whisper-base-hawrami
This model is a fine-tuned version of openai/whisper-base on the razhan/DOLMA-speech hawrami dataset. It achieves the following results on the evaluation set:
- Loss: 3.0851
- Chrf: 13.3279
- Bleu: 0.4036
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: 256
- eval_batch_size: 128
- seed: 42
- optimizer: Use 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: 100
- num_epochs: 4.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Chrf | Bleu |
|---|---|---|---|---|---|
| 4.056 | 1.0 | 40 | 3.7037 | 12.1151 | 0.0829 |
| 3.4175 | 2.0 | 80 | 3.2226 | 11.2675 | 0.1153 |
| 3.1704 | 3.0 | 120 | 3.1141 | 12.9709 | 0.2803 |
| 3.0286 | 4.0 | 160 | 3.0851 | 13.3279 | 0.4036 |
Framework versions
- Transformers 4.49.0.dev0
- Pytorch 2.6.0+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0