audio_cls_sjs

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: 1.0775
• Accuracy: 0.8067

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	2.6291	0.0756
No log	2.0	30	2.4242	0.1849
No log	3.0	45	2.1563	0.2521
No log	4.0	60	1.9319	0.4706
No log	5.0	75	1.7825	0.4790
No log	6.0	90	1.4850	0.6807
No log	7.0	105	1.3075	0.7815
No log	8.0	120	1.1964	0.8151
No log	9.0	135	1.1145	0.8151
No log	10.0	150	1.0775	0.8067

Framework versions

• Transformers 5.15.0
• Pytorch 2.11.0+cu128
• Datasets 4.0.0
• Tokenizers 0.22.2