Downloads · 30 days
2
2% of all-time downloads
ast-gtzan-champion-87-plus
Saran16/ast-gtzan-champion-87-plus
ast-gtzan-champion-87-plus is a audio classification model from Saran16. 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
84
Public
Parameters
86.2M
3.4 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
- Dec 4, 2025
- Updated
- Dec 4, 2025
- SHA
- f3add2d0
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-gtzan-champion-87-plus
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: 0.4260
- Accuracy: 0.86
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: 32
- 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
- lr_scheduler_warmup_steps: 500
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 50 | 1.8862 | 0.43 |
| No log | 2.0 | 100 | 1.0574 | 0.7 |
| No log | 3.0 | 150 | 0.7247 | 0.76 |
| No log | 4.0 | 200 | 0.6073 | 0.81 |
| No log | 5.0 | 250 | 0.6806 | 0.76 |
| No log | 6.0 | 300 | 0.4890 | 0.85 |
| No log | 7.0 | 350 | 0.5299 | 0.87 |
| No log | 8.0 | 400 | 0.6727 | 0.83 |
| No log | 9.0 | 450 | 0.6791 | 0.82 |
| 0.4755 | 10.0 | 500 | 0.6119 | 0.85 |
Framework versions
- Transformers 4.57.2
- Pytorch 2.9.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.1
- Task
- Audio Classification
- Library
- transformers
- Type
- audio-spectrogram-transformer
- License
- bsd-3-clause
- Created
- Dec 4, 2025
- Updated
- Dec 4, 2025