metadata

license: apache-2.0
base_model: openai/whisper-tiny
tags:
  - generated_from_keras_callback
model-index:
  - name: whisper_syl_cv12_pad_lob100__0020
    results: []

whisper_syl_cv12_pad_lob100__0020

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: 0.2444
Train Accuracy: 0.0343
Train Wermet: 1.1298
Validation Loss: 0.6369
Validation Accuracy: 0.0232
Validation Wermet: 0.6637
Epoch: 19

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
0.5787	0.0317	0.2751	0.7970	0.0225	0.3083	15
0.4642	0.0325	0.2878	0.7315	0.0227	0.2964	16
0.3752	0.0332	0.4217	0.6897	0.0229	0.3297	17
0.3042	0.0338	0.7294	0.6572	0.0231	0.4453	18
0.2444	0.0343	1.1298	0.6369	0.0232	0.6637	19

Framework versions

Transformers 4.33.0.dev0
TensorFlow 2.13.0
Tokenizers 0.13.3