whisper_4_with_init_sun_syl_wd_0_lr_en2_0015

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: 4.8581
• Train Accuracy: 0.0113
• Train Wermet: 1.0010
• Train Wermet Syl: 1.0020
• Validation Loss: 4.1140
• Validation Accuracy: 0.0113
• Validation Wermet: 0.9851
• Validation Wermet Syl: 0.9843
• Epoch: 14

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': 0.01, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0}
• training_precision: float32

Training results

Train Loss	Train Accuracy	Train Wermet	Train Wermet Syl	Validation Loss	Validation Accuracy	Validation Wermet	Validation Wermet Syl	Epoch
39.6121	0.0057	33.2649	25.5768	4.5339	0.0113	0.9851	0.9843	0
5.3698	0.0107	12.0116	9.0545	4.3408	0.0112	0.9919	0.9915	1
5.1979	0.0109	9.4008	7.1909	4.2108	0.0113	0.9851	0.9843	2
5.0669	0.0110	7.0382	5.3339	4.1662	0.0113	0.9851	0.9843	3
4.9546	0.0111	4.8506	3.7351	4.3022	0.0112	0.9870	0.9854	4
4.9453	0.0111	3.9228	3.1750	4.1194	0.0113	0.9851	0.9843	5
4.9123	0.0112	2.2402	1.9643	4.1865	0.0112	1.0000	1.0000	6
4.8957	0.0112	1.7673	1.5892	4.1150	0.0112	1.0000	0.9999	7
4.8959	0.0112	2.2166	1.9601	4.1185	0.0113	0.9851	0.9843	8
4.8685	0.0113	0.9890	0.9897	4.1857	0.0113	0.9851	0.9843	9
4.8677	0.0113	1.2238	1.2355	4.1211	0.0113	0.9851	0.9843	10
4.8585	0.0113	1.0074	1.0059	4.1065	0.0113	0.9851	0.9843	11
4.8609	0.0113	1.1844	1.1144	4.1053	0.0113	0.9851	0.9843	12
4.8588	0.0113	1.2374	1.1658	4.1377	0.0113	0.9851	0.9843	13
4.8581	0.0113	1.0010	1.0020	4.1140	0.0113	0.9851	0.9843	14

Framework versions

• Transformers 4.34.0.dev0
• TensorFlow 2.13.0
• Tokenizers 0.13.3