metythorn
/

ViTOCR-base

@@ -9,9 +9,9 @@ tags:
 pipeline_tag: image-to-text
 ---
-# Khmer OCR Transformer
-This repository contains a pure Transformer-based checkpoint for Khmer OCR. Images are patch-embedded and encoded by a Transformer encoder, then decoded autoregressively without any CNN or spatial transformer components.
 ## Installation
 ```python

 pipeline_tag: image-to-text
 ---
+# ViTOCR
+This repository contains a pure Transformer-based checkpoint for Khmer OCR. Images are patch-embedded and encoded by a Transformer encoder, then decoded autoregressively.
 ## Installation
 ```python