<!-- 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. -->
Model_G_S_Berita_Wav2Vec2_Version2
This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4915
- Wer: 0.4678
- Cer: 0.0902
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: 0.0003
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 30
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|---|---|---|---|---|---|
| 0.3249 | 13.79 | 400 | 0.4083 | 0.4049 | 0.0769 |
| 0.0209 | 27.59 | 800 | 0.4915 | 0.4678 | 0.0902 |
Framework versions
- Transformers 4.11.3
- Pytorch 1.10.0+cu113
- Datasets 1.18.3
- Tokenizers 0.10.3
