<!-- This model card has been generated automatically according to the information Keras had access to. You should probably proofread and complete it, then remove this comment. -->
wh_4_sun_syl_w_0_lr_8en5_b32_0010
This model is a fine-tuned version of openai/whisper-tiny on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 4.0719
- Train Accuracy: 0.0133
- Train Wermet: 0.7479
- Train Wermet Syl: 0.7112
- Validation Loss: 2.9385
- Validation Accuracy: 0.0135
- Validation Wermet: 0.7636
- Validation Wermet Syl: 0.7193
- Epoch: 9
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:
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 8e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0}
- training_precision: float32
Training results
| Train Loss | Train Accuracy | Train Wermet | Train Wermet Syl | Validation Loss | Validation Accuracy | Validation Wermet | Validation Wermet Syl | Epoch |
|---|---|---|---|---|---|---|---|---|
| 5.2081 | 0.0105 | 1.5151 | 1.1936 | 4.0143 | 0.0113 | 0.9817 | 0.9765 | 0 |
| 4.7532 | 0.0116 | 0.8756 | 0.8371 | 3.9494 | 0.0114 | 0.9457 | 0.9171 | 1 |
| 4.7031 | 0.0117 | 0.8615 | 0.8175 | 3.9244 | 0.0114 | 0.9383 | 0.8993 | 2 |
| 4.6799 | 0.0117 | 0.8569 | 0.8117 | 3.9091 | 0.0114 | 0.9659 | 0.9487 | 3 |
| 4.6415 | 0.0117 | 0.8450 | 0.7985 | 3.8828 | 0.0115 | 0.9227 | 0.8867 | 4 |
| 4.6194 | 0.0118 | 0.8366 | 0.7901 | 3.8588 | 0.0115 | 0.9314 | 0.8973 | 5 |
| 4.5993 | 0.0118 | 0.8253 | 0.7803 | 3.9068 | 0.0116 | 0.9000 | 0.8526 | 6 |
| 4.5584 | 0.0120 | 0.7864 | 0.7455 | 3.7567 | 0.0118 | 0.8407 | 0.7907 | 7 |
| 4.4423 | 0.0123 | 0.7655 | 0.7209 | 3.5099 | 0.0123 | 0.8256 | 0.7786 | 8 |
| 4.0719 | 0.0133 | 0.7479 | 0.7112 | 2.9385 | 0.0135 | 0.7636 | 0.7193 | 9 |
Framework versions
- Transformers 4.34.0.dev0
- TensorFlow 2.13.0
- Tokenizers 0.13.3
