preprocess_cn.py

import argparse
import text_cn
from tqdm import tqdm
def load_filepaths_and_text(filename, split="|"):
  with open(filename, encoding='utf-8') as f:
    filepaths_and_text = [line.strip().split(split) for line in f]
  return 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=["dataset/ESD/output_cn.txt.jieba.txt"])
  parser.add_argument("--text_cleaners", nargs="+", default=["chinese_cleaners1"])

  args = parser.parse_args()
    

  for filelist in args.filelists:
    print("START:", filelist)
    filepaths_and_text = load_filepaths_and_text(filelist)
    for i in tqdm(range(len(filepaths_and_text))):
      original_text = filepaths_and_text[i][args.text_index]
      cleaned_text = text_cn._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(["|".join(x) + "\n" for x in filepaths_and_text])