audio_cls_y

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: 1.4991
• Accuracy: 0.7563

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	2.6575	0.0756
No log	2.0	30	2.6032	0.1429
No log	3.0	45	2.4576	0.2017
No log	4.0	60	2.2656	0.3193
No log	5.0	75	2.0846	0.4286
No log	6.0	90	1.8924	0.6218
No log	7.0	105	1.7370	0.6807
No log	8.0	120	1.6546	0.7143
No log	9.0	135	1.5345	0.7647
No log	10.0	150	1.4991	0.7563

Framework versions

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