(self, text)
| 117 | self.wordpiece_tokenizer = WordpieceTokenizer(vocab=self.vocab) |
| 118 | |
| 119 | def tokenize(self, text): |
| 120 | split_tokens = [] |
| 121 | for token in self.basic_tokenizer.tokenize(text): |
| 122 | for sub_token in self.wordpiece_tokenizer.tokenize(token): |
| 123 | split_tokens.append(sub_token) |
| 124 | |
| 125 | return split_tokens |
| 126 | |
| 127 | def convert_tokens_to_ids(self, tokens): |
| 128 | return convert_by_vocab(self.vocab, tokens) |
no outgoing calls
no test coverage detected