<!-- 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_2en4_b32_0005
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: 4.6540
- Train Accuracy: 0.0117
- Train Wermet: 0.9103
- Train Wermet Syl: 0.9487
- Validation Loss: 3.9216
- Validation Accuracy: 0.0115
- Validation Wermet: 0.9358
- Validation Wermet Syl: 0.9594
- Epoch: 4
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': 0.0002, '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 |
|---|---|---|---|---|---|---|---|---|
| 5.2282 | 0.0106 | 3.5001 | 2.7069 | 4.0241 | 0.0114 | 0.9693 | 0.9528 | 0 |
| 4.7449 | 0.0116 | 0.8928 | 0.8621 | 3.9408 | 0.0114 | 0.9623 | 0.9431 | 1 |
| 4.7110 | 0.0116 | 0.9319 | 0.9494 | 4.0066 | 0.0114 | 0.9466 | 0.9714 | 2 |
| 4.6727 | 0.0117 | 0.9059 | 0.9227 | 3.9101 | 0.0114 | 0.9428 | 0.9156 | 3 |
| 4.6540 | 0.0117 | 0.9103 | 0.9487 | 3.9216 | 0.0115 | 0.9358 | 0.9594 | 4 |
Framework versions
- Transformers 4.34.0.dev0
- TensorFlow 2.13.0
- Tokenizers 0.13.3
