---
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: 0.0190
- Wer: 0.1120
- Cer: 0.0412

## 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: 0.0001
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- 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: 20
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch   | Step | Validation Loss | Wer    | Cer    |
|:-------------:|:-------:|:----:|:---------------:|:------:|:------:|
| 0.0           | 1.0     | 157  | 0.0180          | 0.1046 | 0.0447 |
| 0.0004        | 2.0     | 314  | 0.0212          | 0.1330 | 0.0435 |
| 0.0012        | 3.0     | 471  | 0.0225          | 0.1584 | 0.0497 |
| 0.0017        | 4.0     | 628  | 0.0199          | 0.1611 | 0.0527 |
| 0.0017        | 5.0     | 785  | 0.0210          | 0.1488 | 0.0509 |
| 0.0013        | 6.0     | 942  | 0.0202          | 0.1417 | 0.0458 |
| 0.001         | 7.0     | 1099 | 0.0200          | 0.1520 | 0.0507 |
| 0.001         | 8.0     | 1256 | 0.0199          | 0.1405 | 0.0445 |
| 0.0006        | 9.0     | 1413 | 0.0193          | 0.1491 | 0.0493 |
| 0.0005        | 10.0    | 1570 | 0.0189          | 0.1271 | 0.0411 |
| 0.0004        | 11.0    | 1727 | 0.0197          | 0.1354 | 0.0454 |
| 0.0003        | 12.0    | 1884 | 0.0198          | 0.1289 | 0.0421 |
| 0.0002        | 13.0    | 2041 | 0.0192          | 0.1298 | 0.0439 |
| 0.0001        | 14.0    | 2198 | 0.0197          | 0.1238 | 0.0407 |
| 0.0001        | 15.0    | 2355 | 0.0198          | 0.1189 | 0.0412 |
| 0.0           | 16.0    | 2512 | 0.0191          | 0.1146 | 0.0398 |
| 0.0           | 17.0    | 2669 | 0.0194          | 0.1140 | 0.0395 |
| 0.0           | 18.0    | 2826 | 0.0199          | 0.1073 | 0.0359 |
| 0.0           | 19.0    | 2983 | 0.0215          | 0.1089 | 0.0403 |
| 0.0           | 19.8768 | 3120 | 0.0210          | 0.1084 | 0.0363 |


### Framework versions

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