Qalam : A Multimodal LLM for Arabic Optical Character and Handwriting Recognition
gagan3012
Abstract
Arabic Optical Character Recognition (OCR) and Handwriting Recognition (HWR) pose unique challenges due to the cursive and context-sensitive nature of the Arabic script. This study introduces Qalam, a novel foundation model designed for Arabic OCR and HWR, built on a SwinV2 encoder and RoBERTa decoder architecture. Our model significantly outperforms existing methods, achieving a Word Error Rate (WER) of just 0.80% in HWR tasks and 1.18% in OCR tasks. We train Qalam on a diverse dataset, including over 4.5 million images from Arabic manuscripts and a synthetic dataset comprising 60k image-text pairs. Notably, Qalam demonstrates exceptional handling of Arabic diacritics, a critical feature in Arabic scripts. Furthermore, it shows a remarkable ability to process high-resolution inputs, addressing a common limitation in current OCR systems. These advancements underscore Qalam's potential as a leading solution for Arabic script recognition, offering a significant leap in accuracy and efficiency.
Community
Arabic Optical Character Recognition (OCR) and Handwriting Recognition (HWR) pose unique challenges due to the cursive and context-sensitive nature of the Arabic script. This study introduces Qalam, a novel foundation model for Arabic OCR and HWR, built on a SwinV2 encoder and RoBERTa decoder architecture. Our model significantly outperforms existing methods, achieving a Word Error Rate (WER) of just 0.80% in HWR tasks and 1.18% in OCR tasks. We train Qalam on a diverse dataset, including over 4.5 million images from Arabic manuscripts and a synthetic dataset comprising 60k image-text pairs. Notably, Qalam demonstrates exceptional handling of Arabic diacritics, a critical feature in Arabic scripts. Furthermore, it shows a remarkable ability to process high-resolution inputs, addressing a common limitation in current OCR systems. These advancements underscore Qalam's potential as a leading solution for Arabic script recognition, offering a significant leap in accuracy and efficiency.
Model and demo will be released soon
Impressive work🔥 Can't wait to see the model and demo on the hub!!
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- DANIEL: A fast Document Attention Network for Information Extraction and Labelling of handwritten documents (2024)
- CATT: Character-based Arabic Tashkeel Transformer (2024)
- Classification of Non-native Handwritten Characters Using Convolutional Neural Network (2024)
- Arabic Handwritten Text for Person Biometric Identification: A Deep Learning Approach (2024)
- Muharaf: Manuscripts of Handwritten Arabic Dataset for Cursive Text Recognition (2024)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
Would like to test it out and compare it to eScriptorium.
For Arabic users check out my idea on Telegram
مجموعة الرقمنة العربية
nice impressive work, when will the model be published?
There is another model that we are working on it, it just be out soon
Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper