audio_cls_1016

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: 1.2876
• Accuracy: 0.8487

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	2.6517	0.0756
No log	2.0	30	2.6327	0.1008
No log	3.0	45	2.4684	0.1933
No log	4.0	60	2.2010	0.3613
No log	5.0	75	1.9770	0.5042
No log	6.0	90	1.7075	0.6807
No log	7.0	105	1.5189	0.7563
No log	8.0	120	1.4073	0.7815
No log	9.0	135	1.3144	0.8151
No log	10.0	150	1.2876	0.8487

Framework versions

• Transformers 5.18.0
• Pytorch 2.11.0+cu130
• Datasets 4.8.5
• Tokenizers 0.23.2