trocr-base-handwritten-OCR-handwriting_recognition_v2

This model is a fine-tuned version of microsoft/trocr-base-handwritten. It achieves the following results on the evaluation set:

  • Loss: 0.2470
  • CER: 0.0360

Model description

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)/Handwriting%20Recognition/Handwriting%20Recognition_v2/Mini%20Handwriting%20OCR%20Project.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/ssarkar445/handwriting-recognitionocr

Character Length for Training Dataset:

Input Character Length for Training Dataset

Character Length for Evaluation Dataset:

Input Character Length for Evaluation 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: 3

Training results

Training Loss Epoch Step Validation Loss Cer
0.4292 1.0 2500 0.4332 0.0679
0.2521 2.0 5000 0.2767 0.0483
0.1049 3.0 7500 0.2470 0.0360

Framework versions

  • Transformers 4.26.0
  • Pytorch 1.12.1
  • Datasets 2.8.0
  • Tokenizers 0.12.1
Downloads last month
259
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Spaces using DunnBC22/trocr-base-handwritten-OCR-handwriting_recognition_v2 3

Collection including DunnBC22/trocr-base-handwritten-OCR-handwriting_recognition_v2