whisper_havest_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: 5.1222
• Train Accuracy: 0.0117
• Train Do Wer: 1.0
• Validation Loss: 5.1600
• Validation Accuracy: 0.0117
• Validation Do Wer: 1.0
• 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 Do Wer	Validation Loss	Validation Accuracy	Validation Do Wer	Epoch
9.9191	0.0046	1.0	8.5836	0.0067	1.0	0
8.0709	0.0083	1.0	7.4667	0.0089	1.0	1
7.1652	0.0100	1.0	6.8204	0.0112	1.0	2
6.7196	0.0114	1.0	6.5192	0.0114	1.0	3
6.4115	0.0115	1.0	6.2357	0.0115	1.0	4
6.1085	0.0115	1.0	5.9657	0.0115	1.0	5
5.8206	0.0115	1.0	5.7162	0.0115	1.0	6
5.5567	0.0115	1.0	5.4963	0.0115	1.0	7
5.3223	0.0116	1.0	5.3096	0.0116	1.0	8
5.1222	0.0117	1.0	5.1600	0.0117	1.0	9

Framework versions

• Transformers 4.25.0.dev0
• TensorFlow 2.9.2
• Datasets 2.6.1
• Tokenizers 0.13.2