Downloads · 30 days
11
21% of all-time downloads
superb-si_hubert-base
jialicheng/superb-si_hubert-base
superb-si_hubert-base is a audio classification model from jialicheng. Use it for the audio classification task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
53
Public
Parameters
94.9M
1.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.npy768 MB · 67%
At a glance
- Task
- Audio Classification
- License
- apache-2.0
- Model type
- hubert
- Access
- Public
- Created
- Aug 26, 2025
- Updated
- Aug 26, 2025
- SHA
- 39e7a64a
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. -->
superb_si_42
This model is a fine-tuned version of facebook/hubert-base-ls960 on the superb dataset. It achieves the following results on the evaluation set:
- Loss: 3.9981
- Accuracy: 0.1577
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: 32
- 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: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 6.2927 | 1.0 | 4324 | 6.5321 | 0.0049 |
| 5.6909 | 2.0 | 8648 | 6.0103 | 0.0088 |
| 5.3829 | 3.0 | 12972 | 5.5309 | 0.0235 |
| 4.9995 | 4.0 | 17296 | 5.1894 | 0.0379 |
| 4.7591 | 5.0 | 21620 | 4.8644 | 0.0620 |
| 4.5243 | 6.0 | 25944 | 4.6042 | 0.0859 |
| 4.2486 | 7.0 | 30268 | 4.3497 | 0.1173 |
| 4.0813 | 8.0 | 34592 | 4.1215 | 0.1405 |
| 3.9317 | 9.0 | 38916 | 4.0431 | 0.1508 |
| 3.8568 | 10.0 | 43240 | 3.9981 | 0.1577 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
- Task
- Audio Classification
- Type
- hubert
- License
- apache-2.0
- Created
- Aug 26, 2025
- Updated
- Aug 26, 2025