<!-- 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-thai
This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5719
- Wer: 0.5448
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: 32
- eval_batch_size: 16
- 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: 40
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 6.7862 | 6.58 | 1000 | 1.8716 | 1.0407 |
| 0.8847 | 13.16 | 2000 | 0.5514 | 0.6268 |
| 0.4436 | 19.74 | 3000 | 0.5391 | 0.5887 |
| 0.3235 | 26.32 | 4000 | 0.5472 | 0.5610 |
| 0.2611 | 32.89 | 5000 | 0.5505 | 0.5488 |
| 0.2339 | 39.47 | 6000 | 0.5719 | 0.5448 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2
