Blame view

egs/hub4_spanish/s5/local/prepare_test_text.pl 1.93 KB
8dcb6dfcb   Yannick Estève   first commit
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
  #!/usr/bin/env perl
  #===============================================================================
  # Copyright (c) 2017  Johns Hopkins University
  #                        (Author: Jan "Yenda" Trmal <jtrmal@gmail.com>)
  #
  # Licensed under the Apache License, Version 2.0 (the "License");
  # you may not use this file except in compliance with the License.
  # You may obtain a copy of the License at
  #
  #  http://www.apache.org/licenses/LICENSE-2.0
  #
  # THIS CODE IS PROVIDED *AS IS* BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
  # KIND, EITHER EXPRESS OR IMPLIED, INCLUDING WITHOUT LIMITATION ANY IMPLIED
  # WARRANTIES OR CONDITIONS OF TITLE, FITNESS FOR A PARTICULAR PURPOSE,
  # MERCHANTABLITY OR NON-INFRINGEMENT.
  # See the Apache 2 License for the specific language governing permissions and
  # limitations under the License.
  #===============================================================================
  
  # the main difference between this script and the prepare_train_data.pl is
  # that in this script we do not remove nor map the word fragments to <unk>
  
  
  use strict;
  use warnings;
  use utf8;
  
  use List::Util qw(max);
  
  binmode(STDOUT, ":utf8");
  binmode(STDERR, ":utf8");
  
  sub  trim { my $s = shift; $s =~ s/^\s+|\s+$//g; return $s };
  
  if (@ARGV != 2) {
    print STDERR "Incorrect number of parameters: $ARGV
  ";
    print STDERR "Script expects two parameters, symbol of unk and the source text
  ";
    die "Example: $0 \"<unk>\" data/eval/text
  ";
  }
  
  my $unk = $ARGV[0];
  open(my $text, "<:encoding(utf-8)", $ARGV[1])
    or die "Cannot open file $ARGV[1]: $!";
  while(<$text>) {
    chomp;
    next if /\[\[NS\]\]/;
    (my $utt, my $line) = split / /, $_, 2;
    $line =~ s/<\/?unclear>//g;
    $line =~ s/<.?foreign( [^ >]+)*>//g;
    $line =~ s/{/</g;
    $line =~ s/}/>/g;
    $line =~ s/[,.?^+*]//g;
    $line =~ s/%([^ ]+)/"<" . lc($1) . ">"/ge;
  
    $line = trim $line;
    next unless $line;
    $line = " $line ";
  
    $line =~ s/^ +//g;
    $line =~ s/ +$//g;
    print "$utt $line
  ";
  }
  close($text);