitch_embedding = self.get_pitch_embedding(
x, pitch_target, mel_mask, p_control
)
x = x + pitch_embedding
if self.energy_feature_level == "frame_level":
energy_prediction, energy_embedding = self.get_energy_embedding(
x, energy_target, mel_mask, p_control
)
x = x + energy_embedding
return (
x,
pitch_prediction,
energy_prediction,
log_duration_prediction,
duration_rounded,
mel_len,
mel_mask,
)
class LengthRegulator(nn.Module):
"""Length Regulator"""
def __init__(self):
super(LengthRegulator, self).__init__()
def LR(self, x, duration, max_len):
output = list()
mel_len = list()
for batch, expand_target in zip(x, duration):
expanded = self.expand(batch, expand_target)
output.append(expanded)
mel_len.append(expanded.shape[0])
if max_len is not None:
output = pad(output, max_len)
else:
output = pad(output)
return output, torch.LongTensor(mel_len).to(device)
def expand(self, batch, predicted):
out = list()
for i, vec in enumerate(batch):
expand_size = predicted[i].item()
out.append(vec.expand(max(int(expand_size), 0), -1))
out = torch.cat(out, 0)
return out
def forward(self, x, duration, max_len):
output, mel_len = self.LR(x, duration, max_len)
return output, mel_len
class VariancePredictor(nn.Module):
"""Duration, Pitch and Energy Predictor"""
def __init__(self, model_config):
super(VariancePredictor, self).__init__()
self.input_size = model_config["transformer"]["encoder_hidden"]
self.filter_size = model_config["variance_predictor"]["filter_size"]
self.kernel = model_config["variance_predictor"]["kernel_size"]
self.conv_output_size = model_config["variance_predictor"]["filter_size"]
self.dropout = model_config["variance_predictor"]["dropout"]
self.conv_layer = nn.Sequential(
OrderedDict(
[
(
"conv1d_1",
Conv(
self.input_size,
self.filter_size,
kernel_size=self.kernel,
padding=(self.kernel - 1) // 2,
),
),
("relu_1", nn.ReLU()),
("layer_norm_1", nn.LayerNorm(self.filter_size)),
("dropout_1", nn.Dropout(self.dropout)),
(
"conv1d_2",
Conv(
self.filter_size,
self.filter_size,
kernel_size=self.kernel,
padding=1,
),
),
("relu_2", nn.ReLU()),
("layer_norm_2", nn.LayerNorm(self.filter_size)),
("dropout_2", nn.Dropout(self.dropout)),
]
)
)
self.linear_layer = nn.Linear(self.conv_output_size, 1)
def forward(self, encoder_output, mask):
out = self.conv_layer(encoder_output)
out = self.linear_layer(out)
out = out.squeeze(-1)
if mask is not None:
out = out.masked_fill(mask, 0.0)
return out
class Conv(nn.Module):
"""
Convolution Module
"""
def __init__(
self,
in_channels,
out_channels,
kernel_size=1,
stride=1,
padding=0,
dilation=1,
bias=True,
w_init="linear",
):
"""
:param in_channels: dimension of input
:param out_channels: dimension of output
:param kernel_size: size of kernel
:param stride: size of stride
:param padding: size of padding
:param dilation: dilation rate
:param bias: boolean. if True, bias is included.
:param w_init: str. weight inits with xavier initialization.
"""
super(Conv, self).__init__()
self.conv = nn.Conv1d(
in_channels,
out_channels,
kernel_size=kernel_size,
stride=stride,
padding=padding,
dilation=dilation,
bias=bias,
)
def forward(self, x):
x = x.contiguous().transpose(1, 2)
x = self.conv(x)
x = x.contiguous().transpose(1, 2)
return x
|