train_from_raw_cv12_true__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: 0.7822
• Train Accuracy: 0.0844
• Train Wermet: 2.7501
• Validation Loss: 0.6499
• Validation Accuracy: 0.0556
• Validation Wermet: 8.5538
• 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': 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
2.3396	0.0444	2.7124	1.8124	0.0331	9.4418	0
1.7496	0.0562	3.2708	1.6529	0.0359	9.7805	1
1.6254	0.0594	3.1714	1.5874	0.0371	10.4139	2
1.5490	0.0615	3.0208	1.5102	0.0382	8.2054	3
1.4910	0.0631	2.8298	1.4213	0.0402	8.9930	4
1.4233	0.0650	2.7100	1.3319	0.0421	8.8483	5
1.3203	0.0679	2.5125	1.1806	0.0450	7.0373	6
1.1453	0.0730	2.5001	1.0029	0.0484	5.7328	7
0.9537	0.0789	2.6295	0.7799	0.0529	6.7373	8
0.7822	0.0844	2.7501	0.6499	0.0556	8.5538	9

Framework versions

• Transformers 4.33.0.dev0
• TensorFlow 2.13.0
• Tokenizers 0.13.3