---
library_name: transformers
base_model: Kkonjeong/wav2vec2-base-korean
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: audio_cls
  results: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# audio_cls

This model is a fine-tuned version of [Kkonjeong/wav2vec2-base-korean](https://huggingface.co/Kkonjeong/wav2vec2-base-korean) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.0437
- 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   | 2.6055          | 0.1345   |
| No log        | 2.0   | 30   | 2.3881          | 0.2605   |
| No log        | 3.0   | 45   | 2.0457          | 0.4538   |
| No log        | 4.0   | 60   | 1.7823          | 0.6050   |
| No log        | 5.0   | 75   | 1.5679          | 0.6891   |
| No log        | 6.0   | 90   | 1.3787          | 0.7479   |
| No log        | 7.0   | 105  | 1.2303          | 0.7731   |
| No log        | 8.0   | 120  | 1.1281          | 0.8151   |
| No log        | 9.0   | 135  | 1.0650          | 0.8067   |
| No log        | 10.0  | 150  | 1.0437          | 0.8067   |


### Framework versions

- Transformers 4.57.3
- Pytorch 2.9.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.1