<!-- 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. -->
wav2vec2-large-xls-r-300m-korean-g-TW3
This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.9885
- Cer: 0.1503
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 |
|---|---|---|---|---|
| 0.028 | 3.25 | 500 | 1.0176 | 0.1568 |
| 0.0399 | 6.49 | 1000 | 1.0700 | 0.1733 |
| 0.0521 | 9.74 | 1500 | 0.9727 | 0.1645 |
| 0.0427 | 12.99 | 2000 | 1.0005 | 0.1610 |
| 0.0342 | 16.23 | 2500 | 1.0248 | 0.1633 |
| 0.029 | 19.48 | 3000 | 0.9593 | 0.1562 |
| 0.0232 | 22.73 | 3500 | 1.0307 | 0.1534 |
| 0.0196 | 25.97 | 4000 | 0.9930 | 0.1535 |
| 0.017 | 29.22 | 4500 | 0.9885 | 0.1503 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 1.18.3
- Tokenizers 0.13.3
