Update README.md

README.md

@@ -1,3 +1,8 @@
+---
+pipeline_tag: image-to-text
+github_repo: https://github.com/FactoDeepLearning/META-DAN
+arxiv: 2504.03349
+---
 **<span style="color: #A6351B;">Warning: this project is under a research/academic usage only license, preventing any usage for commercial purposes without permission.</span>**
 
 This repository contains official trained model weights from the paper:  
@@ -9,5 +14,4 @@ The source code is available [here](https://github.com/FactoDeepLearning/META-DA
 Weights are given for the following models: DAN (TPAMI 2023), Faster DAN (ICDAR 2023), MT-DAN (PR 2026), W-DAN (PR 2026) and Meta-DAN (PR 2026).  
 Pre-trained weights at line level are also provided. 
 
-Each models is either trained on a single dataset (BRESSAY, CASIA2, Eparchos, Esaposalles, IAM, MAURDOR, READ2016, RIMES, ScribbleLens) or on a set of latin languages (IAM+BRESSAY+READ2016+Espossales+ScribbleLens).
-
+Each models is either trained on a single dataset (BRESSAY, CASIA2, Eparchos, Esaposalles, IAM, MAURDOR, READ2016, RIMES, ScribbleLens) or on a set of latin languages (IAM+BRESSAY+READ2016+Espossales+ScribbleLens).