BertTokenizer may not be optimal choice for converstion

[MarkusSagen]

Tensorflow supports two (or three) different types of WordPiece tokenizers.
Could be worth testing to use the FastWordPiece tokenizer, since it can build the model from a vocab directly and claims to be faster as mentioned:

• does the wordpiece tool the same with the bert one? tensorflow/text#116
• Generate BERT wordpiece vocab? tensorflow/text#414

But is will likely also require a bit more setup (https://www.tensorflow.org/text/guide/subwords_tokenizer#overview), as WordPiece only see to split words, but the BertTokenizer splits sentences

Goal

• Compare the different tokenizers and see if they yield the same results
• Compare if the new tokenizer can be saved as a Reusable SavedModel
• Test if the models that previously fails now work Tokenizers do not convert tokens correctly #4