Upload 13 files

ko_fine_tuning/text/LICENSE

@@ -0,0 +1,19 @@
+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.

ko_fine_tuning/text/__init__.py

@@ -0,0 +1,56 @@
+""" from https://github.com/keithito/tacotron """
+from text import cleaners
+from text.symbols import symbols
+
+
+# Mappings from symbol to numeric ID and vice versa:
+_symbol_to_id = {s: i for i, s in enumerate(symbols)}
+_id_to_symbol = {i: s for i, s in enumerate(symbols)}
+
+
+def text_to_sequence(text, cleaner_names):
+  '''Converts a string of text to a sequence of IDs corresponding to the symbols in the text.
+    Args:
+      text: string to convert to a sequence
+      cleaner_names: names of the cleaner functions to run the text through
+    Returns:
+      List of integers corresponding to the symbols in the text
+  '''
+  sequence = []
+
+  clean_text = _clean_text(text, cleaner_names)
+  for symbol in clean_text:
+    if symbol not in _symbol_to_id.keys():
+      continue
+    symbol_id = _symbol_to_id[symbol]
+    sequence += [symbol_id]
+  return sequence
+
+
+def cleaned_text_to_sequence(cleaned_text):
+  '''Converts a string of text to a sequence of IDs corresponding to the symbols in the text.
+    Args:
+      text: string to convert to a sequence
+    Returns:
+      List of integers corresponding to the symbols in the text
+  '''
+  sequence = [_symbol_to_id[symbol] for symbol in cleaned_text if symbol in _symbol_to_id.keys()]
+  return sequence
+
+
+def sequence_to_text(sequence):
+  '''Converts a sequence of IDs back to a string'''
+  result = ''
+  for symbol_id in sequence:
+    s = _id_to_symbol[symbol_id]
+    result += s
+  return result
+
+
+def _clean_text(text, cleaner_names):
+  for name in cleaner_names:
+    cleaner = getattr(cleaners, name)
+    if not cleaner:
+      raise Exception('Unknown cleaner: %s' % name)
+    text = cleaner(text)
+  return text

ko_fine_tuning/text/cantonese.py

@@ -0,0 +1,59 @@
+import re
+import cn2an
+import opencc
+
+
+converter = opencc.OpenCC('jyutjyu')
+
+# List of (Latin alphabet, ipa) pairs:
+_latin_to_ipa = [(re.compile('%s' % x[0]), x[1]) for x in [
+    ('A', 'ei˥'),
+    ('B', 'biː˥'),
+    ('C', 'siː˥'),
+    ('D', 'tiː˥'),
+    ('E', 'iː˥'),
+    ('F', 'e˥fuː˨˩'),
+    ('G', 'tsiː˥'),
+    ('H', 'ɪk̚˥tsʰyː˨˩'),
+    ('I', 'ɐi˥'),
+    ('J', 'tsei˥'),
+    ('K', 'kʰei˥'),
+    ('L', 'e˥llou˨˩'),
+    ('M', 'ɛːm˥'),
+    ('N', 'ɛːn˥'),
+    ('O', 'ou˥'),
+    ('P', 'pʰiː˥'),
+    ('Q', 'kʰiːu˥'),
+    ('R', 'aː˥lou˨˩'),
+    ('S', 'ɛː˥siː˨˩'),
+    ('T', 'tʰiː˥'),
+    ('U', 'juː˥'),
+    ('V', 'wiː˥'),
+    ('W', 'tʊk̚˥piː˥juː˥'),
+    ('X', 'ɪk̚˥siː˨˩'),
+    ('Y', 'waːi˥'),
+    ('Z', 'iː˨sɛːt̚˥')
+]]
+
+
+def number_to_cantonese(text):
+    return re.sub(r'\d+(?:\.?\d+)?', lambda x: cn2an.an2cn(x.group()), text)
+
+
+def latin_to_ipa(text):
+    for regex, replacement in _latin_to_ipa:
+        text = re.sub(regex, replacement, text)
+    return text
+
+
+def cantonese_to_ipa(text):
+    text = number_to_cantonese(text.upper())
+    text = converter.convert(text).replace('-','').replace('$',' ')
+    text = re.sub(r'[A-Z]', lambda x: latin_to_ipa(x.group())+' ', text)
+    text = re.sub(r'[、；：]', '，', text)
+    text = re.sub(r'\s*，\s*', ', ', text)
+    text = re.sub(r'\s*。\s*', '. ', text)
+    text = re.sub(r'\s*？\s*', '? ', text)
+    text = re.sub(r'\s*！\s*', '! ', text)
+    text = re.sub(r'\s*$', '', text)
+    return text

ko_fine_tuning/text/cleaners.py

@@ -0,0 +1,129 @@
+import re
+from text.japanese import japanese_to_romaji_with_accent, japanese_to_ipa, japanese_to_ipa2, japanese_to_ipa3
+from text.korean import latin_to_hangul, number_to_hangul, divide_hangul, korean_to_lazy_ipa, korean_to_ipa
+from g2pk2 import G2p
+from text.mandarin import number_to_chinese, chinese_to_bopomofo, latin_to_bopomofo, chinese_to_romaji, chinese_to_lazy_ipa, chinese_to_ipa, chinese_to_ipa2
+#from text.sanskrit import devanagari_to_ipa
+from text.english import english_to_lazy_ipa, english_to_ipa2, english_to_lazy_ipa2
+#from text.thai import num_to_thai, latin_to_thai
+#from text.shanghainese import shanghainese_to_ipa
+#from text.cantonese import cantonese_to_ipa
+#from text.ngu_dialect import ngu_dialect_to_ipa
+
+
+def japanese_cleaners(text):
+    text = japanese_to_romaji_with_accent(text)
+    text = re.sub(r'([A-Za-z])$', r'\1.', text)
+    return text
+
+
+def japanese_cleaners2(text):
+    return japanese_cleaners(text).replace('ts', 'ʦ').replace('...', '…')
+
+
+def korean_cleaners(text):
+    '''Pipeline for Korean text'''
+    text = latin_to_hangul(text)
+    text = number_to_hangul(text)
+    g2p = G2p()
+    text = g2p(text)
+    text = divide_hangul(text)
+    text = re.sub(r'([\u3131-\u3163])$', r'\1.', text)
+    return text
+
+
+def chinese_cleaners(text):
+    '''Pipeline for Chinese text'''
+    text = number_to_chinese(text)
+    text = chinese_to_bopomofo(text)
+    text = latin_to_bopomofo(text)
+    text = re.sub(r'([ˉˊˇˋ˙])$', r'\1。', text)
+    return text
+
+
+def zh_ja_mixture_cleaners(text):
+    text = re.sub(r'\[ZH\](.*?)\[ZH\]',
+                  lambda x: chinese_to_romaji(x.group(1))+' ', text)
+    text = re.sub(r'\[JA\](.*?)\[JA\]', lambda x: japanese_to_romaji_with_accent(
+        x.group(1)).replace('ts', 'ʦ').replace('u', 'ɯ').replace('...', '…')+' ', text)
+    text = re.sub(r'\s+$', '', text)
+    text = re.sub(r'([^\.,!\?\-…~])$', r'\1.', text)
+    return text
+
+
+def sanskrit_cleaners(text):
+    text = text.replace('॥', '।').replace('ॐ', 'ओम्')
+    text = re.sub(r'([^।])$', r'\1।', text)
+    return text
+
+
+def cjks_cleaners(text):
+    text = re.sub(r'\[ZH\](.*?)\[ZH\]',
+                  lambda x: chinese_to_lazy_ipa(x.group(1))+' ', text)
+    text = re.sub(r'\[JA\](.*?)\[JA\]',
+                  lambda x: japanese_to_ipa(x.group(1))+' ', text)
+    text = re.sub(r'\[KO\](.*?)\[KO\]',
+                  lambda x: korean_to_lazy_ipa(x.group(1))+' ', text)
+    text = re.sub(r'\[SA\](.*?)\[SA\]',
+                  lambda x: devanagari_to_ipa(x.group(1))+' ', text)
+    text = re.sub(r'\[EN\](.*?)\[EN\]',
+                  lambda x: english_to_lazy_ipa(x.group(1))+' ', text)
+    text = re.sub(r'\s+$', '', text)
+    text = re.sub(r'([^\.,!\?\-…~])$', r'\1.', text)
+    return text
+
+def cjke_cleaners(text):
+    text = re.sub(r'\[ZH\](.*?)\[ZH\]', lambda x: chinese_to_lazy_ipa(x.group(1)).replace(
+        'ʧ', 'tʃ').replace('ʦ', 'ts').replace('ɥan', 'ɥæn')+' ', text)
+    text = re.sub(r'\[JA\](.*?)\[JA\]', lambda x: japanese_to_ipa(x.group(1)).replace('ʧ', 'tʃ').replace(
+        'ʦ', 'ts').replace('ɥan', 'ɥæn').replace('ʥ', 'dz')+' ', text)
+    text = re.sub(r'\[KO\](.*?)\[KO\]',
+                  lambda x: korean_to_ipa(x.group(1))+' ', text)
+    text = re.sub(r'\[EN\](.*?)\[EN\]', lambda x: english_to_ipa2(x.group(1)).replace('ɑ', 'a').replace(
+        'ɔ', 'o').replace('ɛ', 'e').replace('ɪ', 'i').replace('ʊ', 'u')+' ', text)
+    text = re.sub(r'\s+$', '', text)
+    text = re.sub(r'([^\.,!\?\-…~])$', r'\1.', text)
+    return text
+
+def cjke_cleaners2(text):
+    text = re.sub(r'\[ZH\](.*?)\[ZH\]',
+                  lambda x: chinese_to_ipa(x.group(1))+' ', text)
+    text = re.sub(r'\[JA\](.*?)\[JA\]',
+                  lambda x: japanese_to_ipa2(x.group(1))+' ', text)
+    text = re.sub(r'\[KO\](.*?)\[KO\]',
+                  lambda x: korean_to_ipa(x.group(1))+' ', text)
+    text = re.sub(r'\[EN\](.*?)\[EN\]',
+                  lambda x: english_to_ipa2(x.group(1))+' ', text)
+    text = re.sub(r'\s+$', '', text)
+    text = re.sub(r'([^\.,!\?\-…~])$', r'\1.', text)
+    return text
+
+
+def thai_cleaners(text):
+    text = num_to_thai(text)
+    text = latin_to_thai(text)
+    return text
+
+
+def shanghainese_cleaners(text):
+    text = shanghainese_to_ipa(text)
+    text = re.sub(r'([^\.,!\?\-…~])$', r'\1.', text)
+    return text
+
+
+def chinese_dialect_cleaners(text):
+    text = re.sub(r'\[ZH\](.*?)\[ZH\]',
+                  lambda x: chinese_to_ipa2(x.group(1))+' ', text)
+    text = re.sub(r'\[JA\](.*?)\[JA\]',
+                  lambda x: japanese_to_ipa3(x.group(1)).replace('Q', 'ʔ')+' ', text)
+    text = re.sub(r'\[SH\](.*?)\[SH\]', lambda x: shanghainese_to_ipa(x.group(1)).replace('1', '˥˧').replace('5',
+                  '˧˧˦').replace('6', '˩˩˧').replace('7', '˥').replace('8', '˩˨').replace('ᴀ', 'ɐ').replace('ᴇ', 'e')+' ', text)
+    text = re.sub(r'\[GD\](.*?)\[GD\]',
+                  lambda x: cantonese_to_ipa(x.group(1))+' ', text)
+    text = re.sub(r'\[EN\](.*?)\[EN\]',
+                  lambda x: english_to_lazy_ipa2(x.group(1))+' ', text)
+    text = re.sub(r'\[([A-Z]{2})\](.*?)\[\1\]', lambda x: ngu_dialect_to_ipa(x.group(2), x.group(
+        1)).replace('ʣ', 'dz').replace('ʥ', 'dʑ').replace('ʦ', 'ts').replace('ʨ', 'tɕ')+' ', text)
+    text = re.sub(r'\s+$', '', text)
+    text = re.sub(r'([^\.,!\?\-…~])$', r'\1.', text)
+    return text

ko_fine_tuning/text/english.py

@@ -0,0 +1,188 @@
+""" from https://github.com/keithito/tacotron """
+
+'''
+Cleaners are transformations that run over the input text at both training and eval time.
+
+Cleaners can be selected by passing a comma-delimited list of cleaner names as the "cleaners"
+hyperparameter. Some cleaners are English-specific. You'll typically want to use:
+  1. "english_cleaners" for English text
+  2. "transliteration_cleaners" for non-English text that can be transliterated to ASCII using
+     the Unidecode library (https://pypi.python.org/pypi/Unidecode)
+  3. "basic_cleaners" if you do not want to transliterate (in this case, you should also update
+     the symbols in symbols.py to match your data).
+'''
+
+
+# Regular expression matching whitespace:
+
+
+import re
+import inflect
+from unidecode import unidecode
+import eng_to_ipa as ipa
+_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]+')
+
+# 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'),
+]]
+
+
+# List of (ipa, lazy ipa) pairs:
+_lazy_ipa = [(re.compile('%s' % x[0]), x[1]) for x in [
+    ('r', 'ɹ'),
+    ('æ', 'e'),
+    ('ɑ', 'a'),
+    ('ɔ', 'o'),
+    ('ð', 'z'),
+    ('θ', 's'),
+    ('ɛ', 'e'),
+    ('ɪ', 'i'),
+    ('ʊ', 'u'),
+    ('ʒ', 'ʥ'),
+    ('ʤ', 'ʥ'),
+    ('ˈ', '↓'),
+]]
+
+# List of (ipa, lazy ipa2) pairs:
+_lazy_ipa2 = [(re.compile('%s' % x[0]), x[1]) for x in [
+    ('r', 'ɹ'),
+    ('ð', 'z'),
+    ('θ', 's'),
+    ('ʒ', 'ʑ'),
+    ('ʤ', 'dʑ'),
+    ('ˈ', '↓'),
+]]
+
+# List of (ipa, ipa2) pairs
+_ipa_to_ipa2 = [(re.compile('%s' % x[0]), x[1]) for x in [
+    ('r', 'ɹ'),
+    ('ʤ', 'dʒ'),
+    ('ʧ', 'tʃ')
+]]
+
+
+def expand_abbreviations(text):
+    for regex, replacement in _abbreviations:
+        text = re.sub(regex, replacement, text)
+    return text
+
+
+def collapse_whitespace(text):
+    return re.sub(r'\s+', ' ', text)
+
+
+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 mark_dark_l(text):
+    return re.sub(r'l([^aeiouæɑɔəɛɪʊ ]*(?: |$))', lambda x: 'ɫ'+x.group(1), text)
+
+
+def english_to_ipa(text):
+    text = unidecode(text).lower()
+    text = expand_abbreviations(text)
+    text = normalize_numbers(text)
+    phonemes = ipa.convert(text)
+    phonemes = collapse_whitespace(phonemes)
+    return phonemes
+
+
+def english_to_lazy_ipa(text):
+    text = english_to_ipa(text)
+    for regex, replacement in _lazy_ipa:
+        text = re.sub(regex, replacement, text)
+    return text
+
+
+def english_to_ipa2(text):
+    text = english_to_ipa(text)
+    text = mark_dark_l(text)
+    for regex, replacement in _ipa_to_ipa2:
+        text = re.sub(regex, replacement, text)
+    return text.replace('...', '…')
+
+
+def english_to_lazy_ipa2(text):
+    text = english_to_ipa(text)
+    for regex, replacement in _lazy_ipa2:
+        text = re.sub(regex, replacement, text)
+    return text

ko_fine_tuning/text/japanese.py

@@ -0,0 +1,153 @@
+import re
+from unidecode import unidecode
+import pyopenjtalk
+
+
+# Regular expression matching Japanese without punctuation marks:
+_japanese_characters = re.compile(
+    r'[A-Za-z\d\u3005\u3040-\u30ff\u4e00-\u9fff\uff11-\uff19\uff21-\uff3a\uff41-\uff5a\uff66-\uff9d]')
+
+# Regular expression matching non-Japanese characters or punctuation marks:
+_japanese_marks = re.compile(
+    r'[^A-Za-z\d\u3005\u3040-\u30ff\u4e00-\u9fff\uff11-\uff19\uff21-\uff3a\uff41-\uff5a\uff66-\uff9d]')
+
+# List of (symbol, Japanese) pairs for marks:
+_symbols_to_japanese = [(re.compile('%s' % x[0]), x[1]) for x in [
+    ('％', 'パーセント')
+]]
+
+# List of (romaji, ipa) pairs for marks:
+_romaji_to_ipa = [(re.compile('%s' % x[0]), x[1]) for x in [
+    ('ts', 'ʦ'),
+    ('u', 'ɯ'),
+    ('j', 'ʥ'),
+    ('y', 'j'),
+    ('ni', 'n^i'),
+    ('nj', 'n^'),
+    ('hi', 'çi'),
+    ('hj', 'ç'),
+    ('f', 'ɸ'),
+    ('I', 'i*'),
+    ('U', 'ɯ*'),
+    ('r', 'ɾ')
+]]
+
+# List of (romaji, ipa2) pairs for marks:
+_romaji_to_ipa2 = [(re.compile('%s' % x[0]), x[1]) for x in [
+    ('u', 'ɯ'),
+    ('ʧ', 'tʃ'),
+    ('j', 'dʑ'),
+    ('y', 'j'),
+    ('ni', 'n^i'),
+    ('nj', 'n^'),
+    ('hi', 'çi'),
+    ('hj', 'ç'),
+    ('f', 'ɸ'),
+    ('I', 'i*'),
+    ('U', 'ɯ*'),
+    ('r', 'ɾ')
+]]
+
+# List of (consonant, sokuon) pairs:
+_real_sokuon = [(re.compile('%s' % x[0]), x[1]) for x in [
+    (r'Q([↑↓]*[kg])', r'k#\1'),
+    (r'Q([↑↓]*[tdjʧ])', r't#\1'),
+    (r'Q([↑↓]*[sʃ])', r's\1'),
+    (r'Q([↑↓]*[pb])', r'p#\1')
+]]
+
+# List of (consonant, hatsuon) pairs:
+_real_hatsuon = [(re.compile('%s' % x[0]), x[1]) for x in [
+    (r'N([↑↓]*[pbm])', r'm\1'),
+    (r'N([↑↓]*[ʧʥj])', r'n^\1'),
+    (r'N([↑↓]*[tdn])', r'n\1'),
+    (r'N([↑↓]*[kg])', r'ŋ\1')
+]]
+
+
+def symbols_to_japanese(text):
+    for regex, replacement in _symbols_to_japanese:
+        text = re.sub(regex, replacement, text)
+    return text
+
+
+def japanese_to_romaji_with_accent(text):
+    '''Reference https://r9y9.github.io/ttslearn/latest/notebooks/ch10_Recipe-Tacotron.html'''
+    text = symbols_to_japanese(text)
+    sentences = re.split(_japanese_marks, text)
+    marks = re.findall(_japanese_marks, text)
+    text = ''
+    for i, sentence in enumerate(sentences):
+        if re.match(_japanese_characters, sentence):
+            if text != '':
+                text += ' '
+            labels = pyopenjtalk.extract_fullcontext(sentence)
+            for n, label in enumerate(labels):
+                phoneme = re.search(r'\-([^\+]*)\+', label).group(1)
+                if phoneme not in ['sil', 'pau']:
+                    text += phoneme.replace('ch', 'ʧ').replace('sh',
+                                                               'ʃ').replace('cl', 'Q')
+                else:
+                    continue
+                # n_moras = int(re.search(r'/F:(\d+)_', label).group(1))
+                a1 = int(re.search(r"/A:(\-?[0-9]+)\+", label).group(1))
+                a2 = int(re.search(r"\+(\d+)\+", label).group(1))
+                a3 = int(re.search(r"\+(\d+)/", label).group(1))
+                if re.search(r'\-([^\+]*)\+', labels[n + 1]).group(1) in ['sil', 'pau']:
+                    a2_next = -1
+                else:
+                    a2_next = int(
+                        re.search(r"\+(\d+)\+", labels[n + 1]).group(1))
+                # Accent phrase boundary
+                if a3 == 1 and a2_next == 1:
+                    text += ' '
+                # Falling
+                elif a1 == 0 and a2_next == a2 + 1:
+                    text += '↓'
+                # Rising
+                elif a2 == 1 and a2_next == 2:
+                    text += '↑'
+        if i < len(marks):
+            text += unidecode(marks[i]).replace(' ', '')
+    return text
+
+
+def get_real_sokuon(text):
+    for regex, replacement in _real_sokuon:
+        text = re.sub(regex, replacement, text)
+    return text
+
+
+def get_real_hatsuon(text):
+    for regex, replacement in _real_hatsuon:
+        text = re.sub(regex, replacement, text)
+    return text
+
+
+def japanese_to_ipa(text):
+    text = japanese_to_romaji_with_accent(text).replace('...', '…')
+    text = re.sub(
+        r'([aiueo])\1+', lambda x: x.group(0)[0]+'ː'*(len(x.group(0))-1), text)
+    text = get_real_sokuon(text)
+    text = get_real_hatsuon(text)
+    for regex, replacement in _romaji_to_ipa:
+        text = re.sub(regex, replacement, text)
+    return text
+
+
+def japanese_to_ipa2(text):
+    text = japanese_to_romaji_with_accent(text).replace('...', '…')
+    text = get_real_sokuon(text)
+    text = get_real_hatsuon(text)
+    for regex, replacement in _romaji_to_ipa2:
+        text = re.sub(regex, replacement, text)
+    return text
+
+
+def japanese_to_ipa3(text):
+    text = japanese_to_ipa2(text).replace('n^', 'ȵ').replace(
+        'ʃ', 'ɕ').replace('*', '\u0325').replace('#', '\u031a')
+    text = re.sub(
+        r'([aiɯeo])\1+', lambda x: x.group(0)[0]+'ː'*(len(x.group(0))-1), text)
+    text = re.sub(r'((?:^|\s)(?:ts|tɕ|[kpt]))', r'\1ʰ', text)
+    return text

ko_fine_tuning/text/korean.py

@@ -0,0 +1,210 @@
+import re
+from jamo import h2j, j2hcj
+import ko_pron
+
+
+# This is a list of Korean classifiers preceded by pure Korean numerals.
+_korean_classifiers = '군데 권 개 그루 닢 대 두 마리 모 모금 뭇 발 발짝 방 번 벌 보루 살 수 술 시 쌈 움큼 정 짝 채 척 첩 축 켤레 톨 통'
+
+# List of (hangul, hangul divided) pairs:
+_hangul_divided = [(re.compile('%s' % x[0]), x[1]) for x in [
+    ('ㄳ', 'ㄱㅅ'),
+    ('ㄵ', 'ㄴㅈ'),
+    ('ㄶ', 'ㄴㅎ'),
+    ('ㄺ', 'ㄹㄱ'),
+    ('ㄻ', 'ㄹㅁ'),
+    ('ㄼ', 'ㄹㅂ'),
+    ('ㄽ', 'ㄹㅅ'),
+    ('ㄾ', 'ㄹㅌ'),
+    ('ㄿ', 'ㄹㅍ'),
+    ('ㅀ', 'ㄹㅎ'),
+    ('ㅄ', 'ㅂㅅ'),
+    ('ㅘ', 'ㅗㅏ'),
+    ('ㅙ', 'ㅗㅐ'),
+    ('ㅚ', 'ㅗㅣ'),
+    ('ㅝ', 'ㅜㅓ'),
+    ('ㅞ', 'ㅜㅔ'),
+    ('ㅟ', 'ㅜㅣ'),
+    ('ㅢ', 'ㅡㅣ'),
+    ('ㅑ', 'ㅣㅏ'),
+    ('ㅒ', 'ㅣㅐ'),
+    ('ㅕ', 'ㅣㅓ'),
+    ('ㅖ', 'ㅣㅔ'),
+    ('ㅛ', 'ㅣㅗ'),
+    ('ㅠ', 'ㅣㅜ')
+]]
+
+# List of (Latin alphabet, hangul) pairs:
+_latin_to_hangul = [(re.compile('%s' % x[0], re.IGNORECASE), x[1]) for x in [
+    ('a', '에이'),
+    ('b', '비'),
+    ('c', '시'),
+    ('d', '디'),
+    ('e', '이'),
+    ('f', '에프'),
+    ('g', '지'),
+    ('h', '에이치'),
+    ('i', '아이'),
+    ('j', '제이'),
+    ('k', '케이'),
+    ('l', '엘'),
+    ('m', '엠'),
+    ('n', '엔'),
+    ('o', '오'),
+    ('p', '피'),
+    ('q', '큐'),
+    ('r', '아르'),
+    ('s', '에스'),
+    ('t', '티'),
+    ('u', '유'),
+    ('v', '브이'),
+    ('w', '더블유'),
+    ('x', '엑스'),
+    ('y', '와이'),
+    ('z', '제트')
+]]
+
+# List of (ipa, lazy ipa) pairs:
+_ipa_to_lazy_ipa = [(re.compile('%s' % x[0], re.IGNORECASE), x[1]) for x in [
+    ('t͡ɕ','ʧ'),
+    ('d͡ʑ','ʥ'),
+    ('ɲ','n^'),
+    ('ɕ','ʃ'),
+    ('ʷ','w'),
+    ('ɭ','l`'),
+    ('ʎ','ɾ'),
+    ('ɣ','ŋ'),
+    ('ɰ','ɯ'),
+    ('ʝ','j'),
+    ('ʌ','ə'),
+    ('ɡ','g'),
+    ('\u031a','#'),
+    ('\u0348','='),
+    ('\u031e',''),
+    ('\u0320',''),
+    ('\u0339','')
+]]
+
+
+def latin_to_hangul(text):
+    for regex, replacement in _latin_to_hangul:
+        text = re.sub(regex, replacement, text)
+    return text
+
+
+def divide_hangul(text):
+    text = j2hcj(h2j(text))
+    for regex, replacement in _hangul_divided:
+        text = re.sub(regex, replacement, text)
+    return text
+
+
+def hangul_number(num, sino=True):
+    '''Reference https://github.com/Kyubyong/g2pK'''
+    num = re.sub(',', '', num)
+
+    if num == '0':
+        return '영'
+    if not sino and num == '20':
+        return '스무'
+
+    digits = '123456789'
+    names = '일이삼사오육칠팔구'
+    digit2name = {d: n for d, n in zip(digits, names)}
+
+    modifiers = '한 두 세 네 다섯 여섯 일곱 여덟 아홉'
+    decimals = '열 스물 서른 마흔 쉰 예순 일흔 여든 아흔'
+    digit2mod = {d: mod for d, mod in zip(digits, modifiers.split())}
+    digit2dec = {d: dec for d, dec in zip(digits, decimals.split())}
+
+    spelledout = []
+    for i, digit in enumerate(num):
+        i = len(num) - i - 1
+        if sino:
+            if i == 0:
+                name = digit2name.get(digit, '')
+            elif i == 1:
+                name = digit2name.get(digit, '') + '십'
+                name = name.replace('일십', '십')
+        else:
+            if i == 0:
+                name = digit2mod.get(digit, '')
+            elif i == 1:
+                name = digit2dec.get(digit, '')
+        if digit == '0':
+            if i % 4 == 0:
+                last_three = spelledout[-min(3, len(spelledout)):]
+                if ''.join(last_three) == '':
+                    spelledout.append('')
+                    continue
+            else:
+                spelledout.append('')
+                continue
+        if i == 2:
+            name = digit2name.get(digit, '') + '백'
+            name = name.replace('일백', '백')
+        elif i == 3:
+            name = digit2name.get(digit, '') + '천'
+            name = name.replace('일천', '천')
+        elif i == 4:
+            name = digit2name.get(digit, '') + '만'
+            name = name.replace('일만', '만')
+        elif i == 5:
+            name = digit2name.get(digit, '') + '십'
+            name = name.replace('일십', '십')
+        elif i == 6:
+            name = digit2name.get(digit, '') + '백'
+            name = name.replace('일백', '백')
+        elif i == 7:
+            name = digit2name.get(digit, '') + '천'
+            name = name.replace('일천', '천')
+        elif i == 8:
+            name = digit2name.get(digit, '') + '억'
+        elif i == 9:
+            name = digit2name.get(digit, '') + '십'
+        elif i == 10:
+            name = digit2name.get(digit, '') + '백'
+        elif i == 11:
+            name = digit2name.get(digit, '') + '천'
+        elif i == 12:
+            name = digit2name.get(digit, '') + '조'
+        elif i == 13:
+            name = digit2name.get(digit, '') + '십'
+        elif i == 14:
+            name = digit2name.get(digit, '') + '백'
+        elif i == 15:
+            name = digit2name.get(digit, '') + '천'
+        spelledout.append(name)
+    return ''.join(elem for elem in spelledout)
+
+
+def number_to_hangul(text):
+    '''Reference https://github.com/Kyubyong/g2pK'''
+    tokens = set(re.findall(r'(\d[\d,]*)([\uac00-\ud71f]+)', text))
+    for token in tokens:
+        num, classifier = token
+        if classifier[:2] in _korean_classifiers or classifier[0] in _korean_classifiers:
+            spelledout = hangul_number(num, sino=False)
+        else:
+            spelledout = hangul_number(num, sino=True)
+        text = text.replace(f'{num}{classifier}', f'{spelledout}{classifier}')
+    # digit by digit for remaining digits
+    digits = '0123456789'
+    names = '영일이삼사오육칠팔구'
+    for d, n in zip(digits, names):
+        text = text.replace(d, n)
+    return text
+
+
+def korean_to_lazy_ipa(text):
+    text = latin_to_hangul(text)
+    text = number_to_hangul(text)
+    text=re.sub('[\uac00-\ud7af]+',lambda x:ko_pron.romanise(x.group(0),'ipa').split('] ~ [')[0],text)
+    for regex, replacement in _ipa_to_lazy_ipa:
+        text = re.sub(regex, replacement, text)
+    return text
+
+
+def korean_to_ipa(text):
+    text = korean_to_lazy_ipa(text)
+    return text.replace('ʧ','tʃ').replace('ʥ','dʑ')

ko_fine_tuning/text/mandarin.py

@@ -0,0 +1,326 @@
+import os
+import sys
+import re
+from pypinyin import lazy_pinyin, BOPOMOFO
+import jieba
+import cn2an
+import logging
+
+
+# List of (Latin alphabet, bopomofo) pairs:
+_latin_to_bopomofo = [(re.compile('%s' % x[0], re.IGNORECASE), x[1]) for x in [
+    ('a', 'ㄟˉ'),
+    ('b', 'ㄅㄧˋ'),
+    ('c', 'ㄙㄧˉ'),
+    ('d', 'ㄉㄧˋ'),
+    ('e', 'ㄧˋ'),
+    ('f', 'ㄝˊㄈㄨˋ'),
+    ('g', 'ㄐㄧˋ'),
+    ('h', 'ㄝˇㄑㄩˋ'),
+    ('i', 'ㄞˋ'),
+    ('j', 'ㄐㄟˋ'),
+    ('k', 'ㄎㄟˋ'),
+    ('l', 'ㄝˊㄛˋ'),
+    ('m', 'ㄝˊㄇㄨˋ'),
+    ('n', 'ㄣˉ'),
+    ('o', 'ㄡˉ'),
+    ('p', 'ㄆㄧˉ'),
+    ('q', 'ㄎㄧㄡˉ'),
+    ('r', 'ㄚˋ'),
+    ('s', 'ㄝˊㄙˋ'),
+    ('t', 'ㄊㄧˋ'),
+    ('u', 'ㄧㄡˉ'),
+    ('v', 'ㄨㄧˉ'),
+    ('w', 'ㄉㄚˋㄅㄨˋㄌㄧㄡˋ'),
+    ('x', 'ㄝˉㄎㄨˋㄙˋ'),
+    ('y', 'ㄨㄞˋ'),
+    ('z', 'ㄗㄟˋ')
+]]
+
+# List of (bopomofo, romaji) pairs:
+_bopomofo_to_romaji = [(re.compile('%s' % x[0]), x[1]) for x in [
+    ('ㄅㄛ', 'p⁼wo'),
+    ('ㄆㄛ', 'pʰwo'),
+    ('ㄇㄛ', 'mwo'),
+    ('ㄈㄛ', 'fwo'),
+    ('ㄅ', 'p⁼'),
+    ('ㄆ', 'pʰ'),
+    ('ㄇ', 'm'),
+    ('ㄈ', 'f'),
+    ('ㄉ', 't⁼'),
+    ('ㄊ', 'tʰ'),
+    ('ㄋ', 'n'),
+    ('ㄌ', 'l'),
+    ('ㄍ', 'k⁼'),
+    ('ㄎ', 'kʰ'),
+    ('ㄏ', 'h'),
+    ('ㄐ', 'ʧ⁼'),
+    ('ㄑ', 'ʧʰ'),
+    ('ㄒ', 'ʃ'),
+    ('ㄓ', 'ʦ`⁼'),
+    ('ㄔ', 'ʦ`ʰ'),
+    ('ㄕ', 's`'),
+    ('ㄖ', 'ɹ`'),
+    ('ㄗ', 'ʦ⁼'),
+    ('ㄘ', 'ʦʰ'),
+    ('ㄙ', 's'),
+    ('ㄚ', 'a'),
+    ('ㄛ', 'o'),
+    ('ㄜ', 'ə'),
+    ('ㄝ', 'e'),
+    ('ㄞ', 'ai'),
+    ('ㄟ', 'ei'),
+    ('ㄠ', 'au'),
+    ('ㄡ', 'ou'),
+    ('ㄧㄢ', 'yeNN'),
+    ('ㄢ', 'aNN'),
+    ('ㄧㄣ', 'iNN'),
+    ('ㄣ', 'əNN'),
+    ('ㄤ', 'aNg'),
+    ('ㄧㄥ', 'iNg'),
+    ('ㄨㄥ', 'uNg'),
+    ('ㄩㄥ', 'yuNg'),
+    ('ㄥ', 'əNg'),
+    ('ㄦ', 'əɻ'),
+    ('ㄧ', 'i'),
+    ('ㄨ', 'u'),
+    ('ㄩ', 'ɥ'),
+    ('ˉ', '→'),
+    ('ˊ', '↑'),
+    ('ˇ', '↓↑'),
+    ('ˋ', '↓'),
+    ('˙', ''),
+    ('，', ','),
+    ('。', '.'),
+    ('！', '!'),
+    ('？', '?'),
+    ('—', '-')
+]]
+
+# List of (romaji, ipa) pairs:
+_romaji_to_ipa = [(re.compile('%s' % x[0], re.IGNORECASE), x[1]) for x in [
+    ('ʃy', 'ʃ'),
+    ('ʧʰy', 'ʧʰ'),
+    ('ʧ⁼y', 'ʧ⁼'),
+    ('NN', 'n'),
+    ('Ng', 'ŋ'),
+    ('y', 'j'),
+    ('h', 'x')
+]]
+
+# List of (bopomofo, ipa) pairs:
+_bopomofo_to_ipa = [(re.compile('%s' % x[0]), x[1]) for x in [
+    ('ㄅㄛ', 'p⁼wo'),
+    ('ㄆㄛ', 'pʰwo'),
+    ('ㄇㄛ', 'mwo'),
+    ('ㄈㄛ', 'fwo'),
+    ('ㄅ', 'p⁼'),
+    ('ㄆ', 'pʰ'),
+    ('ㄇ', 'm'),
+    ('ㄈ', 'f'),
+    ('ㄉ', 't⁼'),
+    ('ㄊ', 'tʰ'),
+    ('ㄋ', 'n'),
+    ('ㄌ', 'l'),
+    ('ㄍ', 'k⁼'),
+    ('ㄎ', 'kʰ'),
+    ('ㄏ', 'x'),
+    ('ㄐ', 'tʃ⁼'),
+    ('ㄑ', 'tʃʰ'),
+    ('ㄒ', 'ʃ'),
+    ('ㄓ', 'ts`⁼'),
+    ('ㄔ', 'ts`ʰ'),
+    ('ㄕ', 's`'),
+    ('ㄖ', 'ɹ`'),
+    ('ㄗ', 'ts⁼'),
+    ('ㄘ', 'tsʰ'),
+    ('ㄙ', 's'),
+    ('ㄚ', 'a'),
+    ('ㄛ', 'o'),
+    ('ㄜ', 'ə'),
+    ('ㄝ', 'ɛ'),
+    ('ㄞ', 'aɪ'),
+    ('ㄟ', 'eɪ'),
+    ('ㄠ', 'ɑʊ'),
+    ('ㄡ', 'oʊ'),
+    ('ㄧㄢ', 'jɛn'),
+    ('ㄩㄢ', 'ɥæn'),
+    ('ㄢ', 'an'),
+    ('ㄧㄣ', 'in'),
+    ('ㄩㄣ', 'ɥn'),
+    ('ㄣ', 'ən'),
+    ('ㄤ', 'ɑŋ'),
+    ('ㄧㄥ', 'iŋ'),
+    ('ㄨㄥ', 'ʊŋ'),
+    ('ㄩㄥ', 'jʊŋ'),
+    ('ㄥ', 'əŋ'),
+    ('ㄦ', 'əɻ'),
+    ('ㄧ', 'i'),
+    ('ㄨ', 'u'),
+    ('ㄩ', 'ɥ'),
+    ('ˉ', '→'),
+    ('ˊ', '↑'),
+    ('ˇ', '↓↑'),
+    ('ˋ', '↓'),
+    ('˙', ''),
+    ('，', ','),
+    ('。', '.'),
+    ('！', '!'),
+    ('？', '?'),
+    ('—', '-')
+]]
+
+# List of (bopomofo, ipa2) pairs:
+_bopomofo_to_ipa2 = [(re.compile('%s' % x[0]), x[1]) for x in [
+    ('ㄅㄛ', 'pwo'),
+    ('ㄆㄛ', 'pʰwo'),
+    ('ㄇㄛ', 'mwo'),
+    ('ㄈㄛ', 'fwo'),
+    ('ㄅ', 'p'),
+    ('ㄆ', 'pʰ'),
+    ('ㄇ', 'm'),
+    ('ㄈ', 'f'),
+    ('ㄉ', 't'),
+    ('ㄊ', 'tʰ'),
+    ('ㄋ', 'n'),
+    ('ㄌ', 'l'),
+    ('ㄍ', 'k'),
+    ('ㄎ', 'kʰ'),
+    ('ㄏ', 'h'),
+    ('ㄐ', 'tɕ'),
+    ('ㄑ', 'tɕʰ'),
+    ('ㄒ', 'ɕ'),
+    ('ㄓ', 'tʂ'),
+    ('ㄔ', 'tʂʰ'),
+    ('ㄕ', 'ʂ'),
+    ('ㄖ', 'ɻ'),
+    ('ㄗ', 'ts'),
+    ('ㄘ', 'tsʰ'),
+    ('ㄙ', 's'),
+    ('ㄚ', 'a'),
+    ('ㄛ', 'o'),
+    ('ㄜ', 'ɤ'),
+    ('ㄝ', 'ɛ'),
+    ('ㄞ', 'aɪ'),
+    ('ㄟ', 'eɪ'),
+    ('ㄠ', 'ɑʊ'),
+    ('ㄡ', 'oʊ'),
+    ('ㄧㄢ', 'jɛn'),
+    ('ㄩㄢ', 'yæn'),
+    ('ㄢ', 'an'),
+    ('ㄧㄣ', 'in'),
+    ('ㄩㄣ', 'yn'),
+    ('ㄣ', 'ən'),
+    ('ㄤ', 'ɑŋ'),
+    ('ㄧㄥ', 'iŋ'),
+    ('ㄨㄥ', 'ʊŋ'),
+    ('ㄩㄥ', 'jʊŋ'),
+    ('ㄥ', 'ɤŋ'),
+    ('ㄦ', 'əɻ'),
+    ('ㄧ', 'i'),
+    ('ㄨ', 'u'),
+    ('ㄩ', 'y'),
+    ('ˉ', '˥'),
+    ('ˊ', '˧˥'),
+    ('ˇ', '˨˩˦'),
+    ('ˋ', '˥˩'),
+    ('˙', ''),
+    ('，', ','),
+    ('。', '.'),
+    ('！', '!'),
+    ('？', '?'),
+    ('—', '-')
+]]
+
+
+def number_to_chinese(text):
+    numbers = re.findall(r'\d+(?:\.?\d+)?', text)
+    for number in numbers:
+        text = text.replace(number, cn2an.an2cn(number), 1)
+    return text
+
+
+def chinese_to_bopomofo(text):
+    text = text.replace('、', '，').replace('；', '，').replace('：', '，')
+    words = jieba.lcut(text, cut_all=False)
+    text = ''
+    for word in words:
+        bopomofos = lazy_pinyin(word, BOPOMOFO)
+        if not re.search('[\u4e00-\u9fff]', word):
+            text += word
+            continue
+        for i in range(len(bopomofos)):
+            bopomofos[i] = re.sub(r'([\u3105-\u3129])$', r'\1ˉ', bopomofos[i])
+        if text != '':
+            text += ' '
+        text += ''.join(bopomofos)
+    return text
+
+
+def latin_to_bopomofo(text):
+    for regex, replacement in _latin_to_bopomofo:
+        text = re.sub(regex, replacement, text)
+    return text
+
+
+def bopomofo_to_romaji(text):
+    for regex, replacement in _bopomofo_to_romaji:
+        text = re.sub(regex, replacement, text)
+    return text
+
+
+def bopomofo_to_ipa(text):
+    for regex, replacement in _bopomofo_to_ipa:
+        text = re.sub(regex, replacement, text)
+    return text
+
+
+def bopomofo_to_ipa2(text):
+    for regex, replacement in _bopomofo_to_ipa2:
+        text = re.sub(regex, replacement, text)
+    return text
+
+
+def chinese_to_romaji(text):
+    text = number_to_chinese(text)
+    text = chinese_to_bopomofo(text)
+    text = latin_to_bopomofo(text)
+    text = bopomofo_to_romaji(text)
+    text = re.sub('i([aoe])', r'y\1', text)
+    text = re.sub('u([aoəe])', r'w\1', text)
+    text = re.sub('([ʦsɹ]`[⁼ʰ]?)([→↓↑ ]+|$)',
+                  r'\1ɹ`\2', text).replace('ɻ', 'ɹ`')
+    text = re.sub('([ʦs][⁼ʰ]?)([→↓↑ ]+|$)', r'\1ɹ\2', text)
+    return text
+
+
+def chinese_to_lazy_ipa(text):
+    text = chinese_to_romaji(text)
+    for regex, replacement in _romaji_to_ipa:
+        text = re.sub(regex, replacement, text)
+    return text
+
+
+def chinese_to_ipa(text):
+    text = number_to_chinese(text)
+    text = chinese_to_bopomofo(text)
+    text = latin_to_bopomofo(text)
+    text = bopomofo_to_ipa(text)
+    text = re.sub('i([aoe])', r'j\1', text)
+    text = re.sub('u([aoəe])', r'w\1', text)
+    text = re.sub('([sɹ]`[⁼ʰ]?)([→↓↑ ]+|$)',
+                  r'\1ɹ`\2', text).replace('ɻ', 'ɹ`')
+    text = re.sub('([s][⁼ʰ]?)([→↓↑ ]+|$)', r'\1ɹ\2', text)
+    return text
+
+
+def chinese_to_ipa2(text):
+    text = number_to_chinese(text)
+    text = chinese_to_bopomofo(text)
+    text = latin_to_bopomofo(text)
+    text = bopomofo_to_ipa2(text)
+    text = re.sub(r'i([aoe])', r'j\1', text)
+    text = re.sub(r'u([aoəe])', r'w\1', text)
+    text = re.sub(r'([ʂɹ]ʰ?)([˩˨˧˦˥ ]+|$)', r'\1ʅ\2', text)
+    text = re.sub(r'(sʰ?)([˩˨˧˦˥ ]+|$)', r'\1ɿ\2', text)
+    return text

ko_fine_tuning/text/ngu_dialect.py

@@ -0,0 +1,30 @@
+import re
+import opencc
+
+
+dialects = {'SZ': 'suzhou', 'WX': 'wuxi', 'CZ': 'changzhou', 'HZ': 'hangzhou',
+            'SX': 'shaoxing', 'NB': 'ningbo', 'JJ': 'jingjiang', 'YX': 'yixing',
+            'JD': 'jiading', 'ZR': 'zhenru', 'PH': 'pinghu', 'TX': 'tongxiang',
+            'JS': 'jiashan', 'HN': 'xiashi', 'LP': 'linping', 'XS': 'xiaoshan',
+            'FY': 'fuyang', 'RA': 'ruao', 'CX': 'cixi', 'SM': 'sanmen',
+            'TT': 'tiantai', 'WZ': 'wenzhou', 'SC': 'suichang', 'YB': 'youbu'}
+
+converters = {}
+
+for dialect in dialects.values():
+    try:
+        converters[dialect] = opencc.OpenCC(dialect)
+    except:
+        pass
+
+
+def ngu_dialect_to_ipa(text, dialect):
+    dialect = dialects[dialect]
+    text = converters[dialect].convert(text).replace('-','').replace('$',' ')
+    text = re.sub(r'[、；：]', '，', text)
+    text = re.sub(r'\s*，\s*', ', ', text)
+    text = re.sub(r'\s*。\s*', '. ', text)
+    text = re.sub(r'\s*？\s*', '? ', text)
+    text = re.sub(r'\s*！\s*', '! ', text)
+    text = re.sub(r'\s*$', '', text)
+    return text

ko_fine_tuning/text/sanskrit.py

@@ -0,0 +1,62 @@
+import re
+from indic_transliteration import sanscript
+
+
+# List of (iast, ipa) pairs:
+_iast_to_ipa = [(re.compile('%s' % x[0]), x[1]) for x in [
+    ('a', 'ə'),
+    ('ā', 'aː'),
+    ('ī', 'iː'),
+    ('ū', 'uː'),
+    ('ṛ', 'ɹ`'),
+    ('ṝ', 'ɹ`ː'),
+    ('ḷ', 'l`'),
+    ('ḹ', 'l`ː'),
+    ('e', 'eː'),
+    ('o', 'oː'),
+    ('k', 'k⁼'),
+    ('k⁼h', 'kʰ'),
+    ('g', 'g⁼'),
+    ('g⁼h', 'gʰ'),
+    ('ṅ', 'ŋ'),
+    ('c', 'ʧ⁼'),
+    ('ʧ⁼h', 'ʧʰ'),
+    ('j', 'ʥ⁼'),
+    ('ʥ⁼h', 'ʥʰ'),
+    ('ñ', 'n^'),
+    ('ṭ', 't`⁼'),
+    ('t`⁼h', 't`ʰ'),
+    ('ḍ', 'd`⁼'),
+    ('d`⁼h', 'd`ʰ'),
+    ('ṇ', 'n`'),
+    ('t', 't⁼'),
+    ('t⁼h', 'tʰ'),
+    ('d', 'd⁼'),
+    ('d⁼h', 'dʰ'),
+    ('p', 'p⁼'),
+    ('p⁼h', 'pʰ'),
+    ('b', 'b⁼'),
+    ('b⁼h', 'bʰ'),
+    ('y', 'j'),
+    ('ś', 'ʃ'),
+    ('ṣ', 's`'),
+    ('r', 'ɾ'),
+    ('l̤', 'l`'),
+    ('h', 'ɦ'),
+    ("'", ''),
+    ('~', '^'),
+    ('ṃ', '^')
+]]
+
+
+def devanagari_to_ipa(text):
+    text = text.replace('ॐ', 'ओम्')
+    text = re.sub(r'\s*।\s*$', '.', text)
+    text = re.sub(r'\s*।\s*', ', ', text)
+    text = re.sub(r'\s*॥', '.', text)
+    text = sanscript.transliterate(text, sanscript.DEVANAGARI, sanscript.IAST)
+    for regex, replacement in _iast_to_ipa:
+        text = re.sub(regex, replacement, text)
+    text = re.sub('(.)[`ː]*ḥ', lambda x: x.group(0)
+                  [:-1]+'h'+x.group(1)+'*', text)
+    return text

ko_fine_tuning/text/shanghainese.py

@@ -0,0 +1,64 @@
+import re
+import cn2an
+import opencc
+
+
+converter = opencc.OpenCC('zaonhe')
+
+# List of (Latin alphabet, ipa) pairs:
+_latin_to_ipa = [(re.compile('%s' % x[0]), x[1]) for x in [
+    ('A', 'ᴇ'),
+    ('B', 'bi'),
+    ('C', 'si'),
+    ('D', 'di'),
+    ('E', 'i'),
+    ('F', 'ᴇf'),
+    ('G', 'dʑi'),
+    ('H', 'ᴇtɕʰ'),
+    ('I', 'ᴀi'),
+    ('J', 'dʑᴇ'),
+    ('K', 'kʰᴇ'),
+    ('L', 'ᴇl'),
+    ('M', 'ᴇm'),
+    ('N', 'ᴇn'),
+    ('O', 'o'),
+    ('P', 'pʰi'),
+    ('Q', 'kʰiu'),
+    ('R', 'ᴀl'),
+    ('S', 'ᴇs'),
+    ('T', 'tʰi'),
+    ('U', 'ɦiu'),
+    ('V', 'vi'),
+    ('W', 'dᴀbɤliu'),
+    ('X', 'ᴇks'),
+    ('Y', 'uᴀi'),
+    ('Z', 'zᴇ')
+]]
+
+
+def _number_to_shanghainese(num):
+    num = cn2an.an2cn(num).replace('一十','十').replace('二十', '廿').replace('二', '两')
+    return re.sub(r'((?:^|[^三四五六七八九])十|廿)两', r'\1二', num)
+
+
+def number_to_shanghainese(text):
+    return re.sub(r'\d+(?:\.?\d+)?', lambda x: _number_to_shanghainese(x.group()), text)
+
+
+def latin_to_ipa(text):
+    for regex, replacement in _latin_to_ipa:
+        text = re.sub(regex, replacement, text)
+    return text
+
+
+def shanghainese_to_ipa(text):
+    text = number_to_shanghainese(text.upper())
+    text = converter.convert(text).replace('-','').replace('$',' ')
+    text = re.sub(r'[A-Z]', lambda x: latin_to_ipa(x.group())+' ', text)
+    text = re.sub(r'[、；：]', '，', text)
+    text = re.sub(r'\s*，\s*', ', ', text)
+    text = re.sub(r'\s*。\s*', '. ', text)
+    text = re.sub(r'\s*？\s*', '? ', text)
+    text = re.sub(r'\s*！\s*', '! ', text)
+    text = re.sub(r'\s*$', '', text)
+    return text

ko_fine_tuning/text/symbols.py

@@ -0,0 +1,76 @@
+'''
+Defines the set of symbols used in text input to the model.
+'''
+
+'''# japanese_cleaners
+_pad        = '_'
+_punctuation = ',.!?-'
+_letters = 'AEINOQUabdefghijkmnoprstuvwyzʃʧ↓↑ '
+'''
+
+'''
+# japanese_cleaners2
+_pad        = '_'
+_punctuation = ',.!?-~…'
+_letters = 'AEINOQUabdefghijkmnoprstuvwyzʃʧʦ↓↑ '
+'''
+
+# korean_cleaners
+_pad        = '_'
+_punctuation = ',.!?…~'
+_letters = 'ㄱㄴㄷㄹㅁㅂㅅㅇㅈㅊㅋㅌㅍㅎㄲㄸㅃㅆㅉㅏㅓㅗㅜㅡㅣㅐㅔ '
+
+
+'''# chinese_cleaners
+_pad        = '_'
+_punctuation = '，。！？—…'
+_letters = 'ㄅㄆㄇㄈㄉㄊㄋㄌㄍㄎㄏㄐㄑㄒㄓㄔㄕㄖㄗㄘㄙㄚㄛㄜㄝㄞㄟㄠㄡㄢㄣㄤㄥㄦㄧㄨㄩˉˊˇˋ˙ '
+'''
+
+'''# zh_ja_mixture_cleaners
+_pad        = '_'
+_punctuation = ',.!?-~…'
+_letters = 'AEINOQUabdefghijklmnoprstuvwyzʃʧʦɯɹəɥ⁼ʰ`→↓↑ '
+'''
+
+'''# sanskrit_cleaners
+_pad        = '_'
+_punctuation = '।'
+_letters = 'ँंःअआइईउऊऋएऐओऔकखगघङचछजझञटठडढणतथदधनपफबभमयरलळवशषसहऽािीुूृॄेैोौ्ॠॢ '
+'''
+
+'''# cjks_cleaners
+_pad        = '_'
+_punctuation = ',.!?-~…'
+_letters = 'NQabdefghijklmnopstuvwxyzʃʧʥʦɯɹəɥçɸɾβŋɦː⁼ʰ`^#*=→↓↑ '
+'''
+
+'''# thai_cleaners
+_pad        = '_'
+_punctuation = '.!? '
+_letters = 'กขฃคฆงจฉชซฌญฎฏฐฑฒณดตถทธนบปผฝพฟภมยรฤลวศษสหฬอฮฯะัาำิีึืุูเแโใไๅๆ็่้๊๋์'
+'''
+
+'''# cjke_cleaners2
+_pad        = '_'
+_punctuation = ',.!?-~…'
+_letters = 'NQabdefghijklmnopstuvwxyzɑæʃʑçɯɪɔɛɹðəɫɥɸʊɾʒθβŋɦ⁼ʰ`^#*=ˈˌ→↓↑ '
+'''
+
+'''# shanghainese_cleaners
+_pad        = '_'
+_punctuation = ',.!?…'
+_letters = 'abdfghiklmnopstuvyzøŋȵɑɔɕəɤɦɪɿʑʔʰ̩̃ᴀᴇ15678 '
+'''
+
+'''# chinese_dialect_cleaners
+_pad        = '_'
+_punctuation = ',.!?~…─'
+_letters = '#Nabdefghijklmnoprstuvwxyzæçøŋœȵɐɑɒɓɔɕɗɘəɚɛɜɣɤɦɪɭɯɵɷɸɻɾɿʂʅʊʋʌʏʑʔʦʮʰʷˀː˥˦˧˨˩̥̩̃̚ᴀᴇ↑↓∅ⱼ '
+'''
+
+# Export all symbols:
+symbols = [_pad] + list(_punctuation) + list(_letters)
+
+# Special symbol ids
+SPACE_ID = symbols.index(" ")

ko_fine_tuning/text/thai.py

@@ -0,0 +1,44 @@
+import re
+from num_thai.thainumbers import NumThai
+
+
+num = NumThai()
+
+# List of (Latin alphabet, Thai) pairs:
+_latin_to_thai = [(re.compile('%s' % x[0], re.IGNORECASE), x[1]) for x in [
+    ('a', 'เอ'),
+    ('b','บี'),
+    ('c','ซี'),
+    ('d','ดี'),
+    ('e','อี'),
+    ('f','เอฟ'),
+    ('g','จี'),
+    ('h','เอช'),
+    ('i','ไอ'),
+    ('j','เจ'),
+    ('k','เค'),
+    ('l','แอล'),
+    ('m','เอ็ม'),
+    ('n','เอ็น'),
+    ('o','โอ'),
+    ('p','พี'),
+    ('q','คิว'),
+    ('r','แอร์'),
+    ('s','เอส'),
+    ('t','ที'),
+    ('u','ยู'),
+    ('v','วี'),
+    ('w','ดับเบิลยู'),
+    ('x','เอ็กซ์'),
+    ('y','วาย'),
+    ('z','ซี')
+]]
+
+
+def num_to_thai(text):
+    return re.sub(r'(?:\d+(?:,?\d+)?)+(?:\.\d+(?:,?\d+)?)?', lambda x: ''.join(num.NumberToTextThai(float(x.group(0).replace(',', '')))), text)
+
+def latin_to_thai(text):
+    for regex, replacement in _latin_to_thai:
+        text = re.sub(regex, replacement, text)
+    return text