metadata

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

whisper_final_havest

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: 0.0287
Train Accuracy: 0.0346
Validation Loss: 0.6219
Validation Accuracy: 0.0314
Epoch: 29

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	Validation Loss	Validation Accuracy	Epoch
5.0949	0.0116	4.4444	0.0124	0
4.3242	0.0130	4.0648	0.0140	1
3.9308	0.0145	3.6837	0.0157	2
3.5552	0.0159	3.3410	0.0171	3
3.1591	0.0175	2.8089	0.0198	4
2.2408	0.0221	1.7104	0.0255	5
1.4220	0.0261	1.2181	0.0279	6
1.0460	0.0280	0.9912	0.0290	7
0.8363	0.0291	0.8645	0.0296	8
0.6967	0.0299	0.7748	0.0301	9
0.5942	0.0305	0.7201	0.0304	10
0.5151	0.0309	0.6675	0.0307	11
0.4496	0.0314	0.6382	0.0308	12
0.3951	0.0318	0.6060	0.0310	13
0.3473	0.0321	0.5945	0.0311	14
0.3053	0.0324	0.5752	0.0312	15
0.2684	0.0327	0.5700	0.0313	16
0.2355	0.0330	0.5651	0.0313	17
0.2065	0.0332	0.5619	0.0313	18
0.1785	0.0334	0.5522	0.0314	19
0.1535	0.0337	0.5609	0.0313	20
0.1310	0.0339	0.5590	0.0314	21
0.1115	0.0340	0.5695	0.0313	22
0.0951	0.0342	0.5723	0.0314	23
0.0787	0.0343	0.5796	0.0314	24
0.0649	0.0344	0.5967	0.0313	25
0.0539	0.0345	0.6019	0.0313	26
0.0441	0.0346	0.6113	0.0313	27
0.0364	0.0346	0.6110	0.0314	28
0.0287	0.0346	0.6219	0.0314	29

Framework versions

Transformers 4.25.0.dev0
TensorFlow 2.9.2
Datasets 2.6.1
Tokenizers 0.13.2