train_from_raw_cv12__0020

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: nan
• Train Accuracy: 0.0032
• Train Wermet: 8.3902
• Validation Loss: nan
• Validation Accuracy: 0.0032
• Validation Wermet: 8.3902
• Epoch: 19

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': 2e-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
nan	0.0032	8.3778	nan	0.0032	8.3902	0
nan	0.0032	8.3902	nan	0.0032	8.3902	1
nan	0.0032	8.3902	nan	0.0032	8.3902	2
nan	0.0032	8.3902	nan	0.0032	8.3902	3
nan	0.0032	8.3902	nan	0.0032	8.3902	4
nan	0.0032	8.3902	nan	0.0032	8.3902	5
nan	0.0032	8.3902	nan	0.0032	8.3902	6
nan	0.0032	8.3902	nan	0.0032	8.3902	7
nan	0.0032	8.3902	nan	0.0032	8.3902	8
nan	0.0032	8.3902	nan	0.0032	8.3902	9
nan	0.0032	8.3902	nan	0.0032	8.3902	10
nan	0.0032	8.3902	nan	0.0032	8.3902	11
nan	0.0032	8.3902	nan	0.0032	8.3902	12
nan	0.0032	8.3902	nan	0.0032	8.3902	13
nan	0.0032	8.3902	nan	0.0032	8.3902	14
nan	0.0032	8.3902	nan	0.0032	8.3902	15
nan	0.0032	8.3902	nan	0.0032	8.3902	16
nan	0.0032	8.3902	nan	0.0032	8.3902	17
nan	0.0032	8.3902	nan	0.0032	8.3902	18
nan	0.0032	8.3902	nan	0.0032	8.3902	19

Framework versions

• Transformers 4.33.0.dev0
• TensorFlow 2.13.0
• Tokenizers 0.13.3