|
|
--- |
|
|
library_name: transformers |
|
|
base_model: Kkonjeong/wav2vec2-base-korean |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- accuracy |
|
|
model-index: |
|
|
- name: kws |
|
|
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. --> |
|
|
|
|
|
# kws |
|
|
|
|
|
This model is a fine-tuned version of [Kkonjeong/wav2vec2-base-korean](https://huggingface.co/Kkonjeong/wav2vec2-base-korean) on the None dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.4170 |
|
|
- Accuracy: 0.9474 |
|
|
|
|
|
## 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: 30 |
|
|
- mixed_precision_training: Native AMP |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
|
| No log | 1.0 | 2 | 1.8732 | 0.3158 | |
|
|
| No log | 2.0 | 4 | 1.9113 | 0.2105 | |
|
|
| No log | 3.0 | 6 | 1.7446 | 0.4737 | |
|
|
| No log | 4.0 | 8 | 1.6420 | 0.7895 | |
|
|
| No log | 5.0 | 10 | 1.5209 | 0.6842 | |
|
|
| No log | 6.0 | 12 | 1.4078 | 0.6842 | |
|
|
| No log | 7.0 | 14 | 1.3386 | 0.7895 | |
|
|
| No log | 8.0 | 16 | 1.2170 | 0.7895 | |
|
|
| No log | 9.0 | 18 | 1.1401 | 0.9474 | |
|
|
| No log | 10.0 | 20 | 1.0615 | 0.8947 | |
|
|
| No log | 11.0 | 22 | 1.0216 | 0.8947 | |
|
|
| No log | 12.0 | 24 | 1.0372 | 0.7895 | |
|
|
| No log | 13.0 | 26 | 0.9032 | 0.9474 | |
|
|
| No log | 14.0 | 28 | 0.8303 | 0.9474 | |
|
|
| No log | 15.0 | 30 | 0.7810 | 0.9474 | |
|
|
| No log | 16.0 | 32 | 0.7487 | 0.9474 | |
|
|
| No log | 17.0 | 34 | 0.6966 | 0.9474 | |
|
|
| No log | 18.0 | 36 | 0.6569 | 0.9474 | |
|
|
| No log | 19.0 | 38 | 0.6278 | 0.9474 | |
|
|
| No log | 20.0 | 40 | 0.5570 | 0.9474 | |
|
|
| No log | 21.0 | 42 | 0.5196 | 0.9474 | |
|
|
| No log | 22.0 | 44 | 0.5068 | 0.9474 | |
|
|
| No log | 23.0 | 46 | 0.5700 | 0.9474 | |
|
|
| No log | 24.0 | 48 | 0.5661 | 0.9474 | |
|
|
| No log | 25.0 | 50 | 0.5427 | 0.9474 | |
|
|
| No log | 26.0 | 52 | 0.4936 | 0.9474 | |
|
|
| No log | 27.0 | 54 | 0.4339 | 0.9474 | |
|
|
| No log | 28.0 | 56 | 0.4257 | 0.9474 | |
|
|
| No log | 29.0 | 58 | 0.4186 | 0.9474 | |
|
|
| No log | 30.0 | 60 | 0.4170 | 0.9474 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.57.3 |
|
|
- Pytorch 2.9.0+cu126 |
|
|
- Datasets 4.0.0 |
|
|
- Tokenizers 0.22.1 |
|
|
|
