---
tags:
- model_hub_mixin
- pytorch_model_hub_mixin
datasets:
- SoyVitou/KhmerSynthetic1M
- seanghay/khmer-hanuman-100k
language:
- km
- en
metrics:
- cer
pipeline_tag: image-to-text
---

TrorYongOCR is a tiny encoder-decoder model for Scene Text Recognition task.
Its image encoder projects image into character embedding space allowing the text decoder to process the image encoding as a prefill prompt and generate character tokens in autoregressive manner.
Current pre-trained weight supports 2 languages: Khmer and English.

# Model Architecture

![](figures/architecture.png)

This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
- Code: https://pypi.org/project/tror-yong-ocr/
- Blog Post: https://kimang18.github.io/krorngai-blog/TrorYongOCR/