File size: 4,628 Bytes
9b2107c |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 |
"""Set of default text cleaners"""
# TODO: pick the cleaner for languages dynamically
import re
from anyascii import anyascii
from TTS.tts.utils.text.chinese_mandarin.numbers import replace_numbers_to_characters_in_text
from .english.abbreviations import abbreviations_en
from .english.number_norm import normalize_numbers as en_normalize_numbers
from .english.time_norm import expand_time_english
from .french.abbreviations import abbreviations_fr
# Regular expression matching whitespace:
_whitespace_re = re.compile(r"\s+")
def expand_abbreviations(text, lang="en"):
if lang == "en":
_abbreviations = abbreviations_en
elif lang == "fr":
_abbreviations = abbreviations_fr
for regex, replacement in _abbreviations:
text = re.sub(regex, replacement, text)
return text
def lowercase(text):
return text.lower()
def collapse_whitespace(text):
return re.sub(_whitespace_re, " ", text).strip()
def convert_to_ascii(text):
return anyascii(text)
def remove_aux_symbols(text):
text = re.sub(r"[\<\>\(\)\[\]\"]+", "", text)
return text
def replace_symbols(text, lang="en"):
"""Replace symbols based on the lenguage tag.
Args:
text:
Input text.
lang:
Lenguage identifier. ex: "en", "fr", "pt", "ca".
Returns:
The modified text
example:
input args:
text: "si l'avi cau, diguem-ho"
lang: "ca"
Output:
text: "si lavi cau, diguemho"
"""
text = text.replace(";", ",")
text = text.replace("-", " ") if lang != "ca" else text.replace("-", "")
text = text.replace(":", ",")
if lang == "en":
text = text.replace("&", " and ")
elif lang == "fr":
text = text.replace("&", " et ")
elif lang == "pt":
text = text.replace("&", " e ")
elif lang == "ca":
text = text.replace("&", " i ")
text = text.replace("'", "")
return 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 basic_german_cleaners(text):
"""Pipeline for German text"""
text = lowercase(text)
text = collapse_whitespace(text)
return text
# TODO: elaborate it
def basic_turkish_cleaners(text):
"""Pipeline for Turkish text"""
text = text.replace("I", "ı")
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_time_english(text)
text = en_normalize_numbers(text)
text = expand_abbreviations(text)
text = replace_symbols(text)
text = remove_aux_symbols(text)
text = collapse_whitespace(text)
return text
def phoneme_cleaners(text):
"""Pipeline for phonemes mode, including number and abbreviation expansion."""
text = en_normalize_numbers(text)
text = expand_abbreviations(text)
text = replace_symbols(text)
text = remove_aux_symbols(text)
text = collapse_whitespace(text)
return text
def french_cleaners(text):
"""Pipeline for French text. There is no need to expand numbers, phonemizer already does that"""
text = expand_abbreviations(text, lang="fr")
text = lowercase(text)
text = replace_symbols(text, lang="fr")
text = remove_aux_symbols(text)
text = collapse_whitespace(text)
return text
def portuguese_cleaners(text):
"""Basic pipeline for Portuguese text. There is no need to expand abbreviation and
numbers, phonemizer already does that"""
text = lowercase(text)
text = replace_symbols(text, lang="pt")
text = remove_aux_symbols(text)
text = collapse_whitespace(text)
return text
def chinese_mandarin_cleaners(text: str) -> str:
"""Basic pipeline for chinese"""
text = replace_numbers_to_characters_in_text(text)
return text
def multilingual_cleaners(text):
"""Pipeline for multilingual text"""
text = lowercase(text)
text = replace_symbols(text, lang=None)
text = remove_aux_symbols(text)
text = collapse_whitespace(text)
return text
def no_cleaners(text):
# remove newline characters
text = text.replace("\n", "")
return text
|