File size: 1,736 Bytes
cf1295a |
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 |
""" from https://github.com/keithito/tacotron """
from matcha.text import cleaners
from matcha.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)} # pylint: disable=unnecessary-comprehension
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:
symbol_id = _symbol_to_id[symbol]
sequence += [symbol_id]
# print(text, clean_text, sep='\n')
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]
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
|