This model is a fine-tuned version of MIT/ast-finetuned-speech-commands-v2 on the audiofolder dataset. It achieves the following results on the evaluation set:

Loss: 0.1346
Precision: 0.9744
Recall: 0.9743
F1: 0.9743

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: 32
eval_batch_size: 32
seed: 42
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 5
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1
0.0799	1.0	3496	0.1498	0.9596	0.9573	0.9577
0.0624	2.0	6992	0.1141	0.9689	0.9687	0.9685
0.0091	3.0	10488	0.1285	0.9713	0.9713	0.9711
0.0384	4.0	13984	0.1237	0.9743	0.9743	0.9742
0.0019	5.0	17480	0.1346	0.9744	0.9743	0.9743

Framework versions

Transformers 4.51.3
Pytorch 2.7.0+cu128
Datasets 3.6.0
Tokenizers 0.21.1

mahmoudmamdouh13/ast-mlcommons-speech-commands

ast-mlcommons-speech-commands

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

mahmoudmamdouh13/
ast-mlcommons-speech-commands