espnet2.text.token_id_converter.TokenIDConverter

source

class espnet2.text.token_id_converter.TokenIDConverter(token_list: Path | str | Iterable[str], unk_symbol: str = '<unk>')

Bases: object

get_num_vocabulary_size() → int

ids2tokens(integers: ndarray | Iterable[int]) → List[str]

tokens2ids(tokens: Iterable[str]) → List[int]