whisper-small-ar
This model is a fine-tuned version of openai/whisper-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3220
- Wer: 37.1239
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: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- training_steps: 400
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 1.2845 | 0.2513 | 100 | 1.2540 | 88.7267 |
| 0.9098 | 0.5025 | 200 | 0.8130 | 76.2804 |
| 0.4903 | 0.7538 | 300 | 0.5251 | 55.3367 |
| 0.3246 | 1.0050 | 400 | 0.3220 | 37.1239 |
Framework versions
- Transformers 4.44.1
- Pytorch 2.4.0+cu124
- Datasets 2.21.0
- Tokenizers 0.19.1