whisper-tiny-ar-finetuned-continued-v3
This model is a fine-tuned version of openai/whisper-tiny on the common_voice_17_0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.4816
- Wer: 12.0477
- Cer: 11.0251
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: 16
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_steps: 50
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|---|---|---|---|---|---|
| 0.5042 | 1.0 | 883 | 0.5605 | 4.1054 | 3.6602 |
| 0.3701 | 2.0 | 1767 | 0.5074 | 6.1383 | 5.4713 |
| 0.2869 | 3.0 | 2649 | 0.4816 | 12.0477 | 11.0251 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.6.0+cu124
- Datasets 2.18.0
- Tokenizers 0.13.3