updated paper deatails

README.md

@@ -27,8 +27,12 @@ A Comprehensive Toolkit for Scene Text Recognition in Indian Languages
 
 
 [![Documentation](https://img.shields.io/badge/Documentation-Click%20Here-007BFF?style=for-the-badge&logo=ReadTheDocs&logoColor=white)](https://bhashini-iitj.github.io/IndicPhotoOCR/)
+
 </div>
 <hr style="width: 100%; border: 1px solid #000;">
 
 
-IndicPhotoOCR is a scene text recognition toolkit designed for detecting, identifying, and recognizing text across Indian languages, including Assamese, Bengali, Gujarati, Hindi, Kannada, Malayalam, Marathi, Odia, Punjabi, Tamil, Telugu, and English, with support for Urdu and Meitei in the pipeline. It is built to handle the unique scripts and complex structures of Indian languages, offering robust detection and recognition capabilities. The package can be installed with just few lines of code, and a straightforward wrapper function makes it easy to use.
+IndicPhotoOCR is a scene text recognition toolkit designed for detecting, identifying, and recognizing text across Indian languages, including Assamese, Bengali, Gujarati, Hindi, Kannada, Malayalam, Marathi, Odia, Punjabi, Tamil, Telugu, and English, with support for Urdu and Meitei in the pipeline. It is built to handle the unique scripts and complex structures of Indian languages, offering robust detection and recognition capabilities. The package can be installed with just few lines of code, and a straightforward wrapper function makes it easy to use.
+The details of the model/Space are described in the accompanying paper on arXiv:
+[Bharat Scene Text: A Novel Comprehensive Dataset and Benchmark for Indian Language Scene Text Understanding
+](https://arxiv.org/abs/2511.23071)