You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
15 lines
550 B
15 lines
550 B
3 years ago
|
import argparse
|
||
|
|
from text_processing import normalization
|
||
|
|
|
||
|
|
parser = argparse.ArgumentParser(description="Normalize text in Chinese with some rules.")
|
||
|
|
parser.add_argument("input", type=str, help="the input sentences")
|
||
|
|
parser.add_argument("output", type=str, help="path to save the output file.")
|
||
|
|
args = parser.parse_args()
|
||
|
|
|
||
|
|
with open(args.input, 'rt') as fin:
|
||
|
|
with open(args.output, 'wt') as fout:
|
||
|
|
for sent in fin:
|
||
|
|
sent = normalization.normalize_sentence(sent.strip())
|
||
|
|
fout.write(sent)
|
||
|
|
fout.write('\n')
|