Downloads · 30 days
17
3% of all-time downloads
ast-music-genre-classifier
jananiramaseshan/ast-music-genre-classifier
ast-music-genre-classifier is a audio classification model from jananiramaseshan. 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
612
Public
Parameters
86.2M
15.9 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1 GB · 100%
At a glance
- Task
- Audio Classification
- Library
- transformers
- License
- bsd-3-clause
- Model type
- audio-spectrogram-transformer
- Access
- Public
- Created
- Mar 28, 2026
- Updated
- Mar 29, 2026
- SHA
- 5a84b2ab
Base models
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-music-genre-classifier
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: 1.5290
- Accuracy: 0.895
- F1: 0.8941
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: 32
- 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: cosine
- lr_scheduler_warmup_steps: 200
- num_epochs: 15
- mixed_precision_training: Native AMP
- label_smoothing_factor: 0.1
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 3.1775 | 1.0 | 113 | 2.9570 | 0.565 | 0.5462 |
| 2.2507 | 2.0 | 226 | 2.4489 | 0.6887 | 0.6725 |
| 2.2435 | 3.0 | 339 | 2.2957 | 0.7075 | 0.7123 |
| 1.9370 | 4.0 | 452 | 2.1434 | 0.7512 | 0.7461 |
| 1.8154 | 5.0 | 565 | 1.8591 | 0.815 | 0.8180 |
| 1.8500 | 6.0 | 678 | 1.8703 | 0.8113 | 0.8079 |
| 1.6311 | 7.0 | 791 | 1.8013 | 0.83 | 0.8257 |
| 1.6089 | 8.0 | 904 | 1.7369 | 0.8538 | 0.8500 |
| 1.4944 | 9.0 | 1017 | 1.7301 | 0.8475 | 0.8430 |
| 1.3589 | 10.0 | 1130 | 1.6516 | 0.8612 | 0.8608 |
| 1.3406 | 11.0 | 1243 | 1.6810 | 0.8425 | 0.8402 |
| 1.2516 | 12.0 | 1356 | 1.6694 | 0.845 | 0.8437 |
| 1.2724 | 13.0 | 1469 | 1.5963 | 0.86 | 0.8575 |
| 1.1974 | 14.0 | 1582 | 1.5826 | 0.8862 | 0.8854 |
| 1.2371 | 15.0 | 1695 | 1.5290 | 0.895 | 0.8941 |
Framework versions
- Transformers 5.0.0
- Pytorch 2.10.0+cu128
- Datasets 4.8.3
- Tokenizers 0.22.2
- Task
- Audio Classification
- Library
- transformers
- Type
- audio-spectrogram-transformer
- License
- bsd-3-clause
- Created
- Mar 28, 2026
- Updated
- Mar 29, 2026