Created
July 31, 2020 18:47
-
-
Save mjpost/4c54446b7030d7c64b57461d27090650 to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python3 | |
import sys | |
from sacremoses.normalize import MosesPunctNormalizer | |
def main(args): | |
normalizer = MosesPunctNormalizer(lang=args.lang, penn=args.penn) | |
for line in sys.stdin: | |
print(normalizer.normalize(line.rstrip()), flush=True) | |
if __name__ == '__main__': | |
import argparse | |
parser = argparse.ArgumentParser() | |
parser.add_argument('--lang', '-l', default='en') | |
parser.add_argument('--penn', '-p', action='store_true') | |
args = parser.parse_args() | |
main(args) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment