(self, text)
| 164 | self.wordpiece_tokenizer = WordpieceTokenizer(vocab=self.vocab) |
| 165 | |
| 166 | def tokenize(self, text): |
| 167 | split_tokens = [] |
| 168 | for token in self.basic_tokenizer.tokenize(text): |
| 169 | for sub_token in self.wordpiece_tokenizer.tokenize(token): |
| 170 | split_tokens.append(sub_token) |
| 171 | |
| 172 | return split_tokens |
| 173 | |
| 174 | def convert_tokens_to_ids(self, tokens): |
| 175 | return convert_by_vocab(self.vocab, tokens) |
no test coverage detected