Downloads · 30 days
9
5% of all-time downloads
ast-genre-classifier-frozen
jananiramaseshan/ast-genre-classifier-frozen
ast-genre-classifier-frozen 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
169
Public
Parameters
86.2M
5.2 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
- Mar 27, 2026
- Updated
- Mar 27, 2026
- SHA
- 927bb656
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-genre-classifier-frozen
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: 3.1315
- Accuracy: 0.5487
- F1: 0.5437
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: 0.001
- train_batch_size: 32
- 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: 200
- num_epochs: 15
- mixed_precision_training: Native AMP
- label_smoothing_factor: 0.1
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 4.2337 | 1.0 | 113 | 4.2102 | 0.2687 | 0.2253 |
| 3.8161 | 2.0 | 226 | 3.9162 | 0.3137 | 0.2691 |
| 3.6756 | 3.0 | 339 | 3.5689 | 0.4138 | 0.3893 |
| 3.3915 | 4.0 | 452 | 3.5414 | 0.4313 | 0.4065 |
| 3.4779 | 5.0 | 565 | 3.4284 | 0.4425 | 0.4192 |
| 3.3611 | 6.0 | 678 | 3.3297 | 0.4875 | 0.4591 |
| 3.2965 | 7.0 | 791 | 3.2457 | 0.4888 | 0.4760 |
| 3.2875 | 8.0 | 904 | 3.2551 | 0.49 | 0.4839 |
| 3.2142 | 9.0 | 1017 | 3.2148 | 0.5038 | 0.4961 |
| 3.0617 | 10.0 | 1130 | 3.1899 | 0.5288 | 0.5231 |
| 3.1601 | 11.0 | 1243 | 3.2020 | 0.515 | 0.5065 |
| 3.1036 | 12.0 | 1356 | 3.1678 | 0.5425 | 0.5312 |
| 3.1826 | 13.0 | 1469 | 3.1346 | 0.5425 | 0.5333 |
| 3.0659 | 14.0 | 1582 | 3.1100 | 0.55 | 0.5438 |
| 3.1693 | 15.0 | 1695 | 3.1315 | 0.5487 | 0.5437 |
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 27, 2026
- Updated
- Mar 27, 2026