<!-- 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-w1
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: 0.1406
- Cer: 0.0393
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: 3
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Cer |
---|---|---|---|---|
24.537 | 0.56 | 800 | 3.0461 | 0.9274 |
1.9309 | 1.13 | 1600 | 0.7723 | 0.2168 |
0.7595 | 1.69 | 2400 | 0.3197 | 0.0916 |
0.4338 | 2.26 | 3200 | 0.2051 | 0.0587 |
0.3067 | 2.82 | 4000 | 0.1406 | 0.0393 |
Framework versions
- Transformers 4.17.0
- Pytorch 1.10.0+cu113
- Datasets 2.6.1
- Tokenizers 0.13.1