waaaaabh
This model is a fine-tuned version of Hyuk/wav2vec2-korean-v2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.2211
- Cer: 0.2478
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
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- num_epochs: 30
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|---|---|---|---|---|
| 20.3296 | 3.25 | 500 | 3.1922 | 0.9414 |
| 2.8739 | 6.49 | 1000 | 3.1014 | 0.7727 |
| 2.1991 | 9.74 | 1500 | 2.9818 | 0.6527 |
| 1.025 | 12.99 | 2000 | 1.1202 | 0.2879 |
| 0.2377 | 16.23 | 2500 | 1.2061 | 0.2660 |
| 0.1402 | 19.48 | 3000 | 1.2518 | 0.2629 |
| 0.1144 | 22.73 | 3500 | 1.2232 | 0.2553 |
| 0.0985 | 25.97 | 4000 | 1.2062 | 0.2478 |
| 0.0886 | 29.22 | 4500 | 1.2211 | 0.2478 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.0
- Tokenizers 0.13.3
- Downloads last month
- 3