Remove the stripping of the prefix space (and any other mangling that tokenizers might do).

[Narsil]

Superseed #1024

What does this PR do?

Fixes # (issue)

Before submitting

• This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).
• Did you read the contributor guideline,
  Pull Request section?
• Was this discussed/approved via a Github issue or the forum? Please add a link
  to it if that's the case.
• Did you make sure to update the documentation with your changes? Here are the
  documentation guidelines, and
  here are tips on formatting docstrings.
• Did you write any new necessary tests?

Who can review?

Anyone in the community is free to review the PR once the tests have passed. Feel free to tag
members/contributors who may be interested in your PR.

[bangoz]

Hi, I'm the author of #1024 (comment).
I found simply reusing decode_token is elegant, but it may return an empty output if the generated text ends with a token that only represent half of a utf-8 character. That's why in the original PR I created a new but similar function .
Thanks a lot for reviewing my PR!