wks

sungsy0323/wks

wks is a audio classification model from sungsy0323. 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. --

Downloads · 30 days

43% of all-time downloads

All-time downloads

Public

Parameters

94.6M

378 MB on disk

Likes

Public

Hugging Face

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: Dec 10, 2025
Updated: Dec 10, 2025
SHA: 04758760

Base models

Kkonjeong/wav2vec2-base-korean

Model card

From the Hugging Face model README

wks

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: 0.3852
Accuracy: 0.9474

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	1.8512	0.1579
No log	2.0	4	1.8512	0.1579
No log	3.0	6	1.7512	0.4211
No log	4.0	8	1.6830	0.3684
No log	5.0	10	1.5444	0.6316
No log	6.0	12	1.4469	0.4737
No log	7.0	14	1.3275	0.6316
No log	8.0	16	1.1882	0.8421
No log	9.0	18	1.0719	0.8421
No log	10.0	20	1.0585	0.8421
No log	11.0	22	1.0017	0.8947
No log	12.0	24	0.9294	0.8947
No log	13.0	26	0.8423	0.8947
No log	14.0	28	0.7696	0.8421
No log	15.0	30	0.7280	0.8947
No log	16.0	32	0.6871	0.9474
No log	17.0	34	0.6423	0.9474
No log	18.0	36	0.6102	0.9474
No log	19.0	38	0.5863	0.9474
No log	20.0	40	0.5561	0.9474
No log	21.0	42	0.5284	0.9474
No log	22.0	44	0.5049	0.9474
No log	23.0	46	0.4834	0.9474
No log	24.0	48	0.4601	0.9474
No log	25.0	50	0.4384	0.9474
No log	26.0	52	0.4260	0.9474
No log	27.0	54	0.4083	0.9474
No log	28.0	56	0.3979	0.9474
No log	29.0	58	0.3931	0.9474
No log	30.0	60	0.3852	0.9474

Framework versions

Transformers 4.57.3
Pytorch 2.9.0+cu126
Datasets 4.0.0
Tokenizers 0.22.1

Task: Audio Classification
Library: transformers
Type: wav2vec2
Created: Dec 10, 2025
Updated: Dec 10, 2025