---
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: 0.0148
- Wer: 0.0829
- Cer: 0.0324

## 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    |
|:-------------:|:-------:|:----:|:---------------:|:------:|:------:|
| 0.0107        | 1.0     | 157  | 0.0086          | 0.0889 | 0.0338 |
| 0.0069        | 2.0     | 314  | 0.0084          | 0.0896 | 0.0353 |
| 0.0042        | 3.0     | 471  | 0.0102          | 0.1070 | 0.0380 |
| 0.004         | 4.0     | 628  | 0.0111          | 0.1135 | 0.0406 |
| 0.0029        | 5.0     | 785  | 0.0118          | 0.1086 | 0.0401 |
| 0.0023        | 6.0     | 942  | 0.0128          | 0.1082 | 0.0388 |
| 0.0017        | 7.0     | 1099 | 0.0125          | 0.1033 | 0.0375 |
| 0.0013        | 8.0     | 1256 | 0.0133          | 0.1073 | 0.0383 |
| 0.0009        | 9.0     | 1413 | 0.0133          | 0.1084 | 0.0376 |
| 0.0007        | 10.0    | 1570 | 0.0134          | 0.1024 | 0.0375 |
| 0.0005        | 11.0    | 1727 | 0.0142          | 0.1024 | 0.0358 |
| 0.0004        | 12.0    | 1884 | 0.0132          | 0.0988 | 0.0331 |
| 0.0003        | 13.0    | 2041 | 0.0137          | 0.0952 | 0.0337 |
| 0.0001        | 14.0    | 2198 | 0.0144          | 0.0972 | 0.0350 |
| 0.0001        | 15.0    | 2355 | 0.0135          | 0.0927 | 0.0338 |
| 0.0           | 16.0    | 2512 | 0.0136          | 0.0934 | 0.0339 |
| 0.0           | 17.0    | 2669 | 0.0134          | 0.0871 | 0.0313 |
| 0.0           | 18.0    | 2826 | 0.0134          | 0.0833 | 0.0307 |
| 0.0           | 19.0    | 2983 | 0.0145          | 0.0841 | 0.0358 |
| 0.0           | 19.8768 | 3120 | 0.0139          | 0.0782 | 0.0296 |


### Framework versions

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