File size: 5,768 Bytes
ad16788 |
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 |
#!/usr/bin/env python3
# Copyright 2018 Nagoya University (Tomoki Hayashi)
# Apache 2.0 (http://www.apache.org/licenses/LICENSE-2.0)
"""TTS decoding script."""
import configargparse
import logging
import os
import platform
import subprocess
import sys
from espnet.utils.cli_utils import strtobool
# NOTE: you need this func to generate our sphinx doc
def get_parser():
"""Get parser of decoding arguments."""
parser = configargparse.ArgumentParser(
description="Synthesize speech from text using a TTS model on one CPU",
config_file_parser_class=configargparse.YAMLConfigFileParser,
formatter_class=configargparse.ArgumentDefaultsHelpFormatter,
)
# general configuration
parser.add("--config", is_config_file=True, help="config file path")
parser.add(
"--config2",
is_config_file=True,
help="second config file path that overwrites the settings in `--config`.",
)
parser.add(
"--config3",
is_config_file=True,
help="third config file path that overwrites "
"the settings in `--config` and `--config2`.",
)
parser.add_argument("--ngpu", default=0, type=int, help="Number of GPUs")
parser.add_argument(
"--backend",
default="pytorch",
type=str,
choices=["chainer", "pytorch"],
help="Backend library",
)
parser.add_argument("--debugmode", default=1, type=int, help="Debugmode")
parser.add_argument("--seed", default=1, type=int, help="Random seed")
parser.add_argument("--out", type=str, required=True, help="Output filename")
parser.add_argument("--verbose", "-V", default=0, type=int, help="Verbose option")
parser.add_argument(
"--preprocess-conf",
type=str,
default=None,
help="The configuration file for the pre-processing",
)
# task related
parser.add_argument(
"--json", type=str, required=True, help="Filename of train label data (json)"
)
parser.add_argument(
"--model", type=str, required=True, help="Model file parameters to read"
)
parser.add_argument(
"--model-conf", type=str, default=None, help="Model config file"
)
# decoding related
parser.add_argument(
"--maxlenratio", type=float, default=5, help="Maximum length ratio in decoding"
)
parser.add_argument(
"--minlenratio", type=float, default=0, help="Minimum length ratio in decoding"
)
parser.add_argument(
"--threshold", type=float, default=0.5, help="Threshold value in decoding"
)
parser.add_argument(
"--use-att-constraint",
type=strtobool,
default=False,
help="Whether to use the attention constraint",
)
parser.add_argument(
"--backward-window",
type=int,
default=1,
help="Backward window size in the attention constraint",
)
parser.add_argument(
"--forward-window",
type=int,
default=3,
help="Forward window size in the attention constraint",
)
parser.add_argument(
"--fastspeech-alpha",
type=float,
default=1.0,
help="Alpha to change the speed for FastSpeech",
)
# save related
parser.add_argument(
"--save-durations",
default=False,
type=strtobool,
help="Whether to save durations converted from attentions",
)
parser.add_argument(
"--save-focus-rates",
default=False,
type=strtobool,
help="Whether to save focus rates of attentions",
)
return parser
def main(args):
"""Run deocding."""
parser = get_parser()
args = parser.parse_args(args)
# logging info
if args.verbose > 0:
logging.basicConfig(
level=logging.INFO,
format="%(asctime)s (%(module)s:%(lineno)d) %(levelname)s: %(message)s",
)
else:
logging.basicConfig(
level=logging.WARN,
format="%(asctime)s (%(module)s:%(lineno)d) %(levelname)s: %(message)s",
)
logging.warning("Skip DEBUG/INFO messages")
# check CUDA_VISIBLE_DEVICES
if args.ngpu > 0:
# python 2 case
if platform.python_version_tuple()[0] == "2":
if "clsp.jhu.edu" in subprocess.check_output(["hostname", "-f"]):
cvd = subprocess.check_output(
["/usr/local/bin/free-gpu", "-n", str(args.ngpu)]
).strip()
logging.info("CLSP: use gpu" + cvd)
os.environ["CUDA_VISIBLE_DEVICES"] = cvd
# python 3 case
else:
if "clsp.jhu.edu" in subprocess.check_output(["hostname", "-f"]).decode():
cvd = (
subprocess.check_output(
["/usr/local/bin/free-gpu", "-n", str(args.ngpu)]
)
.decode()
.strip()
)
logging.info("CLSP: use gpu" + cvd)
os.environ["CUDA_VISIBLE_DEVICES"] = cvd
cvd = os.environ.get("CUDA_VISIBLE_DEVICES")
if cvd is None:
logging.warning("CUDA_VISIBLE_DEVICES is not set.")
elif args.ngpu != len(cvd.split(",")):
logging.error("#gpus is not matched with CUDA_VISIBLE_DEVICES.")
sys.exit(1)
# display PYTHONPATH
logging.info("python path = " + os.environ.get("PYTHONPATH", "(None)"))
# extract
logging.info("backend = " + args.backend)
if args.backend == "pytorch":
from espnet.tts.pytorch_backend.tts import decode
decode(args)
else:
raise NotImplementedError("Only pytorch is supported.")
if __name__ == "__main__":
main(sys.argv[1:])
|