metadata
library_name: transformers
base_model: Kkonjeong/wav2vec2-base-korean
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: audio_cls2
results: []
audio_cls2
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: 1.9947
- Accuracy: 0.1538
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: 3e-05
- 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 | 2 | 1.9488 | 0.4615 |
| No log | 2.0 | 4 | 1.9549 | 0.0769 |
| No log | 3.0 | 6 | 1.9348 | 0.1538 |
| No log | 4.0 | 8 | 1.9568 | 0.1538 |
| No log | 5.0 | 10 | 1.9823 | 0.0 |
| No log | 6.0 | 12 | 1.9865 | 0.1538 |
| No log | 7.0 | 14 | 1.9931 | 0.1538 |
| No log | 8.0 | 16 | 1.9951 | 0.1538 |
| No log | 9.0 | 18 | 1.9933 | 0.1538 |
| No log | 10.0 | 20 | 1.9947 | 0.1538 |
Framework versions
- Transformers 5.10.2
- Pytorch 2.12.0+cu130
- Datasets 4.8.5
- Tokenizers 0.22.2