audio_cls1

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: 2.0155
• Accuracy: 0.5294

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: 3e-05
• 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	2.6457	0.0924
No log	2.0	30	2.5973	0.1345
No log	3.0	45	2.5226	0.2437
No log	4.0	60	2.4096	0.2773
No log	5.0	75	2.2868	0.3613
No log	6.0	90	2.1899	0.4202
No log	7.0	105	2.1210	0.4454
No log	8.0	120	2.0562	0.4538
No log	9.0	135	2.0252	0.5126
No log	10.0	150	2.0155	0.5294

Framework versions

• Transformers 5.0.0
• Pytorch 2.11.0+cu128
• Datasets 4.0.0
• Tokenizers 0.22.2