Downloads · 30 days
3
7% of all-time downloads
unlearn_speech_commands_hubert-large_neggrad_4_42
jialicheng/unlearn_speech_commands_hubert-large_neggrad_4_42
unlearn_speech_commands_hubert-large_neggrad_4_42 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
46
Public
Parameters
316M
1.3 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.3 GB · 100%
At a glance
- Task
- Audio Classification
- License
- apache-2.0
- Model type
- hubert
- Access
- Public
- Created
- Oct 24, 2025
- Updated
- Oct 24, 2025
- SHA
- 388903e3
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_ks_42
This model is a fine-tuned version of facebook/hubert-large-ll60k on the superb dataset. It achieves the following results on the evaluation set:
- Loss: -11.1651
- Accuracy: 0.6209
- Test Accuracy: 0.6209
- Df Accuracy: 0.1395
- Unlearn Overall Accuracy: 0.7407
- Unlearn Time: 720.5727
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: 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: 10.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Overall Accuracy | Unlearn Overall Accuracy | Time |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 64 | -4.3569 | 0.2168 | 0.7192 | 0.7192 | -1 |
| No log | 2.0 | 128 | -11.1651 | 0.1395 | 0.7407 | 0.7407 | -1 |
| No log | 3.0 | 192 | -16.2146 | 0.1395 | 0.7407 | 0.7407 | -1 |
| No log | 4.0 | 256 | -21.2411 | 0.1395 | 0.7407 | 0.7407 | -1 |
| No log | 5.0 | 320 | -26.0470 | 0.1395 | 0.7407 | 0.7407 | -1 |
| No log | 6.0 | 384 | -30.3817 | 0.1395 | 0.7407 | 0.7407 | -1 |
| No log | 7.0 | 448 | -34.0174 | 0.1395 | 0.7407 | 0.7407 | -1 |
| No log | 8.0 | 512 | -36.7682 | 0.1395 | 0.7407 | 0.7407 | -1 |
| No log | 9.0 | 576 | -38.4767 | 0.1395 | 0.7407 | 0.7407 | -1 |
| No log | 10.0 | 640 | -39.0640 | 0.1395 | 0.7407 | 0.7407 | -1 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.2+cu118
- Datasets 2.18.0
- Tokenizers 0.15.2
- Task
- Audio Classification
- Type
- hubert
- License
- apache-2.0
- Created
- Oct 24, 2025
- Updated
- Oct 24, 2025