mirror of
https://github.com/modelscope/FunASR
synced 2025-09-15 14:48:36 +08:00
861147c730
* sensevoice finetune * sensevoice finetune * sensevoice finetune * sensevoice finetune * sensevoice finetune * sensevoice finetune * sensevoice finetune * sensevoice finetune * sensevoice finetune * sensevoice finetune * bugfix * update with main (#1631) * update seaco finetune * v1.0.24 --------- Co-authored-by: 维石 <shixian.shi@alibaba-inc.com> * sensevoice * sensevoice * sensevoice * update with main (#1638) * update seaco finetune * v1.0.24 * update rwkv template --------- Co-authored-by: 维石 <shixian.shi@alibaba-inc.com> * sensevoice * sensevoice * sensevoice * sensevoice * sensevoice * sensevoice * sensevoice * sensevoice * sensevoice * sensevoice * sensevoice * sensevoice * sensevoice * sensevoice * sensevoice * sense voice * sense voice * sense voice * sense voice * sense voice * sense voice * sense voice * sense voice * sense voice * sense voice * sense voice * sense voice * sense voice * sense voice * sense voice * sense voice * sense voice * sense voice * sense voice * sense voice * whisper * whisper * update style * update style --------- Co-authored-by: 维石 <shixian.shi@alibaba-inc.com>
51 lines
1.4 KiB
Python
51 lines
1.4 KiB
Python
# Copyright 2017 Google Inc.
|
||
|
||
|
||
# Adapted from https://github.com/google/TextNormalizationCoveringGrammars
|
||
# Russian minimally supervised number grammar.
|
||
|
||
import pynini
|
||
from fun_text_processing.text_normalization.en.graph_utils import (
|
||
DAMO_NON_BREAKING_SPACE,
|
||
DAMO_SPACE,
|
||
)
|
||
from fun_text_processing.text_normalization.ru.utils import get_abs_path
|
||
|
||
RU_LOWER_ALPHA = "абвгдеёжзийклмнопрстуфхцчшщъыьэюя"
|
||
RU_UPPER_ALPHA = RU_LOWER_ALPHA.upper()
|
||
RU_LOWER_ALPHA = pynini.union(*RU_LOWER_ALPHA).optimize()
|
||
RU_UPPER_ALPHA = pynini.union(*RU_UPPER_ALPHA).optimize()
|
||
RU_ALPHA = (RU_LOWER_ALPHA | RU_UPPER_ALPHA).optimize()
|
||
|
||
RU_STRESSED_MAP = [
|
||
("А́", "А'"),
|
||
("Е́", "Е'"),
|
||
("Ё́", "Е'"),
|
||
("И́", "И'"),
|
||
("О́", "О'"),
|
||
("У́", "У'"),
|
||
("Ы́", "Ы'"),
|
||
("Э́", "Э'"),
|
||
("Ю́", "Ю'"),
|
||
("Я́", "Я'"),
|
||
("а́", "а'"),
|
||
("е́", "е'"),
|
||
("ё́", "е'"),
|
||
("и́", "и'"),
|
||
("о́", "о'"),
|
||
("у́", "у'"),
|
||
("ы́", "ы'"),
|
||
("э́", "э'"),
|
||
("ю́", "ю'"),
|
||
("я́", "я'"),
|
||
("ё", "е"),
|
||
("Ё", "Е"),
|
||
]
|
||
|
||
REWRITE_STRESSED = pynini.closure(
|
||
pynini.string_map(RU_STRESSED_MAP).optimize() | RU_ALPHA
|
||
).optimize()
|
||
TO_CYRILLIC = pynini.string_file(get_abs_path("data/latin_to_cyrillic.tsv")).optimize()
|
||
TO_LATIN = pynini.invert(TO_CYRILLIC).optimize()
|
||
RU_ALPHA_OR_SPACE = pynini.union(RU_ALPHA, DAMO_SPACE, DAMO_NON_BREAKING_SPACE).optimize()
|