# Manually set tokenizer vocabulary

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fmanually-set-tokenizer-vocabulary%2F36946%3E%5C
**Category:** Beginners\
**Created:** [April 18, 2023, 8:03am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fmanually-set-tokenizer-vocabulary%2F36946 "2023-04-18T08:03:34Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![lucadini](https://avatars.discourse-cdn.com/v4/letter/l/d9b06d/32.png) [@lucadini](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Flucadini)%5C
**Post date:** [April 18, 2023, 8:03am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fmanually-set-tokenizer-vocabulary%2F36946%2F1 "2023-04-18T08:03:34Z")

</div>

Hi everyone,

I am currently working with some LMs (GPT2, BERT and T5 like). For some experiments I would like to use a “predetermined” vocabulary. If I have the list of the words, is it possible to build a tokenizer manually setting its vocabulary with my vocabulary?

Thanks in advance!