metadata
library_name: transformers
language:
- ar
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
datasets:
- DrAliGomaa/ar-eg-dataset
model-index:
- name: whisper-small-ar-draligomaa-dataset
results: []
whisper-small-ar-draligomaa-dataset
This model is a fine-tuned version of openai/whisper-small on the draligomaa-dataset dataset. It achieves the following results on the evaluation set:
- Loss: 0.2685
- Wer Ortho: 18.4164
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: 32
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_steps: 50
- training_steps: 500
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho |
|---|---|---|---|---|
| 0.4073 | 0.3195 | 100 | 0.3614 | 25.9486 |
| 0.3108 | 0.6390 | 200 | 0.3088 | 23.1579 |
| 0.2658 | 0.9585 | 300 | 0.2840 | 19.9915 |
| 0.1807 | 1.2780 | 400 | 0.2759 | 19.6826 |
| 0.1591 | 1.5974 | 500 | 0.2685 | 18.4164 |
Framework versions
- Transformers 4.45.1
- Pytorch 2.4.0
- Datasets 3.0.1
- Tokenizers 0.20.0