Downloads · 30 days
5
8% of all-time downloads
transfer-learning-distilhubert-finetuned-gtzan-model
balamaniansp/transfer-learning-distilhubert-finetuned-gtzan-model
transfer-learning-distilhubert-finetuned-gtzan-model is a audio classification model from balamaniansp. 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
64
Public
Parameters
23.7M
190 MB 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
- Mar 25, 2026
- Updated
- Mar 25, 2026
- SHA
- 4633b55c
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. -->
transfer-learning-distilhubert-finetuned-gtzan-model
This model is a fine-tuned version of cleandata/distilhubert-finetuned-gtzan_accuracy_93 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.3958
- Accuracy: 0.5533
- F1: 0.5277
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- 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: 500
- num_epochs: 10
- mixed_precision_training: Native AMP
- label_smoothing_factor: 0.1
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 1.5508 | 1.0 | 1056 | 1.6318 | 0.4264 | 0.4105 |
| 1.3162 | 2.0 | 2112 | 1.4722 | 0.4916 | 0.4617 |
| 1.1019 | 3.0 | 3168 | 1.4511 | 0.5111 | 0.4850 |
| 1.0425 | 4.0 | 4224 | 1.3866 | 0.5340 | 0.5057 |
| 1.1135 | 5.0 | 5280 | 1.4075 | 0.5351 | 0.5093 |
| 1.0064 | 6.0 | 6336 | 1.3918 | 0.5404 | 0.5138 |
| 0.947 | 7.0 | 7392 | 1.3867 | 0.5488 | 0.5223 |
| 0.861 | 8.0 | 8448 | 1.3882 | 0.5512 | 0.5260 |
| 1.0095 | 9.0 | 9504 | 1.3932 | 0.5541 | 0.5289 |
| 0.884 | 10.0 | 10560 | 1.3958 | 0.5533 | 0.5277 |
Framework versions
- Transformers 4.57.1
- Pytorch 2.8.0+cu126
- Datasets 4.4.2
- Tokenizers 0.22.1
- Task
- Audio Classification
- Library
- transformers
- Type
- hubert
- License
- apache-2.0
- Created
- Mar 25, 2026
- Updated
- Mar 25, 2026