audio_cls_hhd – AI Model by chzzk | AlphaNeural AI

You can deploy this model and start earning money today!

chzzk/
audio_cls_hhd

like

0

audio-classification

generated_from_trainer

Kkonjeong/wav2vec2-base-korean

endpoints_compatible

Views

No views yet

audio_cls_hhd

This model is a fine-tuned version of Kkonjeong/wav2vec2-base-korean on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.5459
Accuracy: 0.8739

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: 10
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	15	1.5112	0.6639
No log	2.0	30	1.2246	0.7227
No log	3.0	45	0.9912	0.7731
No log	4.0	60	0.8545	0.8067
No log	5.0	75	0.7632	0.8151
No log	6.0	90	0.6890	0.8151
No log	7.0	105	0.6332	0.8403
No log	8.0	120	0.5748	0.8739
No log	9.0	135	0.5591	0.8739
No log	10.0	150	0.5459	0.8739

Framework versions

Transformers 4.57.1
Pytorch 2.8.0+cu126
Datasets 3.6.0
Tokenizers 0.22.1