---
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: 0.0152
- Wer: 0.0967
- Cer: 0.0379

## 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    |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
| 0.0017        | 1.0   | 469  | 0.0106          | 0.0956 | 0.0363 |
| 0.0011        | 2.0   | 938  | 0.0111          | 0.0970 | 0.0371 |
| 0.0008        | 3.0   | 1407 | 0.0115          | 0.0976 | 0.0372 |
| 0.001         | 4.0   | 1876 | 0.0123          | 0.0974 | 0.0372 |
| 0.0004        | 5.0   | 2345 | 0.0128          | 0.0963 | 0.0367 |
| 0.0001        | 6.0   | 2814 | 0.0130          | 0.0939 | 0.0360 |
| 0.0004        | 7.0   | 3283 | 0.0135          | 0.0932 | 0.0348 |
| 0.0001        | 8.0   | 3752 | 0.0138          | 0.0929 | 0.0353 |
| 0.0           | 9.0   | 4221 | 0.0142          | 0.0914 | 0.0347 |
| 0.0           | 10.0  | 4690 | 0.0146          | 0.0919 | 0.0345 |
| 0.0           | 11.0  | 5159 | 0.0149          | 0.0929 | 0.0345 |
| 0.0           | 12.0  | 5628 | 0.0151          | 0.0936 | 0.0345 |
| 0.0           | 13.0  | 6097 | 0.0154          | 0.0929 | 0.0344 |
| 0.0           | 14.0  | 6566 | 0.0165          | 0.0946 | 0.0366 |
| 0.0           | 15.0  | 7035 | 0.0156          | 0.0934 | 0.0346 |


### Framework versions

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