File size: 930 Bytes
f8b4a6c |
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 |
from .symbols import *
_symbol_to_id = {s: i for i, s in enumerate(symbols)}
def cleaned_text_to_sequence(cleaned_text, tones, language, symbol_to_id=None):
"""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
"""
symbol_to_id_map = symbol_to_id if symbol_to_id else _symbol_to_id
unk_id = symbol_to_id_map.get("UNK")
if unk_id is None:
phones = [symbol_to_id_map[symbol] for symbol in cleaned_text]
else:
phones = [symbol_to_id_map.get(symbol, unk_id) for symbol in cleaned_text]
tone_start = language_tone_start_map[language]
tones = [i + tone_start for i in tones]
lang_id = language_id_map[language]
lang_ids = [lang_id for _ in phones]
return phones, tones, lang_ids
|