vits-japanese / preprocess.py
quyanh's picture
initial commit
d1ceaed
raw
history blame
1.66 kB
import argparse
import text
from utils import load_filepaths_and_text
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument("--out_extension", default="cleaned")
parser.add_argument("--text_index", default=1, type=int)
# parser.add_argument("--filelists", nargs="+", default=["filelists/ljs_audio_text_val_filelist.txt",
# "filelists/ljs_audio_text_test_filelist.txt"])
# parser.add_argument("--text_cleaners", nargs="+", default=["english_cleaners2"])
parser.add_argument("--filelists", nargs="+", default=["filelists/jp_audio_text_val_filelist.txt",
"filelists/jp_audio_text_test_filelist.txt",
"filelists/jp_audio_text_train_filelist.txt"])
parser.add_argument("--text_cleaners", nargs="+", default=["japanese_cleaner"])
parser.add_argument("--split", required=False, default=":")
args = parser.parse_args()
for filelist in args.filelists:
print("START:", filelist)
filepaths_and_text = load_filepaths_and_text(filelist, args.split)
for i in range(len(filepaths_and_text)):
original_text = filepaths_and_text[i][args.text_index]
cleaned_text = text._clean_text(original_text, args.text_cleaners)
filepaths_and_text[i][args.text_index] = cleaned_text
new_filelist = filelist + "." + args.out_extension
with open(new_filelist, "w", encoding="utf-8") as f:
f.writelines([args.split.join(x) + "\n" for x in filepaths_and_text])