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: 2.0288
- Train Accuracy: 0.0397
- Train Wermet: 6.0799
- Validation Loss: 1.9309
- Validation Accuracy: 0.0265
- Validation Wermet: 13.6220
- 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 |
|---|---|---|---|---|---|---|
| 2.9538 | 0.0228 | 5.6932 | 2.4237 | 0.0203 | 14.2654 | 0 |
| 2.4052 | 0.0321 | 6.0897 | 2.1989 | 0.0229 | 15.5551 | 1 |
| 2.2222 | 0.0358 | 6.1102 | 2.0871 | 0.0245 | 13.4374 | 2 |
| 2.1102 | 0.0380 | 6.0428 | 1.9986 | 0.0253 | 13.7934 | 3 |
| 2.0288 | 0.0397 | 6.0799 | 1.9309 | 0.0265 | 13.6220 | 4 |
Framework versions
- Transformers 4.31.0
- TensorFlow 2.13.0
- Tokenizers 0.13.3