metadata

license: apache-2.0
base_model: openai/whisper-tiny
tags:
  - generated_from_keras_callback
model-index:
  - name: train_from_raw_cv12_true__0015
    results: []

train_from_raw_cv12_true__0015

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: 0.2922
Train Accuracy: 0.1013
Train Wermet: 3.5614
Validation Loss: 0.3391
Validation Accuracy: 0.0623
Validation Wermet: 9.6152
Epoch: 14

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': 2e-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
2.3396	0.0444	2.7124	1.8124	0.0331	9.4418	0
1.7496	0.0562	3.2708	1.6529	0.0359	9.7805	1
1.6254	0.0594	3.1714	1.5874	0.0371	10.4139	2
1.5490	0.0615	3.0208	1.5102	0.0382	8.2054	3
1.4910	0.0631	2.8298	1.4213	0.0402	8.9930	4
1.4233	0.0650	2.7100	1.3319	0.0421	8.8483	5
1.3203	0.0679	2.5125	1.1806	0.0450	7.0373	6
1.1453	0.0730	2.5001	1.0029	0.0484	5.7328	7
0.9537	0.0789	2.6295	0.7799	0.0529	6.7373	8
0.7822	0.0844	2.7501	0.6499	0.0556	8.5538	9
0.6317	0.0895	2.9507	0.5467	0.0578	8.4990	10
0.5010	0.0940	3.1604	0.4597	0.0597	9.4002	11
0.4026	0.0975	3.2910	0.3984	0.0610	9.8173	12
0.3372	0.0998	3.5302	0.3571	0.0619	9.6433	13
0.2922	0.1013	3.5614	0.3391	0.0623	9.6152	14

Framework versions

Transformers 4.33.0.dev0
TensorFlow 2.13.0
Tokenizers 0.13.3