Defining own tokenizer

[NathanHoy96]

It would be good if we were able to define our own tokenizer or be able to pass a list of tokens to transform. I'm using a workaround at the moment but in sklearn you're able to pass your own tokenizer and preprocessor.

[nkthiebaut]

Good idea, we could implement passing an optional Tokenizer during the EmbeddingTransformer instantiation. Feel free to raise a PR if you have time to give it a try.