whisper_wermet_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: 0.5820
• Train Accuracy: 0.0305
• Train Wermet: 1.5323
• Validation Loss: 0.6980
• Validation Accuracy: 0.0305
• Validation Wermet: 1.1238
• 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': 0.01}
• training_precision: float32

Training results

Train Loss	Train Accuracy	Train Wermet	Validation Loss	Validation Accuracy	Validation Wermet	Epoch
5.0795	0.0116	43.8776	4.4395	0.0122	35.4119	0
4.3059	0.0131	29.7976	4.0311	0.0143	26.0070	1
3.8871	0.0148	19.3999	3.6500	0.0158	19.2186	2
3.0943	0.0184	18.3704	2.3327	0.0226	22.5034	3
1.8954	0.0240	16.2471	1.4889	0.0266	14.2782	4
1.2781	0.0269	8.4169	1.1273	0.0283	7.4581	5
0.9797	0.0283	4.8739	0.9481	0.0292	3.9451	6
0.8006	0.0293	2.7433	0.8371	0.0297	2.3065	7
0.6764	0.0299	2.1646	0.7554	0.0301	1.3005	8
0.5820	0.0305	1.5323	0.6980	0.0305	1.1238	9

Framework versions

• Transformers 4.25.0.dev0
• TensorFlow 2.9.2
• Datasets 2.6.1
• Tokenizers 0.13.2