train a tokenizer on a data corpus and save model for future use
(self, corpus)
| 509 | raise NotImplementedError('TextTokenizer exists method not implemented') |
| 510 | |
| 511 | def Train(self, corpus): |
| 512 | """train a tokenizer on a data corpus and save model for future use""" |
| 513 | raise NotImplementedError('TextTokenizer Train not implemented') |
| 514 | |
| 515 | def EncodeAsIds(self, text, process_fn=None): |
| 516 | """ |