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.
PaddleSpeech/examples/ted_en_zh/st1/local/remove_punctuation.pl

26 lines
387 B

#!/usr/bin/perl
use warnings;
use strict;
binmode(STDIN,":utf8");
binmode(STDOUT,":utf8");
while(<STDIN>) {
$_ = " $_ ";
# remove punctuation except apostrophe
s/<space>/spacemark/g; # for scoring
s/'/apostrophe/g;
s/[[:punct:]]//g;
s/apostrophe/'/g;
s/spacemark/<space>/g; # for scoring
# remove whitespace
s/\s+/ /g;
s/^\s+//;
s/\s+$//;
print "$_\n";
}