| | |
| | | from funasr.tokenizer.abs_tokenizer import AbsTokenizer |
| | | |
| | | |
| | | g2p_choices = [ |
| | | g2p_classes = [ |
| | | None, |
| | | "g2p_en", |
| | | "g2p_en_no_space", |
| | |
| | | |
| | | """ |
| | | |
| | | def __init__( |
| | | self, descritive=False, group_vowels=False, to_syl=False, no_space=False |
| | | ): |
| | | def __init__(self, descritive=False, group_vowels=False, to_syl=False, no_space=False): |
| | | self.descritive = descritive |
| | | self.group_vowels = group_vowels |
| | | self.to_syl = to_syl |
| | |
| | | non_linguistic_symbols: Union[Path, str, Iterable[str]] = None, |
| | | space_symbol: str = "<space>", |
| | | remove_non_linguistic_symbols: bool = False, |
| | | **kwargs, |
| | | ): |
| | | if g2p_type is None: |
| | | self.g2p = split_by_space |