Spaces:
Sleeping
Sleeping
File size: 9,197 Bytes
df2accb |
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 |
# 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.
from typing import Iterable
import torch
import numpy as np
import torch.utils.data
from torch.nn.utils.rnn import pad_sequence
from utils.data_utils import *
from torch.utils.data import ConcatDataset, Dataset
class VocoderDataset(torch.utils.data.Dataset):
def __init__(self, cfg, dataset, is_valid=False):
"""
Args:
cfg: config
dataset: dataset name
is_valid: whether to use train or valid dataset
"""
assert isinstance(dataset, str)
processed_data_dir = os.path.join(cfg.preprocess.processed_dir, dataset)
meta_file = cfg.preprocess.valid_file if is_valid else cfg.preprocess.train_file
self.metafile_path = os.path.join(processed_data_dir, meta_file)
self.metadata = self.get_metadata()
self.data_root = processed_data_dir
self.cfg = cfg
if cfg.preprocess.use_audio:
self.utt2audio_path = {}
for utt_info in self.metadata:
dataset = utt_info["Dataset"]
uid = utt_info["Uid"]
utt = "{}_{}".format(dataset, uid)
self.utt2audio_path[utt] = os.path.join(
cfg.preprocess.processed_dir,
dataset,
cfg.preprocess.audio_dir,
uid + ".npy",
)
elif cfg.preprocess.use_label:
self.utt2label_path = {}
for utt_info in self.metadata:
dataset = utt_info["Dataset"]
uid = utt_info["Uid"]
utt = "{}_{}".format(dataset, uid)
self.utt2label_path[utt] = os.path.join(
cfg.preprocess.processed_dir,
dataset,
cfg.preprocess.label_dir,
uid + ".npy",
)
elif cfg.preprocess.use_one_hot:
self.utt2one_hot_path = {}
for utt_info in self.metadata:
dataset = utt_info["Dataset"]
uid = utt_info["Uid"]
utt = "{}_{}".format(dataset, uid)
self.utt2one_hot_path[utt] = os.path.join(
cfg.preprocess.processed_dir,
dataset,
cfg.preprocess.one_hot_dir,
uid + ".npy",
)
if cfg.preprocess.use_mel:
self.utt2mel_path = {}
for utt_info in self.metadata:
dataset = utt_info["Dataset"]
uid = utt_info["Uid"]
utt = "{}_{}".format(dataset, uid)
self.utt2mel_path[utt] = os.path.join(
cfg.preprocess.processed_dir,
dataset,
cfg.preprocess.mel_dir,
uid + ".npy",
)
if cfg.preprocess.use_frame_pitch:
self.utt2frame_pitch_path = {}
for utt_info in self.metadata:
dataset = utt_info["Dataset"]
uid = utt_info["Uid"]
utt = "{}_{}".format(dataset, uid)
self.utt2frame_pitch_path[utt] = os.path.join(
cfg.preprocess.processed_dir,
dataset,
cfg.preprocess.pitch_dir,
uid + ".npy",
)
if cfg.preprocess.use_uv:
self.utt2uv_path = {}
for utt_info in self.metadata:
dataset = utt_info["Dataset"]
uid = utt_info["Uid"]
utt = "{}_{}".format(dataset, uid)
self.utt2uv_path[utt] = os.path.join(
cfg.preprocess.processed_dir,
dataset,
cfg.preprocess.uv_dir,
uid + ".npy",
)
if cfg.preprocess.use_amplitude_phase:
self.utt2logamp_path = {}
self.utt2pha_path = {}
self.utt2rea_path = {}
self.utt2imag_path = {}
for utt_info in self.metadata:
dataset = utt_info["Dataset"]
uid = utt_info["Uid"]
utt = "{}_{}".format(dataset, uid)
self.utt2logamp_path[utt] = os.path.join(
cfg.preprocess.processed_dir,
dataset,
cfg.preprocess.log_amplitude_dir,
uid + ".npy",
)
self.utt2pha_path[utt] = os.path.join(
cfg.preprocess.processed_dir,
dataset,
cfg.preprocess.phase_dir,
uid + ".npy",
)
self.utt2rea_path[utt] = os.path.join(
cfg.preprocess.processed_dir,
dataset,
cfg.preprocess.real_dir,
uid + ".npy",
)
self.utt2imag_path[utt] = os.path.join(
cfg.preprocess.processed_dir,
dataset,
cfg.preprocess.imaginary_dir,
uid + ".npy",
)
def __getitem__(self, index):
utt_info = self.metadata[index]
dataset = utt_info["Dataset"]
uid = utt_info["Uid"]
utt = "{}_{}".format(dataset, uid)
single_feature = dict()
if self.cfg.preprocess.use_mel:
mel = np.load(self.utt2mel_path[utt])
assert mel.shape[0] == self.cfg.preprocess.n_mel # [n_mels, T]
if "target_len" not in single_feature.keys():
single_feature["target_len"] = mel.shape[1]
single_feature["mel"] = mel
if self.cfg.preprocess.use_frame_pitch:
frame_pitch = np.load(self.utt2frame_pitch_path[utt])
if "target_len" not in single_feature.keys():
single_feature["target_len"] = len(frame_pitch)
aligned_frame_pitch = align_length(
frame_pitch, single_feature["target_len"]
)
single_feature["frame_pitch"] = aligned_frame_pitch
if self.cfg.preprocess.use_audio:
audio = np.load(self.utt2audio_path[utt])
single_feature["audio"] = audio
return single_feature
def get_metadata(self):
with open(self.metafile_path, "r", encoding="utf-8") as f:
metadata = json.load(f)
return metadata
def get_dataset_name(self):
return self.metadata[0]["Dataset"]
def __len__(self):
return len(self.metadata)
class VocoderConcatDataset(ConcatDataset):
def __init__(self, datasets: Iterable[Dataset], full_audio_inference=False):
"""Concatenate a series of datasets with their random inference audio merged."""
super().__init__(datasets)
self.cfg = self.datasets[0].cfg
self.metadata = []
# Merge metadata
for dataset in self.datasets:
self.metadata += dataset.metadata
# Merge random inference features
if full_audio_inference:
self.eval_audios = []
self.eval_dataset_names = []
if self.cfg.preprocess.use_mel:
self.eval_mels = []
if self.cfg.preprocess.use_frame_pitch:
self.eval_pitchs = []
for dataset in self.datasets:
self.eval_audios.append(dataset.eval_audio)
self.eval_dataset_names.append(dataset.get_dataset_name())
if self.cfg.preprocess.use_mel:
self.eval_mels.append(dataset.eval_mel)
if self.cfg.preprocess.use_frame_pitch:
self.eval_pitchs.append(dataset.eval_pitch)
class VocoderCollator(object):
"""Zero-pads model inputs and targets based on number of frames per step"""
def __init__(self, cfg):
self.cfg = cfg
def __call__(self, batch):
packed_batch_features = dict()
# mel: [b, n_mels, frame]
# frame_pitch: [b, frame]
# audios: [b, frame * hop_size]
for key in batch[0].keys():
if key == "target_len":
packed_batch_features["target_len"] = torch.LongTensor(
[b["target_len"] for b in batch]
)
masks = [
torch.ones((b["target_len"], 1), dtype=torch.long) for b in batch
]
packed_batch_features["mask"] = pad_sequence(
masks, batch_first=True, padding_value=0
)
elif key == "mel":
values = [torch.from_numpy(b[key]).T for b in batch]
packed_batch_features[key] = pad_sequence(
values, batch_first=True, padding_value=0
)
else:
values = [torch.from_numpy(b[key]) for b in batch]
packed_batch_features[key] = pad_sequence(
values, batch_first=True, padding_value=0
)
return packed_batch_features
|