whisper_4_with_init_sun_syl_wd_0_lr_en3_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: 4.6252
• Train Accuracy: 0.0117
• Train Wermet: 1.0167
• Train Wermet Syl: 1.1679
• Validation Loss: 3.9158
• Validation Accuracy: 0.0114
• Validation Wermet: 0.9633
• Validation Wermet Syl: 0.9764
• 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': 0.001, '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
5.0580	0.0110	1.8635	1.7118	4.0077	0.0112	1.0399	1.0195	0
4.7330	0.0115	0.9446	0.9262	3.9889	0.0113	0.9757	0.9619	1
4.6832	0.0116	0.8889	0.8637	3.9832	0.0114	0.9574	0.9276	2
4.6668	0.0116	0.9362	0.9592	3.9389	0.0113	0.9939	1.0310	3
4.6252	0.0117	1.0167	1.1679	3.9158	0.0114	0.9633	0.9764	4

Framework versions

• Transformers 4.34.0.dev0
• TensorFlow 2.13.0
• Tokenizers 0.13.3