whisper_4_with_init_sun_char_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: 2.3528
• Train Accuracy: 0.0376
• Train Wermet: 0.0669
• Validation Loss: 2.0705
• Validation Accuracy: 0.0275
• Validation Wermet: 0.1089
• 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': 1e-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
3.2071	0.0313	0.1237	2.8546	0.0225	0.1109	0
3.0365	0.0325	0.0375	2.8115	0.0228	0.1215	1
3.0162	0.0326	0.0484	2.7884	0.0231	0.1318	2
3.0042	0.0327	0.0555	2.7853	0.0233	0.1393	3
2.9934	0.0328	0.0614	2.7657	0.0232	0.1273	4
2.9858	0.0329	0.0654	2.7542	0.0234	0.1073	5
2.9735	0.0330	0.0673	2.7367	0.0234	0.1414	6
2.9574	0.0332	0.0704	2.6961	0.0240	0.1429	7
2.9320	0.0335	0.0723	2.6652	0.0239	0.0990	8
2.8976	0.0339	0.0729	2.5997	0.0245	0.0944	9
2.8460	0.0343	0.0728	2.5378	0.0248	0.1435	10
2.7781	0.0347	0.0741	2.4355	0.0254	0.1372	11
2.7083	0.0352	0.0747	2.5163	0.0248	0.0987	12
2.6445	0.0356	0.0720	2.2997	0.0261	0.1484	13
2.5838	0.0360	0.0724	2.2386	0.0266	0.1419	14
2.5294	0.0363	0.0721	2.1855	0.0269	0.1289	15
2.4760	0.0367	0.0711	2.1682	0.0271	0.1214	16
2.4339	0.0370	0.0698	2.1018	0.0273	0.1264	17
2.3867	0.0373	0.0684	2.0647	0.0275	0.1403	18
2.3528	0.0376	0.0669	2.0705	0.0275	0.1089	19

Framework versions

• Transformers 4.34.0.dev0
• TensorFlow 2.13.0
• Tokenizers 0.13.3