# Slow inference while performing translation

**URL:** <https://discuss.huggingface.co/t/slow-inference-while-performing-translation/18943>\
**Category:** Intermediate\
**Created:** [June 10, 2022, 10:52am UTC](https://discuss.huggingface.co/t/slow-inference-while-performing-translation/18943 "2022-06-10T10:52:08Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![prashanth](https://avatars.discourse-cdn.com/v4/letter/p/439d5e/32.png) [@prashanth](https://discuss.huggingface.co/u/prashanth)\
**Post date:** [June 10, 2022, 10:52am UTC](https://discuss.huggingface.co/t/slow-inference-while-performing-translation/18943/1 "2022-06-10T10:52:08Z")

</div>

Hi,  
I’m using the **mbart** model to perform the translation of **1000 sentences** and I see that the inference is very slow. Each sentence takes about a minute to infer. How do I speed up the inference ( I do have access to GPU).

Any help appreciated,  
Prashanth