# Processor while fine-tuning TrOCR on IAM

**URL:** <https://discuss.huggingface.co/t/processor-while-fine-tuning-trocr-on-iam/63902>\
**Category:** 🤗Transformers\
**Created:** [November 28, 2023, 9:12pm UTC](https://discuss.huggingface.co/t/processor-while-fine-tuning-trocr-on-iam/63902 "2023-11-28T21:12:20Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![jaydeepb](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/jaydeepb/32/14906_2.png) [@jaydeepb](https://discuss.huggingface.co/u/jaydeepb)\
**Post date:** [November 28, 2023, 9:12pm UTC](https://discuss.huggingface.co/t/processor-while-fine-tuning-trocr-on-iam/63902/1 "2023-11-28T21:12:20Z")

</div>

Hi there! I’m fine-tuning the TrOCR base model on binary images where I’m using this processor:

`processor = TrOCRProcessor.from_pretrained('microsoft/trocr-base-handwritten')`

I was wondering if it would be appropriate to use this processor as I’m fine-tuning on binary images and not greyscale. Or should I be using `processor = TrOCRProcessor.from_pretrained('microsoft/trocr-base-stage1')`?