File size: 4,458 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 |
# -*- 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.
"""Decode trained Melgan from folder."""
import argparse
import logging
import os
import sys
sys.path.append(".")
import numpy as np
import soundfile as sf
import yaml
from tqdm import tqdm
from tensorflow_tts.configs import MelGANGeneratorConfig
from tensorflow_tts.datasets import MelDataset
from tensorflow_tts.models import TFMelGANGenerator
def main():
"""Run melgan decoding from folder."""
parser = argparse.ArgumentParser(
description="Generate Audio from melspectrogram with trained melgan "
"(See detail in example/melgan/decode_melgan.py)."
)
parser.add_argument(
"--rootdir",
default=None,
type=str,
required=True,
help="directory including ids/durations files.",
)
parser.add_argument(
"--outdir", type=str, required=True, help="directory to save generated speech."
)
parser.add_argument(
"--checkpoint", type=str, required=True, help="checkpoint file to be loaded."
)
parser.add_argument(
"--use-norm", type=int, default=1, help="Use norm or raw melspectrogram."
)
parser.add_argument("--batch-size", type=int, default=8, help="batch_size.")
parser.add_argument(
"--config",
default=None,
type=str,
required=True,
help="yaml format configuration file. if not explicitly provided, "
"it will be searched in the checkpoint directory. (default=None)",
)
parser.add_argument(
"--verbose",
type=int,
default=1,
help="logging level. higher is more logging. (default=1)",
)
args = parser.parse_args()
# set logger
if args.verbose > 1:
logging.basicConfig(
level=logging.DEBUG,
format="%(asctime)s (%(module)s:%(lineno)d) %(levelname)s: %(message)s",
)
elif 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 directory existence
if not os.path.exists(args.outdir):
os.makedirs(args.outdir)
# load config
with open(args.config) as f:
config = yaml.load(f, Loader=yaml.Loader)
config.update(vars(args))
if config["format"] == "npy":
mel_query = "*-norm-feats.npy" if args.use_norm == 1 else "*-raw-feats.npy"
mel_load_fn = np.load
else:
raise ValueError("Only npy is supported.")
# define data-loader
dataset = MelDataset(
root_dir=args.rootdir,
mel_query=mel_query,
mel_load_fn=mel_load_fn,
)
dataset = dataset.create(batch_size=args.batch_size)
# define model and load checkpoint
melgan = TFMelGANGenerator(
config=MelGANGeneratorConfig(**config["melgan_generator_params"]), name="melgan_generator"
)
melgan._build()
melgan.load_weights(args.checkpoint)
for data in tqdm(dataset, desc="[Decoding]"):
utt_ids, mels, mel_lengths = data["utt_ids"], data["mels"], data["mel_lengths"]
# melgan inference.
generated_audios = melgan(mels)
# convert to numpy.
generated_audios = generated_audios.numpy() # [B, T]
# save to outdir
for i, audio in enumerate(generated_audios):
utt_id = utt_ids[i].numpy().decode("utf-8")
sf.write(
os.path.join(args.outdir, f"{utt_id}.wav"),
audio[: mel_lengths[i].numpy() * config["hop_size"]],
config["sampling_rate"],
"PCM_16",
)
if __name__ == "__main__":
main()
|