metadata
library_name: transformers
language:
- ar
license: mit
base_model: openai/whisper-large-v3-turbo
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: turboardj0.2
results: []
turboardj0.2
This model is a fine-tuned version of openai/whisper-large-v3-turbo on the test dataset. It achieves the following results on the evaluation set:
- Loss: 0.1442
- Wer: 8.7712
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: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 5000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.2254 | 0.8873 | 1000 | 0.1703 | 12.7173 |
| 0.114 | 1.7746 | 2000 | 0.1476 | 10.4795 |
| 0.0556 | 2.6619 | 3000 | 0.1418 | 9.0360 |
| 0.0253 | 3.5492 | 4000 | 0.1485 | 8.4765 |
| 0.0117 | 4.4366 | 5000 | 0.1442 | 8.7712 |
Framework versions
- Transformers 4.45.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.20.1