| | |
|---|
| | | import numpy as np |
|---|
| | | import yaml |
|---|
| | | |
|---|
| | | from typeguard import check_argument_types |
|---|
| | | |
|---|
| | | import warnings |
|---|
| | | |
|---|
| | |
|---|
| | | class TokenIDConverter(): |
|---|
| | | def __init__(self, token_list: Union[List, str], |
|---|
| | | ): |
|---|
| | | check_argument_types() |
|---|
| | | |
|---|
| | | # self.token_list = self.load_token(token_path) |
|---|
| | | self.token_list = token_list |
|---|
| | | self.unk_symbol = token_list[-1] |
|---|
| | | self.token2id = {v: i for i, v in enumerate(self.token_list)} |
|---|
| | | self.unk_id = self.token2id[self.unk_symbol] |
|---|
| | | |
|---|
| | | |
|---|
| | | def get_num_vocabulary_size(self) -> int: |
|---|
| | | return len(self.token_list) |
|---|
| | |
|---|
| | | return [self.token_list[i] for i in integers] |
|---|
| | | |
|---|
| | | def tokens2ids(self, tokens: Iterable[str]) -> List[int]: |
|---|
| | | token2id = {v: i for i, v in enumerate(self.token_list)} |
|---|
| | | if self.unk_symbol not in token2id: |
|---|
| | | raise TokenIDConverterError( |
|---|
| | | f"Unknown symbol '{self.unk_symbol}' doesn't exist in the token_list" |
|---|
| | | ) |
|---|
| | | unk_id = token2id[self.unk_symbol] |
|---|
| | | return [token2id.get(i, unk_id) for i in tokens] |
|---|
| | | |
|---|
| | | return [self.token2id.get(i, self.unk_id) for i in tokens] |
|---|
| | | |
|---|
| | | |
|---|
| | | class CharTokenizer(): |
|---|
| | |
|---|
| | | space_symbol: str = "<space>", |
|---|
| | | remove_non_linguistic_symbols: bool = False, |
|---|
| | | ): |
|---|
| | | check_argument_types() |
|---|
| | | |
|---|
| | | self.space_symbol = space_symbol |
|---|
| | | self.non_linguistic_symbols = self.load_symbols(symbol_value) |
|---|
