Preprocess text and encode as ids. Return a tokenization object with original text, processed text, and id tokenization.
(self, text, process_fn=None)
| 513 | raise NotImplementedError('TextTokenizer Train not implemented') |
| 514 | |
| 515 | def EncodeAsIds(self, text, process_fn=None): |
| 516 | """ |
| 517 | Preprocess text and encode as ids. Return a tokenization object with |
| 518 | original text, processed text, and id tokenization. |
| 519 | """ |
| 520 | raise NotImplementedError('TextTokenizer EncodeAsIds not implemented') |
| 521 | |
| 522 | def EncodeAsTokens(self, text, process_fn=None): |
| 523 | """ |