Downloads · 30 days
16
28% of all-time downloads
korean_kws2
jandyjeong/korean_kws2
korean_kws2 is a audio classification model from jandyjeong. 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.
should probably proofread and complete it, then remove this comment. --
All-time downloads
58
Public
Parameters
94.6M
378 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors378 MB · 100%
At a glance
- Task
- Audio Classification
- Library
- transformers
- Model type
- wav2vec2
- Access
- Public
- Created
- Apr 16, 2026
- Updated
- Apr 16, 2026
- SHA
- f879b3e9
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. -->
korean_kws2
This model is a fine-tuned version of Kkonjeong/wav2vec2-base-korean on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3823
- Accuracy: 1.0
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: 0.0001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- 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
- num_epochs: 30
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 2 | 1.9713 | 0.0769 |
| No log | 2.0 | 4 | 1.8979 | 0.2308 |
| No log | 3.0 | 6 | 1.7894 | 0.2308 |
| No log | 4.0 | 8 | 1.7711 | 0.3846 |
| No log | 5.0 | 10 | 1.6854 | 0.3846 |
| No log | 6.0 | 12 | 1.5627 | 0.3846 |
| No log | 7.0 | 14 | 1.4135 | 0.6923 |
| No log | 8.0 | 16 | 1.2909 | 0.6923 |
| No log | 9.0 | 18 | 1.1544 | 0.7692 |
| No log | 10.0 | 20 | 1.1544 | 0.7692 |
| No log | 11.0 | 22 | 1.0466 | 0.9231 |
| No log | 12.0 | 24 | 0.9549 | 0.9231 |
| No log | 13.0 | 26 | 0.8672 | 0.9231 |
| No log | 14.0 | 28 | 0.7854 | 0.9231 |
| No log | 15.0 | 30 | 0.7150 | 0.9231 |
| No log | 16.0 | 32 | 0.6466 | 0.9231 |
| No log | 17.0 | 34 | 0.5998 | 1.0 |
| No log | 18.0 | 36 | 0.5572 | 1.0 |
| No log | 19.0 | 38 | 0.5175 | 1.0 |
| No log | 20.0 | 40 | 0.4908 | 1.0 |
| No log | 21.0 | 42 | 0.4667 | 1.0 |
| No log | 22.0 | 44 | 0.4468 | 1.0 |
| No log | 23.0 | 46 | 0.4326 | 1.0 |
| No log | 24.0 | 48 | 0.4214 | 1.0 |
| No log | 25.0 | 50 | 0.4110 | 1.0 |
| No log | 26.0 | 52 | 0.4017 | 1.0 |
| No log | 27.0 | 54 | 0.3937 | 1.0 |
| No log | 28.0 | 56 | 0.3878 | 1.0 |
| No log | 29.0 | 58 | 0.3839 | 1.0 |
| No log | 30.0 | 60 | 0.3823 | 1.0 |
Framework versions
- Transformers 5.0.0
- Pytorch 2.10.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2
- Task
- Audio Classification
- Library
- transformers
- Type
- wav2vec2
- Created
- Apr 16, 2026
- Updated
- Apr 16, 2026