whisper_4_with_init_sun_syl_wd_0__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: 4.5060
• Train Accuracy: 0.0122
• Train Wermet: 0.7392
• Train Wermet Syl: 0.6844
• Validation Loss: 3.7537
• Validation Accuracy: 0.0118
• Validation Wermet: 0.8578
• Validation Wermet Syl: 0.8152
• 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': 1e-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
5.3409	0.0111	1.3547	1.2898	3.9789	0.0114	0.9710	0.9563	0
4.7143	0.0116	0.8622	0.8228	3.9404	0.0113	0.9823	0.9735	1
4.6752	0.0117	0.8472	0.8057	3.9081	0.0114	0.9579	0.9359	2
4.6500	0.0117	0.8382	0.7945	3.8820	0.0115	0.9213	0.8856	3
4.6282	0.0118	0.8286	0.7805	3.8738	0.0114	0.9433	0.9119	4
4.6095	0.0118	0.8190	0.7696	3.8630	0.0115	0.9117	0.8698	5
4.5875	0.0119	0.7976	0.7465	3.8341	0.0116	0.8976	0.8552	6
4.5682	0.0120	0.7753	0.7227	3.8277	0.0116	0.9014	0.8653	7
4.5376	0.0121	0.7528	0.7005	3.7844	0.0118	0.8332	0.7815	8
4.5060	0.0122	0.7392	0.6844	3.7537	0.0118	0.8578	0.8152	9

Framework versions

• Transformers 4.34.0.dev0
• TensorFlow 2.13.0
• Tokenizers 0.13.3