metadata

license: apache-2.0
base_model: openai/whisper-tiny
tags:
  - generated_from_keras_callback
model-index:
  - name: whisper_syl_cv12_pad_lob100__0015
    results: []

whisper_syl_cv12_pad_lob100__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: 0.7388
Train Accuracy: 0.0305
Train Wermet: 0.2828
Validation Loss: 0.8773
Validation Accuracy: 0.0221
Validation Wermet: 0.3322
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
5.0233	0.0115	1.6383	3.8616	0.0117	0.9516	0
4.4412	0.0127	0.8560	3.5410	0.0125	0.8971	1
4.0719	0.0138	0.8366	3.2944	0.0132	0.8706	2
3.8091	0.0146	0.8133	3.1691	0.0134	0.8487	3
3.6239	0.0152	0.7866	3.0647	0.0136	0.8282	4
3.4749	0.0156	0.7589	2.9835	0.0139	0.8049	5
3.3444	0.0161	0.7359	2.9351	0.0140	0.7979	6
3.2215	0.0165	0.7138	2.8468	0.0145	0.7589	7
3.0754	0.0172	0.6873	2.7530	0.0148	0.7413	8
2.8713	0.0181	0.6484	2.5226	0.0157	0.7017	9
2.5469	0.0197	0.5934	2.1931	0.0168	0.6285	10
2.0233	0.0225	0.4997	1.6411	0.0189	0.5215	11
1.3808	0.0264	0.3852	1.2401	0.0205	0.4238	12
0.9722	0.0290	0.3123	1.0195	0.0215	0.3682	13
0.7388	0.0305	0.2828	0.8773	0.0221	0.3322	14

Framework versions

Transformers 4.33.0.dev0
TensorFlow 2.13.0
Tokenizers 0.13.3