audio_cls_hdd

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: 0.8363
• Accuracy: 0.9076

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	2.6492	0.0588
No log	2.0	30	2.4870	0.2857
No log	3.0	45	2.2720	0.3697
No log	4.0	60	1.8467	0.5882
No log	5.0	75	1.5571	0.7059
No log	6.0	90	1.2705	0.7899
No log	7.0	105	1.0683	0.8571
No log	8.0	120	0.9566	0.8824
No log	9.0	135	0.8593	0.9160
No log	10.0	150	0.8363	0.9076

Framework versions

• Transformers 4.56.1
• Pytorch 2.8.0+cu126
• Datasets 4.0.0
• Tokenizers 0.22.0