whisper_havest_0025

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: 4.0701
• Train Accuracy: 0.0135
• Train Do Wer: 1.0
• Validation Loss: 4.6038
• Validation Accuracy: 0.0128
• Validation Do Wer: 1.0
• Epoch: 24

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 Do Wer	Validation Loss	Validation Accuracy	Validation Do Wer	Epoch
9.9191	0.0046	1.0	8.5836	0.0067	1.0	0
8.0709	0.0083	1.0	7.4667	0.0089	1.0	1
7.1652	0.0100	1.0	6.8204	0.0112	1.0	2
6.7196	0.0114	1.0	6.5192	0.0114	1.0	3
6.4115	0.0115	1.0	6.2357	0.0115	1.0	4
6.1085	0.0115	1.0	5.9657	0.0115	1.0	5
5.8206	0.0115	1.0	5.7162	0.0115	1.0	6
5.5567	0.0115	1.0	5.4963	0.0115	1.0	7
5.3223	0.0116	1.0	5.3096	0.0116	1.0	8
5.1222	0.0117	1.0	5.1600	0.0117	1.0	9
4.9580	0.0117	1.0	5.0391	0.0118	1.0	10
4.8251	0.0119	1.0	4.9427	0.0118	1.0	11
4.7171	0.0119	1.0	4.8691	0.0119	1.0	12
4.6284	0.0121	1.0	4.8123	0.0120	1.0	13
4.5508	0.0121	1.0	4.7620	0.0121	1.0	14
4.4855	0.0123	1.0	4.7260	0.0121	1.0	15
4.4305	0.0124	1.0	4.7018	0.0123	1.0	16
4.3788	0.0125	1.0	4.6738	0.0123	1.0	17
4.3305	0.0127	1.0	4.6525	0.0124	1.0	18
4.2860	0.0128	1.0	4.6401	0.0125	1.0	19
4.2451	0.0130	1.0	4.6234	0.0126	1.0	20
4.1994	0.0132	1.0	4.6077	0.0128	1.0	21
4.1521	0.0133	1.0	4.6098	0.0129	1.0	22
4.1148	0.0134	1.0	4.5919	0.0129	1.0	23
4.0701	0.0135	1.0	4.6038	0.0128	1.0	24

Framework versions

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