# Trocr results = 'generated\_text': 'SR'

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ftrocr-results-generated-text-sr%2F75479%3E%5C
**Category:** Beginners\
**Created:** [March 1, 2024, 2:12pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ftrocr-results-generated-text-sr%2F75479 "2024-03-01T14:12:28Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![rubinglen](https://avatars.discourse-cdn.com/v4/letter/r/90db22/32.png) [@rubinglen](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Frubinglen)%5C
**Post date:** [March 1, 2024, 2:12pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ftrocr-results-generated-text-sr%2F75479%2F1 "2024-03-01T14:12:28Z")

</div>

I am trying to test the trocr model on hugging face here [microsoft/trocr-base-printed · Hugging Face](https://huggingface.co/microsoft/trocr-base-printed)

And am using their inference api serverless. When I run the example using my own image png file to test it yields only 2 letters, SR…not sure what’s going on here, it is a whole page with text.

```auto
>>> print(query("debut.png"))
[{'generated_text': 'SR:'}]

```

Any advice on how to access the OCR’d version of my png appreciated!