distil-wav2vec2-finetuned-gtzan – AI Model by apv53-fit | AlphaNeural AI

You can deploy this model and start earning money today!

apv53-fit/
distil-wav2vec2-finetuned-gtzan

like

0

audio-classification

generated_from_trainer

OthmaneJ/distil-wav2vec2

endpoints_compatible

Views

No views yet

apv53-finetuned-gtzan

This model is a fine-tuned version of OthmaneJ/distil-wav2vec2 on the GTZAN dataset. It achieves the following results on the evaluation set:

Loss: 0.7427
Accuracy: 0.82

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 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: 10
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.8074	1.0	113	1.1764	0.63
0.8226	2.0	226	0.8222	0.73
0.8055	3.0	339	0.9653	0.74
0.5099	4.0	452	1.3430	0.59
0.6568	5.0	565	0.8467	0.76
0.5449	6.0	678	0.9551	0.76
0.3872	7.0	791	0.8185	0.81
0.3452	8.0	904	0.8198	0.82
0.1398	9.0	1017	0.7110	0.85
0.1282	10.0	1130	0.7427	0.82

Framework versions

Transformers 4.48.0.dev0
Pytorch 2.5.1+cu121
Datasets 3.2.0
Tokenizers 0.21.0