audio_cls_korean
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: 1.0013
- Accuracy: 0.8739
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 | 2.6275 | 0.1008 |
| No log | 2.0 | 30 | 2.5323 | 0.1176 |
| No log | 3.0 | 45 | 2.3049 | 0.2689 |
| No log | 4.0 | 60 | 1.8939 | 0.5798 |
| No log | 5.0 | 75 | 1.5949 | 0.6723 |
| No log | 6.0 | 90 | 1.3794 | 0.7479 |
| No log | 7.0 | 105 | 1.2348 | 0.8067 |
| No log | 8.0 | 120 | 1.1050 | 0.8235 |
| No log | 9.0 | 135 | 1.0384 | 0.8487 |
| No log | 10.0 | 150 | 1.0013 | 0.8739 |
Framework versions
- Transformers 5.15.0
- Pytorch 2.11.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2