library_name: transformers
language:
- ur
Model Card for Model ID
This is an Urdu OCR model designed for handwriting recognition tasks. It utilizes a VisionEncoderDecoderModel with a ViT-based encoder and a BERT-based decoder, fine-tuned on a custom dataset for robust and accurate text extraction from images.
Model Details
Model Description
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- Developed by: Fajar Pervaiz
- Model type: VisionEncoderDecoderModel
- Language(s) (NLP): Urdu (ur)
- Finetuned from model [optional]: facebook/deit-base-distilled-patch16-384, bert-base-multilingual-cased
Model Sources [optional]
- Repository: [More Information Needed]
- Paper [optional]: [More Information Needed]
- Demo [optional]: [More Information Needed]
Uses
Direct Use
This model can be directly used for Urdu handwriting recognition tasks, particularly for extracting text from scanned documents or handwritten notes.
Downstream Use [optional]
This model can be fine-tuned further for specific handwriting datasets or integrated into larger OCR systems for Urdu or multilingual text recognition.
Out-of-Scope Use
The model is not suitable for languages other than Urdu or domains with highly noisy or distorted images without further fine-tuning.
Bias, Risks, and Limitations
The model may exhibit biases inherent in the training data. Misrecognition of complex or ambiguous handwriting is possible. Users should carefully evaluate its performance in their specific use case.
Recommendations
Users should test the model thoroughly on their specific dataset and consider additional fine-tuning if required. Misuse in sensitive applications (e.g., legal or medical document OCR) should be avoided without rigorous evaluation.
How to Get Started with the Model
Use the code below to get started with the model.
from transformers import VisionEncoderDecoderModel, TrOCRProcessor processor = TrOCRProcessor.from_pretrained("path/to/processor") model = VisionEncoderDecoderModel.from_pretrained("path/to/model")
Training Details
Training Data
The training data comprises 46,742 image-text pairs from a custom dataset of Urdu handwritten texts.
Training Procedure
Images were resized to 384x384 pixels and normalized. Augmentations such as Elastic Transform and Gaussian Blur were applied to enhance robustness.
Preprocessing [optional]
Training Hyperparameters
- Training regime:
- Training regime: Mixed precision (fp16)
- Learning rate: 4e-5
- Batch size: 8
- Epochs: 12
- Optimizer: AdamW
- Scheduler: Linear decay
Speeds, Sizes, Times [optional]
Evaluation
Testing Data, Factors & Metrics
Testing Data
A subset of 4,675 image-text pairs was used for evaluation.
Factors
The model was tested on handwritten text images with varying font styles and complexities.
Metrics
Results
Summary
Model Examination [optional]
Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type: NVIDIA GPU
- Hours used: [More Information Needed]
- Cloud Provider: [More Information Needed]
- Compute Region: [More Information Needed]
- Carbon Emitted: [More Information Needed]
Technical Specifications [optional]
Model Architecture and Objective
The model uses a VisionEncoderDecoder architecture combining a ViT encoder and a BERT decoder.
Compute Infrastructure
Hardware
NVIDIA GPU (e.g., A100)
Software
Python, PyTorch, Hugging Face Transformers
Citation [optional]
BibTeX:
[More Information Needed]
APA:
Glossary [optional]
CER: Character Error Rate WER: Word Error Rate OCR: Optical Character Recognition
More Information [optional]
[More Information Needed]
Model Card Authors [optional]
Fajar Pervaiz