# Summarization Question

**URL:** <https://discuss.huggingface.co/t/summarization-question/89252>\
**Category:** Beginners\
**Created:** [May 29, 2024, 6:26pm UTC](https://discuss.huggingface.co/t/summarization-question/89252 "2024-05-29T18:26:41Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![SathyaSubra](https://avatars.discourse-cdn.com/v4/letter/s/ccd318/32.png) [@SathyaSubra](https://discuss.huggingface.co/u/SathyaSubra)\
**Post date:** [May 29, 2024, 6:26pm UTC](https://discuss.huggingface.co/t/summarization-question/89252/1 "2024-05-29T18:26:41Z")

</div>

When using a hugging face transformer, do I need to tokenize input text for summarization? I have read a text from pdf, which is super long. Can I pass this directly into the transformer for summarization?