Spaces:
Runtime error
Runtime error
File size: 3,661 Bytes
e976cda |
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 |
from .symbols import symbols
from . import cleaners
import re
from .korean import jamo_to_korean, EOS, PAD
from .symbols import en_symbols
import string
# 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)}
isEn = False
# Regular expression matching text enclosed in curly braces:
_curly_re = re.compile(r"(.*?)\{(.+?)\}(.*)")
puncuation_table = str.maketrans({key: None for key in string.punctuation})
def convert_to_en_symbols():
'''Converts built-in korean symbols to english, to be used for english training
'''
global _symbol_to_id, _id_to_symbol, isEn
if not isEn:
print(" [!] Converting to english mode")
_symbol_to_id = {s: i for i, s in enumerate(en_symbols)}
_id_to_symbol = {i: s for i, s in enumerate(en_symbols)}
isEn = True
def text_to_sequence(text, cleaner_names):
"""Converts a string of text to a sequence of IDs corresponding to the symbols in the text.
The text can optionally have ARPAbet sequences enclosed in curly braces embedded
in it. For example, "Turn left on {HH AW1 S S T AH0 N} Street."
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 = []
# Check for curly braces and treat their contents as ARPAbet:
while len(text):
m = _curly_re.match(text)
if not m:
sequence += _symbols_to_sequence(_clean_text(text, cleaner_names))
break
sequence += _symbols_to_sequence(_clean_text(m.group(1), cleaner_names))
sequence += _arpabet_to_sequence(m.group(2))
text = m.group(3)
# Append EOS token
sequence.append(_symbol_to_id["~"])
return sequence
#
# def sequence_to_text(sequence):
# """Converts a sequence of IDs back to a string"""
# result = ""
# for symbol_id in sequence:
# if symbol_id in _id_to_symbol:
# s = _id_to_symbol[symbol_id]
# # Enclose ARPAbet back in curly braces:
# if len(s) > 1 and s[0] == "@":
# s = "{%s}" % s[1:]
# result += s
# return result.replace("}{", " ")
def sequence_to_text(sequence, hparams, skip_eos_and_pad=False, combine_jamo=False):
# '''Converts a sequence of IDs back to a string'''
# cleaner_names = [x.strip() for x in hparams.cleaners.split(',')]
# if 'english_cleaners' in cleaner_names and isEn == False:
# convert_to_en_symbols()
result = ''
for symbol_id in sequence:
if symbol_id in _id_to_symbol:
s = _id_to_symbol[symbol_id]
# Enclose ARPAbet back in curly braces:
if len(s) > 1 and s[0] == '@':
s = '{%s}' % s[1:]
if not skip_eos_and_pad or s not in [EOS, PAD]:
result += s
result = result.replace('}{', ' ')
if combine_jamo:
return jamo_to_korean(result)
else:
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
def _symbols_to_sequence(symbols):
return [_symbol_to_id[s] for s in symbols if _should_keep_symbol(s)]
def _arpabet_to_sequence(text):
return _symbols_to_sequence(["@" + s for s in text.split()])
def _should_keep_symbol(s):
return s in _symbol_to_id and s not in ("_", "~")
|