metadata
license: apache-2.0
base_model: openai/whisper-tiny
tags:
- generated_from_keras_callback
model-index:
- name: whisper_charsplit_new_round2__0004
results: []
whisper_charsplit_new_round2__0004
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: 0.0019
- Train Accuracy: 0.0795
- Train Wermet: 8.9450
- Validation Loss: 0.5623
- Validation Accuracy: 0.0766
- Validation Wermet: 7.7117
- Epoch: 3
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 |
|---|---|---|---|---|---|---|
| 0.0010 | 0.0795 | 8.7507 | 0.5575 | 0.0767 | 7.6778 | 0 |
| 0.0013 | 0.0795 | 8.9468 | 0.5652 | 0.0766 | 8.3360 | 1 |
| 0.0025 | 0.0795 | 8.7338 | 0.5673 | 0.0765 | 8.3770 | 2 |
| 0.0019 | 0.0795 | 8.9450 | 0.5623 | 0.0766 | 7.7117 | 3 |
Framework versions
- Transformers 4.32.0.dev0
- TensorFlow 2.12.0
- Tokenizers 0.13.3