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
Upload processor
e1a334a verified
preview code
|
raw
history blame
1.29 kB
metadata
base_model: cxfajar197/urdu-ocr
language:
  - ur
library_name: transformers
tags:
  - generated_from_trainer
model-index:
  - name: trocr
    results: []

trocr

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

  • eval_loss: 1.8610
  • eval_cer: 0.2585
  • eval_runtime: 30.7583
  • eval_samples_per_second: 3.251
  • eval_steps_per_second: 0.228
  • epoch: 1.9127
  • step: 6000

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: 2
  • mixed_precision_training: Native AMP

Framework versions

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