whisper-small-ar-tiny
This model is a fine-tuned version of openai/whisper-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.6540
- Wer: 49.3976
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: 2
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 4
- 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: 10
- training_steps: 100
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 1.7382 | 2.2222 | 20 | 1.9086 | 59.0361 |
| 1.4855 | 4.4444 | 40 | 1.6540 | 49.3976 |
| 1.2911 | 6.6667 | 60 | 1.4638 | 57.8313 |
| 1.1737 | 8.8889 | 80 | 1.3458 | 102.4096 |
| 1.0991 | 11.1111 | 100 | 1.3061 | 114.4578 |
Framework versions
- Transformers 4.50.3
- Pytorch 2.6.0+cu124
- Datasets 3.5.0
- Tokenizers 0.21.1
- Downloads last month
- 8
Model tree for RawandLaouini/whisper-small-ar-tiny
Base model
openai/whisper-small