File size: 3,845 Bytes
d5ee97c |
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 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 |
# -*- coding: utf-8 -*-
# Copyright (c) 2017 Keith Ito
#
# Permission is hereby granted, free of charge, to any person obtaining a copy
# of this software and associated documentation files (the "Software"), to deal
# in the Software without restriction, including without limitation the rights
# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
# copies of the Software, and to permit persons to whom the Software is
# furnished to do so, subject to the following conditions:
# The above copyright notice and this permission notice shall be included in
# all copies or substantial portions of the Software.
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
# THE SOFTWARE.
import re
from tensorflow_tts.utils.korean import tokenize as ko_tokenize
from tensorflow_tts.utils.number_norm import normalize_numbers
from unidecode import unidecode
try:
from german_transliterate.core import GermanTransliterate
except:
pass
# Regular expression matching whitespace:
_whitespace_re = re.compile(r"\s+")
# List of (regular expression, replacement) pairs for abbreviations:
_abbreviations = [
(re.compile("\\b%s\\." % x[0], re.IGNORECASE), x[1])
for x in [
("mrs", "misess"),
("mr", "mister"),
("dr", "doctor"),
("st", "saint"),
("co", "company"),
("jr", "junior"),
("maj", "major"),
("gen", "general"),
("drs", "doctors"),
("rev", "reverend"),
("lt", "lieutenant"),
("hon", "honorable"),
("sgt", "sergeant"),
("capt", "captain"),
("esq", "esquire"),
("ltd", "limited"),
("col", "colonel"),
("ft", "fort"),
]
]
def expand_abbreviations(text):
for regex, replacement in _abbreviations:
text = re.sub(regex, replacement, text)
return text
def expand_numbers(text):
return normalize_numbers(text)
def lowercase(text):
return text.lower()
def collapse_whitespace(text):
return re.sub(_whitespace_re, " ", text)
def convert_to_ascii(text):
return unidecode(text)
def basic_cleaners(text):
"""Basic pipeline that lowercases and collapses whitespace without transliteration."""
text = lowercase(text)
text = collapse_whitespace(text)
return text
def transliteration_cleaners(text):
"""Pipeline for non-English text that transliterates to ASCII."""
text = convert_to_ascii(text)
text = lowercase(text)
text = collapse_whitespace(text)
return text
def english_cleaners(text):
"""Pipeline for English text, including number and abbreviation expansion."""
text = convert_to_ascii(text)
text = lowercase(text)
text = expand_numbers(text)
text = expand_abbreviations(text)
text = collapse_whitespace(text)
return text
def korean_cleaners(text):
"""Pipeline for Korean text, including number and abbreviation expansion."""
text = ko_tokenize(
text
) # 'μ‘΄κ²½νλ' --> ['α', 'α
©', 'α«', 'α', 'α
§', 'αΌ', 'α', 'α
‘', 'α', 'α
³', 'α«']
return text
def german_cleaners(text):
"""Pipeline for German text, including number and abbreviation expansion."""
try:
text = GermanTransliterate(replace={';': ',', ':': ' '}, sep_abbreviation=' -- ').transliterate(text)
except NameError:
raise ModuleNotFoundError("Install german_transliterate package to use german_cleaners")
return text |