-
Notifications
You must be signed in to change notification settings - Fork 3
/
encoder_preprocess.py
69 lines (63 loc) · 3.12 KB
/
encoder_preprocess.py
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
from encoder.preprocess import preprocess_persian
from utils.argutils import print_args
from pathlib import Path
import argparse
if __name__ == "__main__":
class MyFormatter(argparse.ArgumentDefaultsHelpFormatter, argparse.RawDescriptionHelpFormatter):
pass
parser = argparse.ArgumentParser(
description="Preprocesses audio files from datasets, encodes them as mel spectrograms and "
"writes them to the disk. This will allow you to train the encoder. The "
"datasets required are at least one of VoxCeleb1, VoxCeleb2 and LibriSpeech. "
"Ideally, you should have all three. You should extract them as they are "
"after having downloaded them and put them in a same directory, e.g.:\n"
"-[datasets_root]\n"
" -LibriSpeech\n"
" -train-other-500\n"
" -VoxCeleb1\n"
" -wav\n"
" -vox1_meta.csv\n"
" -VoxCeleb2\n"
" -dev",
formatter_class=MyFormatter
)
parser.add_argument("datasets_root", type=Path, help=\
"Path to the directory containing your LibriSpeech/TTS and VoxCeleb datasets.")
parser.add_argument("-o", "--out_dir", type=Path, default=argparse.SUPPRESS, help=\
"Path to the output directory that will contain the mel spectrograms. If left out, "
"defaults to <datasets_root>/SV2TTS/encoder/")
parser.add_argument("-d", "--datasets", type=str,
default="librispeech_other,voxceleb1,voxceleb2", help=\
"Comma-separated list of the name of the datasets you want to preprocess. Only the train "
"set of these datasets will be used. Possible names: librispeech_other, voxceleb1, "
"voxceleb2.")
parser.add_argument("-s", "--skip_existing", action="store_true", help=\
"Whether to skip existing output files with the same name. Useful if this script was "
"interrupted.")
parser.add_argument("--no_trim", action="store_true", help=\
"Preprocess audio without trimming silences (not recommended).")
args = parser.parse_args()
# Verify webrtcvad is available
if not args.no_trim:
try:
import webrtcvad
except:
raise ModuleNotFoundError("Package 'webrtcvad' not found. This package enables "
"noise removal and is recommended. Please install and try again. If installation fails, "
"use --no_trim to disable this error message.")
del args.no_trim
# Process the arguments
args.datasets = args.datasets.split(",")
if not hasattr(args, "out_dir"):
args.out_dir = args.datasets_root.joinpath("SV2TTS", "encoder")
assert args.datasets_root.exists()
args.out_dir.mkdir(exist_ok=True, parents=True)
# Preprocess the datasets
print_args(args, parser)
preprocess_func = {
"persian_data": preprocess_persian
}
args = vars(args)
for dataset in args.pop("datasets"):
print("Preprocessing %s" % dataset)
preprocess_func[dataset](**args)