---
tags:
- generated_from_trainer
- trocr
language: ar
model-index:
- name: ArOCR
  results:
  - task:
      name: Optical Charater Recogntion 
      type: image-to-text
    metrics:
    - name: Test CER
      type: cer
      value: 4.46
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# ArOCR

This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0620
- Cer: 0.0446

## 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: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step  | Validation Loss | Cer    |
|:-------------:|:-----:|:-----:|:---------------:|:------:|
| 3.6633        | 0.3   | 1000  | 3.3381          | 1.0385 |
| 2.3915        | 0.59  | 2000  | 2.3581          | 0.6389 |
| 1.5061        | 0.89  | 3000  | 1.4635          | 0.4779 |
| 0.8043        | 1.18  | 4000  | 0.8260          | 0.3427 |
| 0.46          | 1.48  | 5000  | 0.5074          | 0.2242 |
| 0.3393        | 1.77  | 6000  | 0.2699          | 0.1219 |
| 0.1077        | 2.07  | 7000  | 0.1794          | 0.0933 |
| 0.063         | 2.37  | 8000  | 0.1343          | 0.0617 |
| 0.0356        | 2.66  | 9000  | 0.0790          | 0.0692 |
| 0.0292        | 2.96  | 10000 | 0.0620          | 0.0446 |


### Framework versions

- Transformers 4.18.0
- Pytorch 1.9.1
- Datasets 2.1.0
- Tokenizers 0.11.6