wav2vec2-large-xls-r-1b-korean-convsen1
This model is a fine-tuned version of facebook/wav2vec2-xls-r-1b on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0014
- Cer: 0.0002
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
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|---|---|---|---|---|
| 1.3161 | 1.0 | 1762 | 0.1495 | 0.0443 |
| 0.1188 | 2.0 | 3524 | 0.0125 | 0.0033 |
| 0.0399 | 3.0 | 5286 | 0.0014 | 0.0002 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.13.0
- Datasets 2.6.1
- Tokenizers 0.11.0