Update readme

README.md

@@ -27,23 +27,21 @@ High-Accuracy Vietnamese Legal Document Correction
 
 ## **Introduction**
 
-**ProtonX Legal Text Correction (v1.2-NC)** is a **specialized Vietnamese correction model** optimized for:
+### **ProtonX Legal Text Correction (v1.2-NC)**
 
-* legal texts
-* government and administrative documents
-* contracts, decrees, circulars
-* OCR post-processing
-* enterprise compliance systems
-* archival digitization workflows
+A **specialized Vietnamese correction model** engineered for **high-accuracy OCR post-processing**, especially **to fix noisy PaddleOCR outputs** in enterprise and legal workflows.
 
-It corrects:
+#### **Best Use Case (Primary Focus)**: **Fixing PaddleOCR text errors** 
 
-* spelling
-* punctuation
-* diacritics
-* grammar
-* legal terminology normalization
-* formal writing style issues
+<img src="https://protonx.co/assets/img/paddle-ocr-protonx.png">
+
+The model is optimized to clean up real-world OCR mistakes such as:
+
+* missing or incorrect diacritics
+* broken word segmentation
+* misrecognized legal terms
+* punctuation artifacts
+* formatting inconsistencies
 
 Built on a Seq2Seq Transformer architecture, the model is trained on 70,000 correction pairs, including 20,000 pairs manually annotated by expert Vietnamese annotators, covering:
 
@@ -67,10 +65,8 @@ Strict constraints ensure:
 1. **ROUGE-L: 98.44**
 - Achieved on the ProtonX Legal Correction Validation Dataset. The evaluation dataset will be released in an upcoming public release.
 
-2. Fixing and normalizing PaddleOCR output to ensure high-quality downstream correction
 
 
-<img src="https://protonx.co/assets/img/paddle-ocr-protonx.png">
 
 ---