ast-gtzan

polinaZaroko/ast-gtzan

ast-gtzan is a machine learning model from polinaZaroko. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as bsd-3-clause.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

22% of all-time downloads

All-time downloads

Public

Parameters

86.2M

345 MB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors345 MB · 100%

At a glance

License: bsd-3-clause
Model type: audio-spectrogram-transformer
Access: Public
Created: Apr 26, 2025
Updated: Apr 26, 2025
SHA: abb42597

Base models

MIT/ast-finetuned-audioset-10-10-0.4593

Model card

From the Hugging Face model README

ast-gtzan

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: 0.6011
Accuracy: 0.87

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: 2
eval_batch_size: 2
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 8
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 10
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	100	1.2436	0.575
No log	2.0	200	0.6776	0.765
No log	3.0	300	0.5227	0.815
No log	4.0	400	0.6133	0.805
0.6647	5.0	500	0.6569	0.82
0.6647	6.0	600	0.6299	0.855
0.6647	7.0	700	0.6213	0.85
0.6647	8.0	800	0.6398	0.85
0.6647	9.0	900	0.6011	0.87
0.0343	10.0	1000	0.6092	0.87

Framework versions

Transformers 4.39.3
Pytorch 2.6.0+cu124
Datasets 3.5.0
Tokenizers 0.15.2

Type: audio-spectrogram-transformer
License: bsd-3-clause
Created: Apr 26, 2025
Updated: Apr 26, 2025