Fix for slow the bug tokenizer adding spaces to single id decodes

[DuyguA]

What does this PR do?

Quick fix for a bug with the tokenizer, slow tokenizers add spaces in between when the input is a single id.

Fixes #29489

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?

@ArthurZucker

[HuggingFaceDocBuilderDev]

The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update.

[LysandreJik]

cc @itazap as well!

[itazap]

Thanks for the quick update 🤗 Thanks for merging the tests! Left a few comments about the single special token case, let me know what you think!

[DuyguA]

Thanks for the quick update 🤗 Thanks for merging the tests! Left a few comments about the single special token case, let me know what you think!

No worries, I'll do the changes 😉

[itazap]

Thank you! Nice tests 🤗

[DuyguA]

@ArthurZucker and @LysandreJik merge time please 😉

[DuyguA]

Gentle ping @itazap , can we do the merge? Some commits from the main was failing this branch but looks like all fixed , can we do the merge before any more breaking changes come 😁 😁 😬