metadata
library_name: transformers
base_model: Kkonjeong/wav2vec2-base-korean
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: korean_kws
results: []
korean_kws
This model is a fine-tuned version of Kkonjeong/wav2vec2-base-korean on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.1867
- Accuracy: 0.7857
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 | 1 | 1.5822 | 0.1429 |
| No log | 2.0 | 2 | 1.5822 | 0.1429 |
| No log | 3.0 | 3 | 1.5114 | 0.5714 |
| No log | 4.0 | 4 | 1.5114 | 0.5714 |
| No log | 5.0 | 5 | 1.3987 | 0.7857 |
| No log | 6.0 | 6 | 1.3493 | 0.7143 |
| No log | 7.0 | 7 | 1.2831 | 0.7143 |
| No log | 8.0 | 8 | 1.2381 | 0.7857 |
| No log | 9.0 | 9 | 1.2050 | 0.7857 |
| No log | 10.0 | 10 | 1.1867 | 0.7857 |
Framework versions
- Transformers 4.56.1
- Pytorch 2.8.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.0