voiced_pathology

This model is a fine-tuned version of MIT/ast-finetuned-audioset-10-10-0.4593 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 3.1422
• Accuracy: 0.3095

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: 5e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	21	2.3713	0.1905
No log	2.0	42	1.3738	0.2143
No log	3.0	63	1.3843	0.3333
No log	4.0	84	1.7123	0.4048
No log	5.0	105	2.0619	0.3095
No log	6.0	126	2.1451	0.3333
No log	7.0	147	2.5940	0.3095
No log	8.0	168	2.7798	0.2619
No log	9.0	189	3.0970	0.2619
No log	10.0	210	3.1422	0.3095

Framework versions

• Transformers 4.57.0
• Pytorch 2.8.0+cu126
• Datasets 4.2.0
• Tokenizers 0.22.1