<!-- 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-convsen2
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: 0.0094
- Cer: 0.0012
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 |
---|---|---|---|---|
4.8421 | 1.0 | 1762 | 0.2383 | 0.0591 |
0.1721 | 2.0 | 3524 | 0.0309 | 0.0060 |
0.065 | 3.0 | 5286 | 0.0094 | 0.0012 |
Framework versions
- Transformers 4.17.0
- Pytorch 1.10.0+cu113
- Datasets 2.6.1
- Tokenizers 0.13.1