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: 1.0793
• Accuracy: 0.8403

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	2.6630	0.0420
No log	2.0	30	2.4615	0.2101
No log	3.0	45	2.3445	0.2269
No log	4.0	60	2.1374	0.4202
No log	5.0	75	1.8770	0.4286
No log	6.0	90	1.5967	0.6723
No log	7.0	105	1.3563	0.7311
No log	8.0	120	1.1919	0.8487
No log	9.0	135	1.1172	0.8487
No log	10.0	150	1.0793	0.8403

Framework versions

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