Downloads · 30 days
23
4% of all-time downloads
ast-finetuned-gtzan
model-man/ast-finetuned-gtzan
ast-finetuned-gtzan is a audio classification model from model-man. 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
610
Public
Repo size
7.6 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin345 MB · 100%
At a glance
- Task
- Audio Classification
- Library
- transformers
- License
- bsd-3-clause
- Model type
- audio-spectrogram-transformer
- Access
- Public
- Created
- Jul 20, 2023
- Updated
- Jul 20, 2023
- SHA
- 5c465a0d
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: 0.6261
- 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: 5e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.03 | 1.0 | 225 | 0.7218 | 0.81 |
| 0.3004 | 2.0 | 450 | 1.1639 | 0.8 |
| 0.5633 | 3.0 | 675 | 0.8839 | 0.83 |
| 0.0354 | 4.0 | 900 | 0.8839 | 0.8 |
| 0.5666 | 5.0 | 1125 | 1.1155 | 0.82 |
| 0.0001 | 6.0 | 1350 | 0.6813 | 0.9 |
| 0.2482 | 7.0 | 1575 | 0.6845 | 0.9 |
| 0.0001 | 8.0 | 1800 | 1.4196 | 0.8 |
| 0.0 | 9.0 | 2025 | 0.9603 | 0.84 |
| 0.0 | 10.0 | 2250 | 0.7030 | 0.88 |
| 0.0 | 11.0 | 2475 | 0.6363 | 0.89 |
| 0.0 | 12.0 | 2700 | 0.6589 | 0.89 |
| 0.0 | 13.0 | 2925 | 0.6845 | 0.87 |
| 0.0 | 14.0 | 3150 | 0.6061 | 0.9 |
| 0.0 | 15.0 | 3375 | 0.6210 | 0.89 |
| 0.0 | 16.0 | 3600 | 0.6136 | 0.89 |
| 0.0 | 17.0 | 3825 | 0.6104 | 0.89 |
| 0.0 | 18.0 | 4050 | 0.6147 | 0.89 |
| 0.0 | 19.0 | 4275 | 0.6259 | 0.89 |
| 0.0 | 20.0 | 4500 | 0.6261 | 0.89 |
Framework versions
- Transformers 4.32.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
- Task
- Audio Classification
- Library
- transformers
- Type
- audio-spectrogram-transformer
- License
- bsd-3-clause
- Created
- Jul 20, 2023
- Updated
- Jul 20, 2023