whisper_4_with_init_sun_syl_wd_0_lr_5en4_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: 1.5840
• Train Accuracy: 0.0226
• Train Wermet: 1.2436
• Train Wermet Syl: 1.9323
• Validation Loss: 1.4040
• Validation Accuracy: 0.0188
• Validation Wermet: 0.5958
• Validation Wermet Syl: 0.6870
• 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': 0.0005, '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
4.9887	0.0111	2.4313	2.0277	3.9591	0.0113	0.9814	0.9748	0
4.6955	0.0116	1.0254	1.1408	3.9756	0.0114	0.9556	0.9274	1
4.6375	0.0117	0.9863	1.1057	3.9172	0.0113	1.0035	1.0561	2
4.5880	0.0118	0.9259	1.0151	3.8477	0.0115	0.9131	0.8768	3
4.4281	0.0121	0.9097	1.0158	3.4905	0.0121	0.8963	0.8527	4
3.7757	0.0137	0.9637	1.1849	2.6810	0.0138	0.8056	0.7421	5
2.9154	0.0165	0.7874	0.9588	2.0364	0.0160	0.6531	0.6367	6
2.2740	0.0191	0.9549	1.3576	1.6962	0.0173	0.6010	0.6229	7
1.8660	0.0210	0.8321	1.1975	1.4948	0.0183	0.5637	0.6709	8
1.5840	0.0226	1.2436	1.9323	1.4040	0.0188	0.5958	0.6870	9

Framework versions

• Transformers 4.34.0.dev0
• TensorFlow 2.13.0
• Tokenizers 0.13.3