Ocr Stn Cnn Transformer Base
This repository contains a ResNet + Transformer decoder checkpoint for Khmer OCR, I don’t have a public paper for this model — everything comes from thousands of experiments across different model architectures and...
Model source
- Kind
- Other
- File size
- 273 MB
- Version
- vRevision 0f4b9e9
- Updated
- Sep 17, 2026
- Downloads
- 24
- Tasks
- Captioning
- Source
- Hugging Face
Source description
Khmer OCR CNN + Transformer
This repository contains a ResNet + Transformer decoder checkpoint for Khmer OCR, I don’t have a public paper for this model — everything comes from thousands of experiments across different model architectures and datasets.
Installation
pip install mer
Usage
from mer import Mer
model = Mer(markdown=True, device='cuda')
result = model.predict("sample_image.png")
print("Predicted text:", result)
Sources
1 source
Sources
1 sourceVerified Sep 17
Model artifacts
1 artifact
Model artifacts
1 artifactSource excerpts
2 excerpts
Source excerpts
2 excerpts--- language: - km license: apache-2.0 tags: - ocr - transformer - vision pipeline_tag: image-to-text --- # Khmer OCR CNN + Transformer This repository contains a ResNet + Transformer decoder checkpoint for Khmer OCR, I don’t have a public paper for this model — everything comes from thousands of experiments across different model architectures and datasets. ## Installation ```python pip install mer ``` ## Usage ```python from mer import Mer model = Mer(markdown=True, device='cuda') result = model.predict("sample_image.png") print("Predicted text:", result) ```
Source context: 24 downloads · 1 likes · Pipeline image-to-text · Repo metythorn/ocr-stn-cnn-transformer-base
