---
library_name: transformers
license: mit
base_model: TutlaytAI/TrOCR-arb
tags:
- generated_from_trainer
model-index:
- name: TrOCR-arb-hausaFull
  results: []
language:
- ha
pipeline_tag: image-text-to-text
datasets:
- TutlaytAI/Hausa_Ajami_OCR
---

<!-- 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. -->

# TrOCR-arb-hausaFull

This model is a fine-tuned version of [microsoft/trocr-base-handwritten](https://huggingface.co/microsoft/trocr-base-handwritten) on an unknown dataset.
It achieves the following results on the evaluation set:

- Cer: 0.6361

## 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-06
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 60
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch   | Step | Validation Loss | Cer    |
|:-------------:|:-------:|:----:|:---------------:|:------:|
| No log        | 6.4103  | 500  | 4.1384          | 0.9864 |
| No log        | 12.8205 | 1000 | 3.7169          | 0.9803 |
| No log        | 19.2308 | 1500 | 3.7846          | 0.9770 |
| No log        | 25.6410 | 2000 | 3.8778          | 0.9758 |


### Framework versions

- Transformers 4.53.2
- Pytorch 2.7.1+cu126
- Datasets 4.0.0
- Tokenizers 0.21.2