whisper_4_with_init_sun__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: 4.6273
• Train Accuracy: 0.0118
• Train Wermet: 0.8243
• Validation Loss: 3.8721
• Validation Accuracy: 0.0115
• Validation Wermet: 0.9414
• 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
5.3333	0.0111	1.3132	3.9675	0.0114	0.9339	0
4.7131	0.0116	0.8607	3.9360	0.0114	0.9503	1
4.6717	0.0117	0.8449	3.9196	0.0113	0.9768	2
4.6474	0.0117	0.8338	3.9039	0.0114	0.9557	3
4.6273	0.0118	0.8243	3.8721	0.0115	0.9414	4

Framework versions

• Transformers 4.34.0.dev0
• TensorFlow 2.13.0
• Tokenizers 0.13.3