whisper_4_with_init_sun_syl_wd_0_lr_en4_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: 4.1772
• Train Accuracy: 0.0130
• Train Wermet: 0.7540
• Train Wermet Syl: 0.7249
• Validation Loss: 2.8900
• Validation Accuracy: 0.0136
• Validation Wermet: 0.7575
• Validation Wermet Syl: 0.7119
• 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': 1e-04, '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
4.9733	0.0111	1.5643	1.4238	3.9610	0.0114	0.9612	0.9404	0
4.6745	0.0116	0.8628	0.8245	3.8859	0.0115	0.9258	0.8928	1
4.6271	0.0117	0.8456	0.8063	3.8727	0.0114	0.9561	0.9364	2
4.5738	0.0119	0.8242	0.8004	3.7410	0.0117	0.8760	0.8375	3
4.1772	0.0130	0.7540	0.7249	2.8900	0.0136	0.7575	0.7119	4

Framework versions

• Transformers 4.34.0.dev0
• TensorFlow 2.13.0
• Tokenizers 0.13.3