Downloads · 30 days
4
18% of all-time downloads
unlearn_speech_commands_wav2vec2-base_random_label_2_42
jialicheng/unlearn_speech_commands_wav2vec2-base_random_label_2_42
unlearn_speech_commands_wav2vec2-base_random_label_2_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
22
Public
Parameters
94.6M
381 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors378 MB · 99%
At a glance
- Task
- Audio Classification
- License
- apache-2.0
- Model type
- wav2vec2
- Access
- Public
- Created
- Oct 24, 2025
- Updated
- Oct 24, 2025
- SHA
- ade752b4
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/wav2vec2-base on the superb dataset. It achieves the following results on the evaluation set:
- Loss: 0.1257
- Accuracy: 0.9804
- Test Accuracy: 0.9804
- Df Accuracy: 0.9628
- Unlearn Overall Accuracy: 0.5088
- Unlearn Time: 4127.6066
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: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Overall Accuracy | Unlearn Overall Accuracy | Time |
|---|---|---|---|---|---|---|---|
| 0.2134 | 1.0 | 1597 | 0.1121 | 0.9716 | 0.5053 | 0.5053 | -1 |
| 0.2221 | 2.0 | 3194 | 0.1051 | 0.9677 | 0.5059 | 0.5059 | -1 |
| 0.2427 | 3.0 | 4791 | 0.1541 | 0.9618 | 0.5082 | 0.5082 | -1 |
| 0.2382 | 4.0 | 6388 | 0.1214 | 0.9677 | 0.5067 | 0.5067 | -1 |
| 0.2278 | 5.0 | 7985 | 0.1257 | 0.9628 | 0.5088 | 0.5088 | -1 |
| 0.2151 | 6.0 | 9582 | 0.1155 | 0.9696 | 0.5057 | 0.5057 | -1 |
| 0.2179 | 7.0 | 11179 | 0.1231 | 0.9667 | 0.5066 | 0.5066 | -1 |
| 0.2079 | 8.0 | 12776 | 0.1087 | 0.9687 | 0.5060 | 0.5060 | -1 |
| 0.1962 | 9.0 | 14373 | 0.1241 | 0.9706 | 0.5051 | 0.5051 | -1 |
| 0.1925 | 10.0 | 15970 | 0.1071 | 0.9706 | 0.5059 | 0.5059 | -1 |
| 0.1885 | 11.0 | 17567 | 0.1240 | 0.9716 | 0.5048 | 0.5048 | -1 |
| 0.1808 | 12.0 | 19164 | 0.1151 | 0.9706 | 0.5061 | 0.5061 | -1 |
| 0.1702 | 13.0 | 20761 | 0.1304 | 0.9716 | 0.5046 | 0.5046 | -1 |
| 0.17 | 14.0 | 22358 | 0.1301 | 0.9716 | 0.5051 | 0.5051 | -1 |
| 0.1611 | 15.0 | 23955 | 0.1237 | 0.9716 | 0.5050 | 0.5050 | -1 |
| 0.1582 | 16.0 | 25552 | 0.1239 | 0.9716 | 0.5054 | 0.5054 | -1 |
| 0.1528 | 17.0 | 27149 | 0.1257 | 0.9755 | 0.5033 | 0.5033 | -1 |
| 0.1516 | 18.0 | 28746 | 0.1250 | 0.9736 | 0.5042 | 0.5042 | -1 |
| 0.1495 | 19.0 | 30343 | 0.1274 | 0.9745 | 0.5040 | 0.5040 | -1 |
| 0.1426 | 20.0 | 31940 | 0.1338 | 0.9745 | 0.5038 | 0.5038 | -1 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.2+cu118
- Datasets 2.18.0
- Tokenizers 0.15.2
- Task
- Audio Classification
- Type
- wav2vec2
- License
- apache-2.0
- Created
- Oct 24, 2025
- Updated
- Oct 24, 2025