# Pipelines without a tokenizer

**URL:** <https://discuss.huggingface.co/t/pipelines-without-a-tokenizer/9301>\
**Category:** 🤗Transformers\
**Created:** [August 17, 2021, 4:46pm UTC](https://discuss.huggingface.co/t/pipelines-without-a-tokenizer/9301 "2021-08-17T16:46:53Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![brosand](https://avatars.discourse-cdn.com/v4/letter/b/3e96dc/32.png) [@brosand](https://discuss.huggingface.co/u/brosand)\
**Post date:** [August 17, 2021, 4:46pm UTC](https://discuss.huggingface.co/t/pipelines-without-a-tokenizer/9301/1 "2021-08-17T16:46:53Z")

</div>

Hello,

I am trying to use a pipeline for zero-shot classification, and due to my need to pretokenize the data in order to split large text, I have tokenized data I would like to feed into the pipeline. Is there any way to do this? I don’t see any options to run a pipeline without a tokenizer.

Is my only method to define some new tokenizer that doesn’t actually do anything?

Thanks

---

<div class="post-metadata">

**Author:** ![Illuminarchie](https://avatars.discourse-cdn.com/v4/letter/i/c5a1d2/32.png) [@Illuminarchie](https://discuss.huggingface.co/u/Illuminarchie)\
**Post date:** [February 19, 2024, 12:27am UTC](https://discuss.huggingface.co/t/pipelines-without-a-tokenizer/9301/2 "2024-02-19T00:27:25Z")

</div>

Hi,

Hate to bring this back up, but did you ever find a solution to this? I was thinking of trying to make a custom tokenizer which doesn’t do anything, but I was wondering if you found any good solution ! Thank you!