Downloads · 30 days
9
2% of all-time downloads
ast-finetuned-gtzan
fisheggg/ast-finetuned-gtzan
ast-finetuned-gtzan is a audio classification model from fisheggg. 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
435
Public
Repo size
690 MB
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
- Aug 25, 2023
- Updated
- Aug 25, 2023
- SHA
- 07451909
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: 0.3724
- Accuracy: 0.9
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
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- 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 |
|---|---|---|---|---|
| 0.8858 | 1.0 | 112 | 0.5691 | 0.8 |
| 0.5797 | 2.0 | 225 | 0.6960 | 0.74 |
| 0.7178 | 3.0 | 337 | 0.4546 | 0.85 |
| 0.0858 | 4.0 | 450 | 0.4605 | 0.86 |
| 0.0048 | 5.0 | 562 | 0.6531 | 0.86 |
| 0.0218 | 6.0 | 675 | 0.3650 | 0.91 |
| 0.0831 | 7.0 | 787 | 0.4631 | 0.88 |
| 0.0002 | 8.0 | 900 | 0.4604 | 0.87 |
| 0.1109 | 9.0 | 1012 | 0.4126 | 0.91 |
| 0.0003 | 10.0 | 1125 | 0.3681 | 0.92 |
| 0.0001 | 11.0 | 1237 | 0.3977 | 0.9 |
| 0.0001 | 12.0 | 1350 | 0.3466 | 0.91 |
| 0.0001 | 13.0 | 1462 | 0.3682 | 0.91 |
| 0.0001 | 14.0 | 1575 | 0.3695 | 0.9 |
| 0.0 | 15.0 | 1687 | 0.3664 | 0.91 |
| 0.0001 | 16.0 | 1800 | 0.3714 | 0.9 |
| 0.0 | 17.0 | 1912 | 0.3718 | 0.9 |
| 0.0001 | 18.0 | 2025 | 0.3730 | 0.9 |
| 0.0001 | 19.0 | 2137 | 0.3717 | 0.9 |
| 0.0 | 19.91 | 2240 | 0.3724 | 0.9 |
Framework versions
- Transformers 4.33.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3
- Task
- Audio Classification
- Library
- transformers
- Type
- audio-spectrogram-transformer
- License
- bsd-3-clause
- Created
- Aug 25, 2023
- Updated
- Aug 25, 2023