whisper_4_with_init_sun_syl_wd_0_lr_5en4_0005

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: 4.4281
• Train Accuracy: 0.0121
• Train Wermet: 0.9097
• Train Wermet Syl: 1.0158
• Validation Loss: 3.4905
• Validation Accuracy: 0.0121
• Validation Wermet: 0.8963
• Validation Wermet Syl: 0.8527
• Epoch: 4

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

Framework versions

• Transformers 4.34.0.dev0
• TensorFlow 2.13.0
• Tokenizers 0.13.3