normalize_transcript_prefixed.py
1.54 KB
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
#!/usr/bin/env python
'''
# Copyright 2013-2014 Mirsk Digital Aps (Author: Andreas Kirkedal)
# Copyright 2016 KTH Royal Institute of Technology (Author: Emelie Kullmann)
# 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.
'''
import codecs
import sys
import re
## Global vars
normdict = {",": " ",
":": " ",
";": " ",
"?": " ",
"!": " ",
"\\": " ",
"\t": " ",
".": ""
}
t_table = str.maketrans(normdict)
## Utility function
def getuttid_text(line):
return line.split(" ", 1)
## Main
textin = codecs.open(sys.argv[1], "r", "utf8")
fid = codecs.open(sys.argv[2], "w", "utf8")
outtext = codecs.open(sys.argv[3], "w", "utf8")
for line in textin:
utt_id, text = getuttid_text(line)
normtext1 = text.translate(t_table)
normtext2 = re.sub(r' +', ' ', normtext1.strip())
fid.write(utt_id + "\n")
outtext.write(normtext2.upper() + "\n")
textin.close()
outtext.close()
fid.close()