Hugging Face's logo

mohammadalihumayun
/
trocr-ur

Image-Text-to-Text
Transformers
Safetensors
Urdu
vision-encoder-decoder
Generated from Trainer
Inference Endpoints
Model card Files Community
trocr-ur / README.md
mohammadalihumayun's picture
mohammadalihumayun
End of training
36d3027 verified
preview code
|
raw
history blame
1.51 kB
metadata
library_name: transformers
language:
  - ur
base_model: cxfajar197/urdu-ocr
tags:
  - generated_from_trainer
model-index:
  - name: trocr for Urdu
    results: []

trocr for Urdu

This model is a fine-tuned version of cxfajar197/urdu-ocr on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 1.8947
  • Cer: 0.2676

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 5e-05
  • train_batch_size: 16
  • eval_batch_size: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 1
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Cer
0.762 0.3188 1000 2.0288 0.2936
0.6622 0.6376 2000 2.0111 0.2791
0.5878 0.9563 3000 1.8947 0.2676

Framework versions

  • Transformers 4.45.1
  • Pytorch 2.4.0
  • Datasets 3.0.1
  • Tokenizers 0.20.0