Downloads · 30 days
5
9% of all-time downloads
unlearn_speech_commands_wav2vec2-base_random_label_6_42
jialicheng/unlearn_speech_commands_wav2vec2-base_random_label_6_42
unlearn_speech_commands_wav2vec2-base_random_label_6_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
54
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
- c4fafa80
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: 0.1522
- Accuracy: 0.9835
- Test Accuracy: 0.9835
- Df Accuracy: 0.9772
- Unlearn Overall Accuracy: 0.5032
- Unlearn Time: -1
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 |
|---|---|---|---|---|---|---|---|
| 0.3859 | 1.0 | 1597 | 0.1543 | 0.9798 | 0.5020 | 0.5020 | -1 |
| 0.3298 | 2.0 | 3194 | 0.1617 | 0.9755 | 0.5007 | 0.5007 | -1 |
| 0.3355 | 3.0 | 4791 | 0.1713 | 0.9755 | 0.5014 | 0.5014 | -1 |
| 0.3295 | 4.0 | 6388 | 0.1542 | 0.9775 | 0.5021 | 0.5021 | -1 |
| 0.3231 | 5.0 | 7985 | 0.1422 | 0.9798 | 0.5020 | 0.5020 | -1 |
| 0.3181 | 6.0 | 9582 | 0.1633 | 0.9791 | 0.5006 | 0.5006 | -1 |
| 0.3074 | 7.0 | 11179 | 0.1458 | 0.9791 | 0.5007 | 0.5007 | -1 |
| 0.3042 | 8.0 | 12776 | 0.1432 | 0.9781 | 0.5022 | 0.5022 | -1 |
| 0.2968 | 9.0 | 14373 | 0.1645 | 0.9781 | 0.5014 | 0.5014 | -1 |
| 0.2897 | 10.0 | 15970 | 0.1546 | 0.9785 | 0.5009 | 0.5009 | -1 |
| 0.2846 | 11.0 | 17567 | 0.1464 | 0.9794 | 0.5009 | 0.5009 | -1 |
| 0.2827 | 12.0 | 19164 | 0.1590 | 0.9788 | 0.5011 | 0.5011 | -1 |
| 0.271 | 13.0 | 20761 | 0.1540 | 0.9801 | 0.5011 | 0.5011 | -1 |
| 0.2727 | 14.0 | 22358 | 0.1657 | 0.9798 | 0.5020 | 0.5020 | -1 |
| 0.2655 | 15.0 | 23955 | 0.1458 | 0.9801 | 0.5021 | 0.5021 | -1 |
| 0.2643 | 16.0 | 25552 | 0.1453 | 0.9785 | 0.5028 | 0.5028 | -1 |
| 0.2569 | 17.0 | 27149 | 0.1542 | 0.9785 | 0.5027 | 0.5027 | -1 |
| 0.255 | 18.0 | 28746 | 0.1504 | 0.9781 | 0.5029 | 0.5029 | -1 |
| 0.2508 | 19.0 | 30343 | 0.1463 | 0.9775 | 0.5031 | 0.5031 | -1 |
| 0.252 | 20.0 | 31940 | 0.1522 | 0.9772 | 0.5032 | 0.5032 | -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