File size: 5,280 Bytes
d9f82df
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
import os
import re

import inflect
import torch
from tokenizers import Tokenizer


# Regular expression matching whitespace:
from unidecode import unidecode

_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


_inflect = inflect.engine()
_comma_number_re = re.compile(r'([0-9][0-9\,]+[0-9])')
_decimal_number_re = re.compile(r'([0-9]+\.[0-9]+)')
_pounds_re = re.compile(r'£([0-9\,]*[0-9]+)')
_dollars_re = re.compile(r'\$([0-9\.\,]*[0-9]+)')
_ordinal_re = re.compile(r'[0-9]+(st|nd|rd|th)')
_number_re = re.compile(r'[0-9]+')


def _remove_commas(m):
  return m.group(1).replace(',', '')


def _expand_decimal_point(m):
  return m.group(1).replace('.', ' point ')


def _expand_dollars(m):
  match = m.group(1)
  parts = match.split('.')
  if len(parts) > 2:
    return match + ' dollars'  # Unexpected format
  dollars = int(parts[0]) if parts[0] else 0
  cents = int(parts[1]) if len(parts) > 1 and parts[1] else 0
  if dollars and cents:
    dollar_unit = 'dollar' if dollars == 1 else 'dollars'
    cent_unit = 'cent' if cents == 1 else 'cents'
    return '%s %s, %s %s' % (dollars, dollar_unit, cents, cent_unit)
  elif dollars:
    dollar_unit = 'dollar' if dollars == 1 else 'dollars'
    return '%s %s' % (dollars, dollar_unit)
  elif cents:
    cent_unit = 'cent' if cents == 1 else 'cents'
    return '%s %s' % (cents, cent_unit)
  else:
    return 'zero dollars'


def _expand_ordinal(m):
  return _inflect.number_to_words(m.group(0))


def _expand_number(m):
  num = int(m.group(0))
  if num > 1000 and num < 3000:
    if num == 2000:
      return 'two thousand'
    elif num > 2000 and num < 2010:
      return 'two thousand ' + _inflect.number_to_words(num % 100)
    elif num % 100 == 0:
      return _inflect.number_to_words(num // 100) + ' hundred'
    else:
      return _inflect.number_to_words(num, andword='', zero='oh', group=2).replace(', ', ' ')
  else:
    return _inflect.number_to_words(num, andword='')


def normalize_numbers(text):
  text = re.sub(_comma_number_re, _remove_commas, text)
  text = re.sub(_pounds_re, r'\1 pounds', text)
  text = re.sub(_dollars_re, _expand_dollars, text)
  text = re.sub(_decimal_number_re, _expand_decimal_point, text)
  text = re.sub(_ordinal_re, _expand_ordinal, text)
  text = re.sub(_number_re, _expand_number, 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 transliterate 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)
  text = text.replace('"', '')
  return text


def lev_distance(s1, s2):
  if len(s1) > len(s2):
    s1, s2 = s2, s1

  distances = range(len(s1) + 1)
  for i2, c2 in enumerate(s2):
    distances_ = [i2 + 1]
    for i1, c1 in enumerate(s1):
      if c1 == c2:
        distances_.append(distances[i1])
      else:
        distances_.append(1 + min((distances[i1], distances[i1 + 1], distances_[-1])))
    distances = distances_
  return distances[-1]


DEFAULT_VOCAB_FILE = os.path.join(os.path.dirname(os.path.realpath(__file__)), '../data/tokenizer.json')


class VoiceBpeTokenizer:
    def __init__(self, vocab_file=None, use_basic_cleaners=False):
        self.tokenizer = Tokenizer.from_file(
          DEFAULT_VOCAB_FILE if vocab_file is None else vocab_file
        )
        if use_basic_cleaners:
            self.preprocess_text = basic_cleaners
        else:
            self.preprocess_text = english_cleaners

    def encode(self, txt):
        txt = self.preprocess_text(txt)
        txt = txt.replace(' ', '[SPACE]')
        return self.tokenizer.encode(txt).ids

    def decode(self, seq):
        if isinstance(seq, torch.Tensor):
            seq = seq.cpu().numpy()
        txt = self.tokenizer.decode(seq, skip_special_tokens=False).replace(' ', '')
        txt = txt.replace('[SPACE]', ' ')
        txt = txt.replace('[STOP]', '')
        txt = txt.replace('[UNK]', '')
        return txt