metadata
license: apache-2.0
base_model: openai/whisper-tiny
tags:
- generated_from_keras_callback
model-index:
- name: whisper_new_split_ch_08__0005
results: []
whisper_new_split_ch_08__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: 1.8240
- Train Accuracy: 0.0439
- Train Wermet: 4.6041
- Validation Loss: 1.6213
- Validation Accuracy: 0.0308
- Validation Wermet: 12.0288
- 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': 1e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
- training_precision: float32
Training results
| Train Loss | Train Accuracy | Train Wermet | Validation Loss | Validation Accuracy | Validation Wermet | Epoch |
|---|---|---|---|---|---|---|
| 2.9164 | 0.0249 | 6.7624 | 2.3005 | 0.0222 | 17.3950 | 0 |
| 2.2801 | 0.0354 | 6.3518 | 2.0871 | 0.0247 | 13.2620 | 1 |
| 2.0950 | 0.0388 | 5.1467 | 1.9468 | 0.0263 | 12.7130 | 2 |
| 1.9681 | 0.0411 | 4.7586 | 1.8190 | 0.0281 | 13.0904 | 3 |
| 1.8240 | 0.0439 | 4.6041 | 1.6213 | 0.0308 | 12.0288 | 4 |
Framework versions
- Transformers 4.31.0
- TensorFlow 2.13.0
- Tokenizers 0.13.3