<!-- 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_0020
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: 0.5573
- Train Accuracy: 0.0301
- Train Wermet: 0.1858
- Train Wermet Syl: 0.3290
- Validation Loss: 1.1996
- Validation Accuracy: 0.0206
- Validation Wermet: 0.3176
- Validation Wermet Syl: 0.3171
- Epoch: 19
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 |
| 4.6333 | 0.0117 | 0.9864 | 1.1325 | 3.9306 | 0.0115 | 0.9255 | 0.9484 | 5 |
| 4.6176 | 0.0117 | 0.9803 | 1.1203 | 3.9175 | 0.0115 | 0.9420 | 0.9530 | 6 |
| 4.5944 | 0.0118 | 1.0060 | 1.1999 | 3.8546 | 0.0115 | 0.9307 | 0.9259 | 7 |
| 4.5516 | 0.0119 | 0.9620 | 1.1243 | 3.7716 | 0.0117 | 0.8963 | 0.9090 | 8 |
| 4.3967 | 0.0123 | 0.9533 | 1.1468 | 3.3131 | 0.0126 | 0.8398 | 0.8514 | 9 |
| 3.6948 | 0.0142 | 1.0093 | 1.2963 | 2.5045 | 0.0143 | 0.7208 | 0.7981 | 10 |
| 2.7175 | 0.0174 | 1.0107 | 1.4791 | 1.6944 | 0.0173 | 0.5291 | 0.5397 | 11 |
| 1.9685 | 0.0207 | 0.8511 | 1.3318 | 1.3460 | 0.0189 | 0.4535 | 0.4901 | 12 |
| 1.5230 | 0.0231 | 0.6365 | 1.0150 | 1.4574 | 0.0184 | 0.4208 | 0.4469 | 13 |
| 1.1565 | 0.0254 | 0.4528 | 0.7311 | 1.1631 | 0.0200 | 0.3639 | 0.3688 | 14 |
| 0.9615 | 0.0268 | 0.3751 | 0.6218 | 1.1632 | 0.0201 | 0.3579 | 0.3572 | 15 |
| 0.8007 | 0.0281 | 0.3001 | 0.5086 | 1.1379 | 0.0205 | 0.3373 | 0.3423 | 16 |
| 0.6860 | 0.0291 | 0.2588 | 0.4497 | 1.1096 | 0.0206 | 0.3192 | 0.3128 | 17 |
| 0.5421 | 0.0304 | 0.2152 | 0.3919 | 1.0932 | 0.0209 | 0.3167 | 0.3123 | 18 |
| 0.5573 | 0.0301 | 0.1858 | 0.3290 | 1.1996 | 0.0206 | 0.3176 | 0.3171 | 19 |
Framework versions
- Transformers 4.34.0.dev0
- TensorFlow 2.13.0
- Tokenizers 0.13.3
