forked from mrq/DL-Art-School
88 lines
2.4 KiB
Python
88 lines
2.4 KiB
Python
""" from https://github.com/keithito/tacotron """
|
|
import re
|
|
|
|
import torch
|
|
|
|
from models.tacotron2.text import cleaners
|
|
from models.tacotron2.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)}
|
|
|
|
# Regular expression matching text enclosed in curly braces:
|
|
_curly_re = re.compile(r'(.*?)\{(.+?)\}(.*)')
|
|
|
|
|
|
def text_to_sequence(text, cleaner_names=['english_cleaners']):
|
|
'''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)
|
|
|
|
return sequence
|
|
|
|
|
|
def sequence_to_text(sequence):
|
|
'''Converts a sequence of IDs back to a string'''
|
|
result = ''
|
|
for symbol_id in sequence:
|
|
if isinstance(symbol_id, torch.Tensor):
|
|
symbol_id = symbol_id.item()
|
|
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 tacotron_symbols():
|
|
return list(_symbol_to_id.keys())
|
|
|
|
|
|
def tacotron_symbol_mapping():
|
|
return _symbol_to_id.copy()
|
|
|
|
|
|
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 != '_' and s != '~'
|