File size: 1,140 Bytes
107eeac
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 text.symbols import *

_symbol_to_id = {s: i for i, s in enumerate(symbols)}


def cleaned_text_to_sequence(cleaned_text, tones, language):
    """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
    """
    phones = [_symbol_to_id[symbol] 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 i in phones]
    return phones, tones, lang_ids


def get_bert(
    norm_text, word2ph, language, device, assist_text=None, assist_text_weight=0.7
):
    from .chinese_bert import get_bert_feature as zh_bert
    from .english_bert_mock import get_bert_feature as en_bert
    from .japanese_bert import get_bert_feature as jp_bert

    lang_bert_func_map = {"ZH": zh_bert, "EN": en_bert, "JP": jp_bert}
    bert = lang_bert_func_map[language](
        norm_text, word2ph, device, assist_text, assist_text_weight
    )
    return bert