File size: 8,659 Bytes
d5ee97c |
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 |
# -*- coding: utf-8 -*-
# Copyright 2020 Minh Nguyen (@dathudeptrai)
#
# 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.
"""Dataset modules."""
import itertools
import logging
import os
import random
import numpy as np
import tensorflow as tf
from tensorflow_tts.datasets.abstract_dataset import AbstractDataset
from tensorflow_tts.utils import find_files
class CharactorDurationMelDataset(AbstractDataset):
"""Tensorflow Charactor Mel dataset."""
def __init__(
self,
root_dir,
charactor_query="*-ids.npy",
mel_query="*-norm-feats.npy",
duration_query="*-durations.npy",
charactor_load_fn=np.load,
mel_load_fn=np.load,
duration_load_fn=np.load,
mel_length_threshold=0,
):
"""Initialize dataset.
Args:
root_dir (str): Root directory including dumped files.
charactor_query (str): Query to find charactor files in root_dir.
mel_query (str): Query to find feature files in root_dir.
duration_query (str): Query to find duration files in root_dir.
charactor_load_fn (func): Function to load charactor file.
mel_load_fn (func): Function to load feature file.
duration_load_fn (func): Function to load duration file.
mel_length_threshold (int): Threshold to remove short feature files.
return_utt_id (bool): Whether to return the utterance id with arrays.
"""
# find all of charactor and mel files.
charactor_files = sorted(find_files(root_dir, charactor_query))
mel_files = sorted(find_files(root_dir, mel_query))
duration_files = sorted(find_files(root_dir, duration_query))
# assert the number of files
assert len(mel_files) != 0, f"Not found any mels files in ${root_dir}."
assert (
len(mel_files) == len(charactor_files) == len(duration_files)
), f"Number of charactor, mel and duration files are different \
({len(mel_files)} vs {len(charactor_files)} vs {len(duration_files)})."
if ".npy" in charactor_query:
suffix = charactor_query[1:]
utt_ids = [os.path.basename(f).replace(suffix, "") for f in charactor_files]
# set global params
self.utt_ids = utt_ids
self.mel_files = mel_files
self.charactor_files = charactor_files
self.duration_files = duration_files
self.mel_load_fn = mel_load_fn
self.charactor_load_fn = charactor_load_fn
self.duration_load_fn = duration_load_fn
self.mel_length_threshold = mel_length_threshold
def get_args(self):
return [self.utt_ids]
def generator(self, utt_ids):
for i, utt_id in enumerate(utt_ids):
mel_file = self.mel_files[i]
charactor_file = self.charactor_files[i]
duration_file = self.duration_files[i]
items = {
"utt_ids": utt_id,
"mel_files": mel_file,
"charactor_files": charactor_file,
"duration_files": duration_file,
}
yield items
@tf.function
def _load_data(self, items):
mel = tf.numpy_function(np.load, [items["mel_files"]], tf.float32)
charactor = tf.numpy_function(np.load, [items["charactor_files"]], tf.int32)
duration = tf.numpy_function(np.load, [items["duration_files"]], tf.int32)
items = {
"utt_ids": items["utt_ids"],
"input_ids": charactor,
"speaker_ids": 0,
"duration_gts": duration,
"mel_gts": mel,
"mel_lengths": len(mel),
}
return items
def create(
self,
allow_cache=False,
batch_size=1,
is_shuffle=False,
map_fn=None,
reshuffle_each_iteration=True,
):
"""Create tf.dataset function."""
output_types = self.get_output_dtypes()
datasets = tf.data.Dataset.from_generator(
self.generator, output_types=output_types, args=(self.get_args())
)
# load data
datasets = datasets.map(
lambda items: self._load_data(items), tf.data.experimental.AUTOTUNE
)
datasets = datasets.filter(
lambda x: x["mel_lengths"] > self.mel_length_threshold
)
if allow_cache:
datasets = datasets.cache()
if is_shuffle:
datasets = datasets.shuffle(
self.get_len_dataset(),
reshuffle_each_iteration=reshuffle_each_iteration,
)
# define padded_shapes
padded_shapes = {
"utt_ids": [],
"input_ids": [None],
"speaker_ids": [],
"duration_gts": [None],
"mel_gts": [None, None],
"mel_lengths": [],
}
datasets = datasets.padded_batch(batch_size, padded_shapes=padded_shapes)
datasets = datasets.prefetch(tf.data.experimental.AUTOTUNE)
return datasets
def get_output_dtypes(self):
output_types = {
"utt_ids": tf.string,
"mel_files": tf.string,
"charactor_files": tf.string,
"duration_files": tf.string,
}
return output_types
def get_len_dataset(self):
return len(self.utt_ids)
def __name__(self):
return "CharactorDurationMelDataset"
class CharactorDataset(AbstractDataset):
"""Tensorflow Charactor dataset."""
def __init__(
self, root_dir, charactor_query="*-ids.npy", charactor_load_fn=np.load,
):
"""Initialize dataset.
Args:
root_dir (str): Root directory including dumped files.
charactor_query (str): Query to find charactor files in root_dir.
charactor_load_fn (func): Function to load charactor file.
return_utt_id (bool): Whether to return the utterance id with arrays.
"""
# find all of charactor and mel files.
charactor_files = sorted(find_files(root_dir, charactor_query))
# assert the number of files
assert (
len(charactor_files) != 0
), f"Not found any char or duration files in ${root_dir}."
if ".npy" in charactor_query:
suffix = charactor_query[1:]
utt_ids = [os.path.basename(f).replace(suffix, "") for f in charactor_files]
# set global params
self.utt_ids = utt_ids
self.charactor_files = charactor_files
self.charactor_load_fn = charactor_load_fn
def get_args(self):
return [self.utt_ids]
def generator(self, utt_ids):
for i, utt_id in enumerate(utt_ids):
charactor_file = self.charactor_files[i]
charactor = self.charactor_load_fn(charactor_file)
items = {"utt_ids": utt_id, "input_ids": charactor}
yield items
def create(
self,
allow_cache=False,
batch_size=1,
is_shuffle=False,
map_fn=None,
reshuffle_each_iteration=True,
):
"""Create tf.dataset function."""
output_types = self.get_output_dtypes()
datasets = tf.data.Dataset.from_generator(
self.generator, output_types=output_types, args=(self.get_args())
)
if allow_cache:
datasets = datasets.cache()
if is_shuffle:
datasets = datasets.shuffle(
self.get_len_dataset(),
reshuffle_each_iteration=reshuffle_each_iteration,
)
# define padded shapes
padded_shapes = {"utt_ids": [], "input_ids": [None]}
datasets = datasets.padded_batch(
batch_size, padded_shapes=padded_shapes, drop_remainder=True
)
datasets = datasets.prefetch(tf.data.experimental.AUTOTUNE)
return datasets
def get_output_dtypes(self):
output_types = {"utt_ids": tf.string, "input_ids": tf.int32}
return output_types
def get_len_dataset(self):
return len(self.utt_ids)
def __name__(self):
return "CharactorDataset"
|