whisper_train_on_validated_cv_model__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: 0.0257
• Train Accuracy: 0.0818
• Train Wermet: 6.1581
• Validation Loss: 0.4476
• Validation Accuracy: 0.0720
• Validation Wermet: 7.0531
• 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
2.2992	0.0331	6.3187	1.9677	0.0372	7.2782	0
1.7447	0.0431	5.6345	1.7865	0.0408	6.3969	1
1.5036	0.0480	5.6512	1.4821	0.0468	5.1810	2
1.0955	0.0567	4.4606	1.0492	0.0557	3.7886	3
0.7076	0.0654	4.9157	0.7312	0.0627	4.2416	4
0.4703	0.0710	4.9749	0.5668	0.0664	4.8883	5
0.3552	0.0737	5.1823	0.4725	0.0685	4.8141	6
0.2865	0.0754	4.1024	0.4358	0.0694	3.8550	7
0.2380	0.0765	3.3689	0.3947	0.0704	2.2953	8
0.1998	0.0775	2.6219	0.3848	0.0707	3.0529	9
0.1687	0.0782	2.2111	0.3689	0.0711	1.8146	10
0.1417	0.0789	2.5284	0.3709	0.0713	1.9439	11
0.1190	0.0795	2.8048	0.3631	0.0716	3.0845	12
0.0983	0.0800	3.2668	0.3657	0.0717	3.6423	13
0.0815	0.0804	3.8567	0.3806	0.0717	6.1506	14
0.0659	0.0808	5.0931	0.3920	0.0718	6.4431	15
0.0520	0.0812	5.6397	0.3935	0.0720	5.1514	16
0.0409	0.0814	5.7797	0.4147	0.0720	4.2822	17
0.0330	0.0816	5.1017	0.4354	0.0719	6.2876	18
0.0257	0.0818	6.1581	0.4476	0.0720	7.0531	19

Framework versions

• Transformers 4.32.0.dev0
• TensorFlow 2.12.0
• Tokenizers 0.13.3