File size: 999 Bytes
c2546a5
 
 
 
 
1a40474
c2546a5
 
 
 
 
 
1a40474
c2546a5
1a40474
c2546a5
1a40474
 
 
 
 
 
 
c2546a5
 
 
1a40474
 
 
 
 
 
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
""" from https://github.com/keithito/tacotron """
from text import cleaners


def text_to_sequence(text, symbols, 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
  '''
    _symbol_to_id = {s: i for i, s in enumerate(symbols)}

    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 _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