Downloads · 30 days
9
10% of all-time downloads
ast-finetuned-gtzan
Janos98/ast-finetuned-gtzan
ast-finetuned-gtzan is a audio classification model from Janos98. Use it for the audio classification task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as bsd-3-clause.
should probably proofread and complete it, then remove this comment. --
All-time downloads
88
Public
Parameters
86.2M
7.6 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors345 MB · 100%
At a glance
- Task
- Audio Classification
- Library
- transformers
- License
- bsd-3-clause
- Model type
- audio-spectrogram-transformer
- Access
- Public
- Created
- Aug 16, 2026
- Updated
- Aug 16, 2026
- SHA
- 2b2a1b08
Base models
Datasets
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
ast-finetuned-gtzan
This model is a fine-tuned version of MIT/ast-finetuned-audioset-10-10-0.4593 on the GTZAN dataset. It achieves the following results on the evaluation set:
- Loss: 0.4226
- Accuracy: 0.89
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: 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: cosine
- lr_scheduler_warmup_steps: 0.1
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.7520 | 1.0 | 57 | 0.5558 | 0.84 |
| 0.3352 | 2.0 | 114 | 0.4808 | 0.83 |
| 0.1013 | 3.0 | 171 | 0.4496 | 0.84 |
| 0.0380 | 4.0 | 228 | 0.6519 | 0.85 |
| 0.0399 | 5.0 | 285 | 0.3841 | 0.89 |
| 0.0105 | 6.0 | 342 | 0.4051 | 0.88 |
| 0.0005 | 7.0 | 399 | 0.4256 | 0.87 |
| 0.0005 | 8.0 | 456 | 0.4204 | 0.89 |
| 0.0005 | 9.0 | 513 | 0.4224 | 0.89 |
| 0.0005 | 10.0 | 570 | 0.4226 | 0.89 |
Framework versions
- Transformers 5.13.1
- Pytorch 2.11.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2
- Task
- Audio Classification
- Library
- transformers
- Type
- audio-spectrogram-transformer
- License
- bsd-3-clause
- Created
- Aug 16, 2026
- Updated
- Aug 16, 2026