---
library_name: transformers
language:
- ar
license: apache-2.0
base_model: openai/whisper-tiny
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: Whisper tiny AR - BH
  results: []
---

<!-- 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. -->

# Whisper tiny AR - BH

This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co./openai/whisper-tiny) on the quran-ayat-speech-to-text dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0064
- Wer: 0.0813
- Cer: 0.0322

## 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
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Use 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: 500
- num_epochs: 15
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer    | Cer    |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
| 0.0056        | 1.0   | 469  | 0.0061          | 0.0813 | 0.0325 |
| 0.0054        | 2.0   | 938  | 0.0057          | 0.0748 | 0.0289 |
| 0.0038        | 3.0   | 1407 | 0.0058          | 0.0720 | 0.0274 |
| 0.0018        | 4.0   | 1876 | 0.0061          | 0.0735 | 0.0285 |
| 0.0034        | 5.0   | 2345 | 0.0064          | 0.0737 | 0.0283 |
| 0.0011        | 6.0   | 2814 | 0.0069          | 0.1537 | 0.0660 |
| 0.0006        | 7.0   | 3283 | 0.0071          | 0.1546 | 0.0663 |
| 0.0007        | 8.0   | 3752 | 0.0076          | 0.1535 | 0.0654 |
| 0.0006        | 9.0   | 4221 | 0.0078          | 0.0764 | 0.0301 |
| 0.0002        | 10.0  | 4690 | 0.0081          | 0.0757 | 0.0287 |
| 0.0003        | 11.0  | 5159 | 0.0084          | 0.0786 | 0.0313 |
| 0.0003        | 12.0  | 5628 | 0.0085          | 0.0737 | 0.0287 |
| 0.0003        | 13.0  | 6097 | 0.0087          | 0.0755 | 0.0297 |
| 0.0001        | 14.0  | 6566 | 0.0104          | 0.0799 | 0.0323 |
| 0.0001        | 15.0  | 7035 | 0.0088          | 0.0738 | 0.0293 |


### Framework versions

- Transformers 4.47.0
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0