---
library_name: transformers
language:
- ar
license: apache-2.0
base_model: openai/whisper-small
tags:
- Whisper
- Quran
- Speech Recognition
- 'dataset: abdulhamedeid/quran-verses-audio-clips'
- generated_from_trainer
metrics:
- wer
model-index:
- name: Whisper Small For Quran
  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 Small For Quran

This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0425
- Wer: 11.9814

## 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: 1e-05
- train_batch_size: 35
- eval_batch_size: 8
- seed: 42
- 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
- training_steps: 4000
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Wer     |
|:-------------:|:------:|:----:|:---------------:|:-------:|
| 0.1319        | 0.5845 | 1000 | 0.1063          | 17.3778 |
| 0.0507        | 1.1689 | 2000 | 0.0701          | 14.1397 |
| 0.0406        | 1.7534 | 3000 | 0.0499          | 12.7187 |
| 0.0352        | 2.3378 | 4000 | 0.0425          | 11.9814 |


### Framework versions

- Transformers 4.48.0
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0