Downloads · 30 days
10
3% of all-time downloads
distilhubert-finetuned-gtzan
oyemade/distilhubert-finetuned-gtzan
distilhubert-finetuned-gtzan is a audio classification model from oyemade. 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 apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
310
Public
Parameters
23.7M
1.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors94.8 MB · 100%
At a glance
- Task
- Audio Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- hubert
- Access
- Public
- Created
- Apr 24, 2024
- Updated
- Apr 24, 2024
- SHA
- 0f04a054
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. -->
distilhubert-finetuned-gtzan
This model is a fine-tuned version of ntu-spml/distilhubert on the GTZAN dataset. It achieves the following results on the evaluation set:
- Loss: 0.6691
- 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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- 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: 15
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.0761 | 1.0 | 113 | 1.9856 | 0.5 |
| 1.3376 | 2.0 | 226 | 1.3481 | 0.65 |
| 1.0645 | 3.0 | 339 | 1.0655 | 0.68 |
| 0.6495 | 4.0 | 452 | 0.8836 | 0.73 |
| 0.4802 | 5.0 | 565 | 0.7388 | 0.79 |
| 0.3875 | 6.0 | 678 | 0.6475 | 0.74 |
| 0.2788 | 7.0 | 791 | 0.5626 | 0.84 |
| 0.0623 | 8.0 | 904 | 0.6053 | 0.86 |
| 0.0848 | 9.0 | 1017 | 0.5784 | 0.85 |
| 0.033 | 10.0 | 1130 | 0.6307 | 0.86 |
| 0.0152 | 11.0 | 1243 | 0.6946 | 0.82 |
| 0.0098 | 12.0 | 1356 | 0.6419 | 0.87 |
| 0.0083 | 13.0 | 1469 | 0.6583 | 0.87 |
| 0.0081 | 14.0 | 1582 | 0.6584 | 0.87 |
| 0.0072 | 15.0 | 1695 | 0.6691 | 0.86 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
- Task
- Audio Classification
- Library
- transformers
- Type
- hubert
- License
- apache-2.0
- Created
- Apr 24, 2024
- Updated
- Apr 24, 2024