---
library_name: transformers
language:
- ar
license: apache-2.0
base_model: openai/whisper-large
tags:
- generated_from_trainer
datasets:
- Mohsen21/WHISPERLARGEUAE
metrics:
- wer
model-index:
- name: Whisper Large fine tuned
  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 Large fine tuned

This model is a fine-tuned version of [openai/whisper-large](https://huggingface.co/openai/whisper-large) on the 1620 RAW dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1902
- Wer: 12.3332

## 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: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.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: 750
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Wer     |
|:-------------:|:------:|:----:|:---------------:|:-------:|
| 0.0375        | 2.4691 | 200  | 0.1497          | 13.3916 |
| 0.0174        | 4.9383 | 400  | 0.1739          | 12.7934 |
| 0.0114        | 7.4074 | 600  | 0.1902          | 12.3332 |


### Framework versions

- Transformers 4.48.1
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0