trocr-base-printed_license_plates_ocr

This model is a fine-tuned version of microsoft/trocr-base-printed.

It achieves the following results on the evaluation set:

• Loss: 0.1581
• CER: 0.0368

Model description

This model extracts text from image input (License Plates).

For more information on how it was created, check out the following link: https://github.com/DunnBC22/Vision_Audio_and_Multimodal_Projects/blob/main/Optical%20Character%20Recognition%20(OCR)/OCR%20License%20Plates/OCR_license_plate_text_recognition.ipynb

Intended uses & limitations

This model is intended to demonstrate my ability to solve a complex problem using technology. You are welcome to test and experiment with this model, but it is at your own risk/peril.

Training and evaluation data

Dataset Source: https://www.kaggle.com/datasets/nickyazdani/license-plate-text-recognition-dataset

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 5e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss	CER
0.3144	1.0	2000	0.2463	0.0473
0.143	2.0	4000	0.1581	0.0368

Framework versions

• Transformers 4.21.3
• Pytorch 1.12.1
• Datasets 2.4.0
• Tokenizers 0.12.1