metadata
library_name: transformers
base_model: Kkonjeong/wav2vec2-base-korean
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: audio_cls
results: []
audio_cls
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: 0.4659
- Accuracy: 0.8992
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Use OptimizerNames.ADAMW_TORCH 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 |
|---|---|---|---|---|
| 2.6218 | 1.0 | 60 | 2.6014 | 0.1261 |
| 2.2243 | 2.0 | 120 | 2.1842 | 0.2857 |
| 1.7892 | 3.0 | 180 | 1.7467 | 0.5126 |
| 1.0666 | 4.0 | 240 | 1.2378 | 0.7143 |
| 0.8213 | 5.0 | 300 | 0.9638 | 0.7479 |
| 0.4477 | 6.0 | 360 | 0.9652 | 0.7731 |
| 0.2323 | 7.0 | 420 | 0.6221 | 0.8824 |
| 0.1026 | 8.0 | 480 | 0.5741 | 0.8487 |
| 0.0944 | 9.0 | 540 | 0.4625 | 0.8992 |
| 0.057 | 10.0 | 600 | 0.4659 | 0.8992 |
Framework versions
- Transformers 4.56.0
- Pytorch 2.5.1+cu121
- Datasets 3.6.0
- Tokenizers 0.22.0