Downloads · 30 days
46
12% of all-time downloads
distilhubert-finetuned-ravdess
amnesiackid/distilhubert-finetuned-ravdess
distilhubert-finetuned-ravdess is a audio classification model from amnesiackid. 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
399
Public
Parameters
23.7M
2.5 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
- Jul 18, 2025
- Updated
- Sep 5, 2026
- SHA
- 93da8aa5
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. -->
distilhubert-finetuned-ravdess
This model is a fine-tuned version of ntu-spml/distilhubert on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8330
- Accuracy: 0.8681
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: 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: linear
- lr_scheduler_warmup_steps: 0.1
- num_epochs: 20
- mixed_precision_training: Native AMP
- label_smoothing_factor: 0.1
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.0479 | 1.0 | 126 | 2.0465 | 0.2639 |
| 1.9198 | 2.0 | 252 | 1.7636 | 0.3472 |
| 1.7474 | 3.0 | 378 | 1.5941 | 0.4514 |
| 1.4198 | 4.0 | 504 | 1.3667 | 0.5486 |
| 1.4462 | 5.0 | 630 | 1.2058 | 0.6458 |
| 1.1219 | 6.0 | 756 | 1.0412 | 0.7708 |
| 1.4561 | 7.0 | 882 | 0.9866 | 0.7708 |
| 1.1193 | 8.0 | 1008 | 0.9222 | 0.8264 |
| 1.1304 | 9.0 | 1134 | 0.9000 | 0.8125 |
| 0.9479 | 10.0 | 1260 | 0.8796 | 0.8194 |
| 0.9131 | 11.0 | 1386 | 0.8657 | 0.8194 |
| 0.8876 | 12.0 | 1512 | 0.8330 | 0.8681 |
| 0.8605 | 13.0 | 1638 | 0.8073 | 0.8611 |
| 0.9696 | 14.0 | 1764 | 0.8280 | 0.8403 |
| 0.9908 | 15.0 | 1890 | 0.8373 | 0.8403 |
| 0.8529 | 16.0 | 2016 | 0.8283 | 0.8681 |
| 0.6335 | 17.0 | 2142 | 0.8225 | 0.8542 |
| 0.7234 | 18.0 | 2268 | 0.8164 | 0.8611 |
| 1.0229 | 19.0 | 2394 | 0.8132 | 0.8542 |
| 0.8715 | 20.0 | 2520 | 0.8083 | 0.8611 |
Framework versions
- Transformers 5.16.1
- Pytorch 2.11.0+cu128
- Datasets 4.0.0
- Tokenizers 0.23.1
- Task
- Audio Classification
- Library
- transformers
- Type
- hubert
- License
- apache-2.0
- Created
- Jul 18, 2025
- Updated
- Sep 5, 2026