wav2vec2-large-xls-r-300m-korean-ws1
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0431
- Cer: 0.0047
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: 4
- 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: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|---|---|---|---|---|
| 1.8176 | 1.0 | 4451 | 0.7022 | 0.2494 |
| 0.3505 | 2.0 | 8902 | 0.1369 | 0.0303 |
| 0.1696 | 3.0 | 13353 | 0.0431 | 0.0047 |
Framework versions
- Transformers 4.17.0
- Pytorch 1.10.0+cu113
- Datasets 2.6.1
- Tokenizers 0.13.1