train_from_raw_cv12_true__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: 0.1551
• Train Accuracy: 0.1061
• Train Wermet: 3.5489
• Validation Loss: 0.2849
• Validation Accuracy: 0.0638
• Validation Wermet: 9.6569
• 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
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
0.6317	0.0895	2.9507	0.5467	0.0578	8.4990	10
0.5010	0.0940	3.1604	0.4597	0.0597	9.4002	11
0.4026	0.0975	3.2910	0.3984	0.0610	9.8173	12
0.3372	0.0998	3.5302	0.3571	0.0619	9.6433	13
0.2922	0.1013	3.5614	0.3391	0.0623	9.6152	14
0.2572	0.1025	3.5685	0.3157	0.0628	9.4497	15
0.2258	0.1036	3.5179	0.3104	0.0630	9.7735	16
0.1995	0.1045	3.5362	0.2944	0.0634	9.8154	17
0.1762	0.1054	3.5227	0.2820	0.0637	9.8672	18
0.1551	0.1061	3.5489	0.2849	0.0638	9.6569	19

Framework versions

• Transformers 4.33.0.dev0
• TensorFlow 2.13.0
• Tokenizers 0.13.3