Downloads · 30 days
7
19% of all-time downloads
distilhubertmk36
hwhjones/distilhubertmk36
distilhubertmk36 is a audio classification model from hwhjones. 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
37
Public
Parameters
23.7M
948 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
- Dec 29, 2023
- Updated
- Dec 29, 2023
- SHA
- 0e97ed1e
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: 0.8185
- Accuracy: 0.87
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: 0.01
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.668 | 1.0 | 225 | 0.5547 | 0.84 |
| 0.4179 | 2.0 | 450 | 0.7757 | 0.74 |
| 0.0298 | 3.0 | 675 | 0.7077 | 0.84 |
| 0.2144 | 4.0 | 900 | 0.6262 | 0.87 |
| 0.0079 | 5.0 | 1125 | 0.6068 | 0.88 |
| 0.0021 | 6.0 | 1350 | 0.8321 | 0.84 |
| 0.0014 | 7.0 | 1575 | 0.9661 | 0.84 |
| 0.0013 | 8.0 | 1800 | 0.7852 | 0.86 |
| 0.001 | 9.0 | 2025 | 0.8126 | 0.86 |
| 0.001 | 10.0 | 2250 | 0.8185 | 0.87 |
Framework versions
- Transformers 4.37.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.4.0
- Tokenizers 0.15.0
- Task
- Audio Classification
- Library
- transformers
- Type
- hubert
- License
- apache-2.0
- Created
- Dec 29, 2023
- Updated
- Dec 29, 2023