(
self,
train: bool,
use_lang_prompt: bool = False,
use_nlp_prompt: bool = False,
token_type: Optional[str] = None,
token_list: Union[Path, str, Iterable[str]] = None,
bpemodel: Union[Path, str, Iterable[str]] = None,
text_cleaner: Collection[str] = None,
g2p_type: Optional[str] = None,
unk_symbol: str = "<unk>",
space_symbol: str = "<space>",
non_linguistic_symbols: Union[Path, str, Iterable[str]] = None,
delimiter: Optional[str] = None,
rir_scp: Optional[str] = None,
rir_apply_prob: float = 1.0,
noise_scp: Optional[str] = None,
noise_apply_prob: float = 1.0,
noise_db_range: str = "3_10",
short_noise_thres: float = 0.5,
aux_task_names: Collection[str] = None,
speech_volume_normalize: float = None,
speech_name: str = "speech",
text_name: List[str] = ["text"],
fs: int = 0,
speaker_change_symbol: Iterable[str] = None,
data_aug_effects: List = None,
data_aug_num: List[int] = [1, 1],
data_aug_prob: float = 0.0,
# only use for whisper
whisper_language: Optional[str] = None,
whisper_task: Optional[str] = None,
)
| 640 | |
| 641 | class CommonPreprocessor_multi(CommonPreprocessor): |
| 642 | def __init__( |
| 643 | self, |
| 644 | train: bool, |
| 645 | use_lang_prompt: bool = False, |
| 646 | use_nlp_prompt: bool = False, |
| 647 | token_type: Optional[str] = None, |
| 648 | token_list: Union[Path, str, Iterable[str]] = None, |
| 649 | bpemodel: Union[Path, str, Iterable[str]] = None, |
| 650 | text_cleaner: Collection[str] = None, |
| 651 | g2p_type: Optional[str] = None, |
| 652 | unk_symbol: str = "<unk>", |
| 653 | space_symbol: str = "<space>", |
| 654 | non_linguistic_symbols: Union[Path, str, Iterable[str]] = None, |
| 655 | delimiter: Optional[str] = None, |
| 656 | rir_scp: Optional[str] = None, |
| 657 | rir_apply_prob: float = 1.0, |
| 658 | noise_scp: Optional[str] = None, |
| 659 | noise_apply_prob: float = 1.0, |
| 660 | noise_db_range: str = "3_10", |
| 661 | short_noise_thres: float = 0.5, |
| 662 | aux_task_names: Collection[str] = None, |
| 663 | speech_volume_normalize: float = None, |
| 664 | speech_name: str = "speech", |
| 665 | text_name: List[str] = ["text"], |
| 666 | fs: int = 0, |
| 667 | speaker_change_symbol: Iterable[str] = None, |
| 668 | data_aug_effects: List = None, |
| 669 | data_aug_num: List[int] = [1, 1], |
| 670 | data_aug_prob: float = 0.0, |
| 671 | # only use for whisper |
| 672 | whisper_language: Optional[str] = None, |
| 673 | whisper_task: Optional[str] = None, |
| 674 | ): |
| 675 | super().__init__( |
| 676 | train=train, |
| 677 | token_type=token_type, |
| 678 | token_list=token_list, |
| 679 | bpemodel=bpemodel, |
| 680 | text_cleaner=text_cleaner, |
| 681 | g2p_type=g2p_type, |
| 682 | unk_symbol=unk_symbol, |
| 683 | space_symbol=space_symbol, |
| 684 | non_linguistic_symbols=non_linguistic_symbols, |
| 685 | delimiter=delimiter, |
| 686 | rir_scp=rir_scp, |
| 687 | rir_apply_prob=rir_apply_prob, |
| 688 | noise_scp=noise_scp, |
| 689 | noise_apply_prob=noise_apply_prob, |
| 690 | noise_db_range=noise_db_range, |
| 691 | short_noise_thres=short_noise_thres, |
| 692 | aux_task_names=aux_task_names, |
| 693 | speech_volume_normalize=speech_volume_normalize, |
| 694 | speech_name=speech_name, |
| 695 | fs=fs, |
| 696 | nonsplit_symbol=speaker_change_symbol, |
| 697 | data_aug_effects=data_aug_effects, |
| 698 | data_aug_num=data_aug_num, |
| 699 | data_aug_prob=data_aug_prob, |
nothing calls this directly
no test coverage detected