audio_cls_sjs

This model is a fine-tuned version of Kkonjeong/wav2vec2-base-korean on the PolyAI/minds14 dataset. It achieves the following results on the evaluation set:

• Loss: 1.2026
• Accuracy: 0.7311

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	2.6319	0.1008
No log	2.0	30	2.4686	0.2101
No log	3.0	45	2.2363	0.3361
No log	4.0	60	2.0202	0.4286
No log	5.0	75	1.7058	0.5714
No log	6.0	90	1.5203	0.6303
No log	7.0	105	1.4001	0.6471
No log	8.0	120	1.2837	0.6975
No log	9.0	135	1.2277	0.7227
No log	10.0	150	1.2026	0.7311

Framework versions

• Transformers 5.0.0
• Pytorch 2.10.0+cu128
• Datasets 4.0.0
• Tokenizers 0.22.2