---
library_name: transformers
base_model: Kkonjeong/wav2vec2-base-korean
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: audio_kor
  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_kor

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: 0.3679
- Accuracy: 0.9496

## 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: 2
- total_train_batch_size: 16
- 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
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 2.6342        | 1.0   | 30   | 2.6301          | 0.0588   |
| 2.4757        | 2.0   | 60   | 2.3899          | 0.3109   |
| 1.9266        | 3.0   | 90   | 1.8527          | 0.6134   |
| 1.5614        | 4.0   | 120  | 1.4405          | 0.7227   |
| 0.9955        | 5.0   | 150  | 1.0447          | 0.8655   |
| 0.6666        | 6.0   | 180  | 0.7428          | 0.9076   |
| 0.4623        | 7.0   | 210  | 0.5859          | 0.9160   |
| 0.334         | 8.0   | 240  | 0.4750          | 0.9244   |
| 0.2673        | 9.0   | 270  | 0.3788          | 0.9496   |
| 0.196         | 10.0  | 300  | 0.3679          | 0.9496   |


### Framework versions

- Transformers 4.56.1
- Pytorch 2.8.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.0