Bangla OCR using TrOCR
A transformer-based Optical Character Recognition (OCR) model for printed Bangla text using Microsoft's TrOCR architecture.
Features
- Printed Bangla OCR
- Transformer-based architecture
- Fine-tuned TrOCR model
- Supports Unicode Bangla output
Model
- Base Model: microsoft/trocr-base-printed
- Framework: PyTorch
- Library: Hugging Face Transformers
Example
Input:
Image containing printed Bangla text
Output:
বাংলা লেখা
Author
Md. Sakib Rahman
University of Asia Pacific
license: mit
bangla-ocr-model/
│
├── config.json
├── generation_config.json
├── model.safetensors
├── preprocessor_config.json
├── tokenizer.json
├── tokenizer_config.json
├── special_tokens_map.json
└── README.md (এটি তুমি লিখবে)
