laryngitis-sentence

This model is a fine-tuned version of facebook/wav2vec2-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.4969
• Accuracy: 0.8182

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:

• learning_rate: 3e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.6954	1.0	6	0.7061	0.1818
0.6906	2.0	12	0.7867	0.1818
0.6466	3.0	18	0.7956	0.1818
0.63	4.0	24	0.7992	0.1818
0.5842	5.0	30	0.7482	0.4545
0.5338	6.0	36	0.6246	0.6364
0.4733	7.0	42	0.8296	0.5
0.4509	8.0	48	0.5392	0.7273
0.3703	9.0	54	0.5102	0.7727
0.3161	10.0	60	0.3694	0.9545
0.2741	11.0	66	0.5227	0.7727
0.2373	12.0	72	0.4092	0.8182
0.2064	13.0	78	0.5372	0.8182
0.1726	14.0	84	0.5193	0.8182
0.2062	15.0	90	0.4969	0.8182

Framework versions

• Transformers 4.37.2
• Pytorch 2.2.0
• Datasets 2.12.0
• Tokenizers 0.15.1