<!-- 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-1b-korean-convsen5
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: 0.0655
- Cer: 0.0105
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: 4
- 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: 5
Training results
Training Loss | Epoch | Step | Cer | Validation Loss |
---|---|---|---|---|
0.2312 | 1.0 | 1408 | 0.0869 | 0.4450 |
0.109 | 2.0 | 2816 | 0.0789 | 0.4756 |
0.0457 | 3.0 | 4224 | 0.0696 | 0.5013 |
0.0334 | 4.0 | 5632 | 0.0628 | 0.4815 |
0.0222 | 5.0 | 7040 | 0.0655 | 0.0105 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.13.0
- Datasets 2.6.1
- Tokenizers 0.11.0