Blame view
egs/sprakbanken/s5/local/normalize_transcript_prefixed.py
1.68 KB
8dcb6dfcb 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 |
#!/usr/bin/env python ''' # Copyright 2013-2014 Mirsk Digital Aps (Author: Andreas Kirkedal) # Copyright 2014-2016 Andreas Kirkedal # 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 import writenumbers ## Global vars # normdict = {",": " ", # ":": " ", # ";": " ", # "?": " ", # "\\": " ", # "\t": " ", # #".": "" # } # t_table = str.maketrans(normdict) ## Utility function def getuttid_text(line): return line.split(" ", 1) ## Main numtable = writenumbers.loadNumTable(sys.argv[1]) textin = codecs.open(sys.argv[2], "r", "utf8") fid = codecs.open(sys.argv[3], "w", "utf8") outtext = codecs.open(sys.argv[4], "w", "utf8") for line in textin: utt_id, text = getuttid_text(line) normtext1 = re.sub(r'[\.,:;\?]', '', text) normtext2 = re.sub(r'[\t\\]', ' ', normtext1) normtext3 = re.sub(r' +', ' ', normtext2.strip()) normtext4 = writenumbers.normNumber(normtext3, numtable) outtext.write(normtext4) fid.write(utt_id + " ") textin.close() outtext.close() fid.close() |