metadata
license: apache-2.0
base_model: openai/whisper-tiny
tags:
- generated_from_keras_callback
model-index:
- name: whisper_new_split_ch_08__0010
results: []
whisper_new_split_ch_08__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: 3.5190
- Train Accuracy: 0.0142
- Train Wermet: 6.2910
- 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': 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 | Epoch |
|---|---|---|---|
| 7.0502 | 0.0020 | 5.6150 | 0 |
| 5.6527 | 0.0046 | 11.3162 | 1 |
| 4.8654 | 0.0085 | 4.8190 | 2 |
| 4.4295 | 0.0107 | 5.4574 | 3 |
| 4.1588 | 0.0111 | 6.9059 | 4 |
| 3.9861 | 0.0112 | 6.9104 | 5 |
| 3.8010 | 0.0121 | 6.8845 | 6 |
| 3.6776 | 0.0124 | 6.9533 | 7 |
| 3.5939 | 0.0135 | 6.6166 | 8 |
| 3.5190 | 0.0142 | 6.2910 | 9 |
Framework versions
- Transformers 4.31.0
- TensorFlow 2.13.0
- Tokenizers 0.13.3