Support for FastTokenizer in huggingface

[zhipeng-cai]

Hello, I found there is no a corresponding PLBartTokenizerFast in huggingface, do you have a plan to implement a fast version tokenizer?

In fact, I need to call the word_ids() function of fast tokenizer to get the list indicating the original word corresponding to each tokenized token. word_ids = tokenized_inputs.word_ids(batch_index=i)

Or do you have any ways to calculate the original word index corresponding to each tokenized token?

Thank you very much!