File size: 12,834 Bytes
c56c253 |
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 |
from multiprocess.pool import ThreadPool
from speaker_encoder.params_data import *
from speaker_encoder.config import librispeech_datasets, anglophone_nationalites
from datetime import datetime
from speaker_encoder import audio
from pathlib import Path
from tqdm import tqdm
import numpy as np
class DatasetLog:
"""
Registers metadata about the dataset in a text file.
"""
def __init__(self, root, name):
self.text_file = open(Path(root, "Log_%s.txt" % name.replace("/", "_")), "w")
self.sample_data = dict()
start_time = str(datetime.now().strftime("%A %d %B %Y at %H:%M"))
self.write_line("Creating dataset %s on %s" % (name, start_time))
self.write_line("-----")
self._log_params()
def _log_params(self):
from speaker_encoder import params_data
self.write_line("Parameter values:")
for param_name in (p for p in dir(params_data) if not p.startswith("__")):
value = getattr(params_data, param_name)
self.write_line("\t%s: %s" % (param_name, value))
self.write_line("-----")
def write_line(self, line):
self.text_file.write("%s\n" % line)
def add_sample(self, **kwargs):
for param_name, value in kwargs.items():
if not param_name in self.sample_data:
self.sample_data[param_name] = []
self.sample_data[param_name].append(value)
def finalize(self):
self.write_line("Statistics:")
for param_name, values in self.sample_data.items():
self.write_line("\t%s:" % param_name)
self.write_line("\t\tmin %.3f, max %.3f" % (np.min(values), np.max(values)))
self.write_line("\t\tmean %.3f, median %.3f" % (np.mean(values), np.median(values)))
self.write_line("-----")
end_time = str(datetime.now().strftime("%A %d %B %Y at %H:%M"))
self.write_line("Finished on %s" % end_time)
self.text_file.close()
def _init_preprocess_dataset(dataset_name, datasets_root, out_dir) -> (Path, DatasetLog):
dataset_root = datasets_root.joinpath(dataset_name)
if not dataset_root.exists():
print("Couldn\'t find %s, skipping this dataset." % dataset_root)
return None, None
return dataset_root, DatasetLog(out_dir, dataset_name)
def _preprocess_speaker_dirs(speaker_dirs, dataset_name, datasets_root, out_dir, extension,
skip_existing, logger):
print("%s: Preprocessing data for %d speakers." % (dataset_name, len(speaker_dirs)))
# Function to preprocess utterances for one speaker
def preprocess_speaker(speaker_dir: Path):
# Give a name to the speaker that includes its dataset
speaker_name = "_".join(speaker_dir.relative_to(datasets_root).parts)
# Create an output directory with that name, as well as a txt file containing a
# reference to each source file.
speaker_out_dir = out_dir.joinpath(speaker_name)
speaker_out_dir.mkdir(exist_ok=True)
sources_fpath = speaker_out_dir.joinpath("_sources.txt")
# There's a possibility that the preprocessing was interrupted earlier, check if
# there already is a sources file.
if sources_fpath.exists():
try:
with sources_fpath.open("r") as sources_file:
existing_fnames = {line.split(",")[0] for line in sources_file}
except:
existing_fnames = {}
else:
existing_fnames = {}
# Gather all audio files for that speaker recursively
sources_file = sources_fpath.open("a" if skip_existing else "w")
for in_fpath in speaker_dir.glob("**/*.%s" % extension):
# Check if the target output file already exists
out_fname = "_".join(in_fpath.relative_to(speaker_dir).parts)
out_fname = out_fname.replace(".%s" % extension, ".npy")
if skip_existing and out_fname in existing_fnames:
continue
# Load and preprocess the waveform
wav = audio.preprocess_wav(in_fpath)
if len(wav) == 0:
continue
# Create the mel spectrogram, discard those that are too short
frames = audio.wav_to_mel_spectrogram(wav)
if len(frames) < partials_n_frames:
continue
out_fpath = speaker_out_dir.joinpath(out_fname)
np.save(out_fpath, frames)
logger.add_sample(duration=len(wav) / sampling_rate)
sources_file.write("%s,%s\n" % (out_fname, in_fpath))
sources_file.close()
# Process the utterances for each speaker
with ThreadPool(8) as pool:
list(tqdm(pool.imap(preprocess_speaker, speaker_dirs), dataset_name, len(speaker_dirs),
unit="speakers"))
logger.finalize()
print("Done preprocessing %s.\n" % dataset_name)
# Function to preprocess utterances for one speaker
def __preprocess_speaker(speaker_dir: Path, datasets_root: Path, out_dir: Path, extension: str, skip_existing: bool):
# Give a name to the speaker that includes its dataset
speaker_name = "_".join(speaker_dir.relative_to(datasets_root).parts)
# Create an output directory with that name, as well as a txt file containing a
# reference to each source file.
speaker_out_dir = out_dir.joinpath(speaker_name)
speaker_out_dir.mkdir(exist_ok=True)
sources_fpath = speaker_out_dir.joinpath("_sources.txt")
# There's a possibility that the preprocessing was interrupted earlier, check if
# there already is a sources file.
# if sources_fpath.exists():
# try:
# with sources_fpath.open("r") as sources_file:
# existing_fnames = {line.split(",")[0] for line in sources_file}
# except:
# existing_fnames = {}
# else:
# existing_fnames = {}
existing_fnames = {}
# Gather all audio files for that speaker recursively
sources_file = sources_fpath.open("a" if skip_existing else "w")
for in_fpath in speaker_dir.glob("**/*.%s" % extension):
# Check if the target output file already exists
out_fname = "_".join(in_fpath.relative_to(speaker_dir).parts)
out_fname = out_fname.replace(".%s" % extension, ".npy")
if skip_existing and out_fname in existing_fnames:
continue
# Load and preprocess the waveform
wav = audio.preprocess_wav(in_fpath)
if len(wav) == 0:
continue
# Create the mel spectrogram, discard those that are too short
frames = audio.wav_to_mel_spectrogram(wav)
if len(frames) < partials_n_frames:
continue
out_fpath = speaker_out_dir.joinpath(out_fname)
np.save(out_fpath, frames)
# logger.add_sample(duration=len(wav) / sampling_rate)
sources_file.write("%s,%s\n" % (out_fname, in_fpath))
sources_file.close()
return len(wav)
def _preprocess_speaker_dirs_vox2(speaker_dirs, dataset_name, datasets_root, out_dir, extension,
skip_existing, logger):
# from multiprocessing import Pool, cpu_count
from pathos.multiprocessing import ProcessingPool as Pool
# Function to preprocess utterances for one speaker
def __preprocess_speaker(speaker_dir: Path):
# Give a name to the speaker that includes its dataset
speaker_name = "_".join(speaker_dir.relative_to(datasets_root).parts)
# Create an output directory with that name, as well as a txt file containing a
# reference to each source file.
speaker_out_dir = out_dir.joinpath(speaker_name)
speaker_out_dir.mkdir(exist_ok=True)
sources_fpath = speaker_out_dir.joinpath("_sources.txt")
existing_fnames = {}
# Gather all audio files for that speaker recursively
sources_file = sources_fpath.open("a" if skip_existing else "w")
wav_lens = []
for in_fpath in speaker_dir.glob("**/*.%s" % extension):
# Check if the target output file already exists
out_fname = "_".join(in_fpath.relative_to(speaker_dir).parts)
out_fname = out_fname.replace(".%s" % extension, ".npy")
if skip_existing and out_fname in existing_fnames:
continue
# Load and preprocess the waveform
wav = audio.preprocess_wav(in_fpath)
if len(wav) == 0:
continue
# Create the mel spectrogram, discard those that are too short
frames = audio.wav_to_mel_spectrogram(wav)
if len(frames) < partials_n_frames:
continue
out_fpath = speaker_out_dir.joinpath(out_fname)
np.save(out_fpath, frames)
# logger.add_sample(duration=len(wav) / sampling_rate)
sources_file.write("%s,%s\n" % (out_fname, in_fpath))
wav_lens.append(len(wav))
sources_file.close()
return wav_lens
print("%s: Preprocessing data for %d speakers." % (dataset_name, len(speaker_dirs)))
# Process the utterances for each speaker
# with ThreadPool(8) as pool:
# list(tqdm(pool.imap(preprocess_speaker, speaker_dirs), dataset_name, len(speaker_dirs),
# unit="speakers"))
pool = Pool(processes=20)
for i, wav_lens in enumerate(pool.map(__preprocess_speaker, speaker_dirs), 1):
for wav_len in wav_lens:
logger.add_sample(duration=wav_len / sampling_rate)
print(f'{i}/{len(speaker_dirs)} \r')
logger.finalize()
print("Done preprocessing %s.\n" % dataset_name)
def preprocess_librispeech(datasets_root: Path, out_dir: Path, skip_existing=False):
for dataset_name in librispeech_datasets["train"]["other"]:
# Initialize the preprocessing
dataset_root, logger = _init_preprocess_dataset(dataset_name, datasets_root, out_dir)
if not dataset_root:
return
# Preprocess all speakers
speaker_dirs = list(dataset_root.glob("*"))
_preprocess_speaker_dirs(speaker_dirs, dataset_name, datasets_root, out_dir, "flac",
skip_existing, logger)
def preprocess_voxceleb1(datasets_root: Path, out_dir: Path, skip_existing=False):
# Initialize the preprocessing
dataset_name = "VoxCeleb1"
dataset_root, logger = _init_preprocess_dataset(dataset_name, datasets_root, out_dir)
if not dataset_root:
return
# Get the contents of the meta file
with dataset_root.joinpath("vox1_meta.csv").open("r") as metafile:
metadata = [line.split("\t") for line in metafile][1:]
# Select the ID and the nationality, filter out non-anglophone speakers
nationalities = {line[0]: line[3] for line in metadata}
# keep_speaker_ids = [speaker_id for speaker_id, nationality in nationalities.items() if
# nationality.lower() in anglophone_nationalites]
keep_speaker_ids = [speaker_id for speaker_id, nationality in nationalities.items()]
print("VoxCeleb1: using samples from %d (presumed anglophone) speakers out of %d." %
(len(keep_speaker_ids), len(nationalities)))
# Get the speaker directories for anglophone speakers only
speaker_dirs = dataset_root.joinpath("wav").glob("*")
speaker_dirs = [speaker_dir for speaker_dir in speaker_dirs if
speaker_dir.name in keep_speaker_ids]
print("VoxCeleb1: found %d anglophone speakers on the disk, %d missing (this is normal)." %
(len(speaker_dirs), len(keep_speaker_ids) - len(speaker_dirs)))
# Preprocess all speakers
_preprocess_speaker_dirs(speaker_dirs, dataset_name, datasets_root, out_dir, "wav",
skip_existing, logger)
def preprocess_voxceleb2(datasets_root: Path, out_dir: Path, skip_existing=False):
# Initialize the preprocessing
dataset_name = "VoxCeleb2"
dataset_root, logger = _init_preprocess_dataset(dataset_name, datasets_root, out_dir)
if not dataset_root:
return
# Get the speaker directories
# Preprocess all speakers
speaker_dirs = list(dataset_root.joinpath("dev", "aac").glob("*"))
_preprocess_speaker_dirs_vox2(speaker_dirs, dataset_name, datasets_root, out_dir, "m4a",
skip_existing, logger)
|