whisper_4_with_init_sun_syl_wd_0_lr_9en5_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: 1.1777
• Train Accuracy: 0.0257
• Train Wermet: 0.2978
• Train Wermet Syl: 0.3545
• Validation Loss: 1.1199
• Validation Accuracy: 0.0201
• Validation Wermet: 0.3470
• Validation Wermet Syl: 0.3139
• 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': 9e-05, '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
4.9681	0.0110	1.0978	1.0320	3.9638	0.0115	0.9381	0.9056	0
4.6761	0.0117	0.8575	0.8228	3.9169	0.0114	0.9712	0.9620	1
4.6236	0.0117	0.8445	0.8081	3.8797	0.0114	0.9326	0.8917	2
4.5632	0.0119	0.8050	0.7742	3.7177	0.0119	0.8440	0.7958	3
4.1937	0.0130	0.7566	0.7272	3.0202	0.0133	0.7910	0.7506	4
3.3184	0.0155	0.6793	0.6727	2.3451	0.0150	0.6482	0.6128	5
2.5030	0.0186	0.5700	0.6068	1.7355	0.0172	0.5112	0.4890	6
1.9211	0.0214	0.4611	0.5181	1.3854	0.0187	0.4265	0.3990	7
1.4913	0.0237	0.3598	0.4021	1.2044	0.0197	0.3828	0.3518	8
1.1777	0.0257	0.2978	0.3545	1.1199	0.0201	0.3470	0.3139	9

Framework versions

• Transformers 4.34.0.dev0
• TensorFlow 2.13.0
• Tokenizers 0.13.3