metadata
tags:
- generated_from_trainer
model-index:
- name: Model_G_S_P_Wav2Vec2
results: []
Model_G_S_P_Wav2Vec2
This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.4856
- Wer: 0.5755
- Cer: 0.2446
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 |
|---|---|---|---|---|---|
| 1.0588 | 4.17 | 400 | 1.7492 | 0.6409 | 0.2597 |
| 0.5411 | 8.33 | 800 | 2.0539 | 0.6467 | 0.2779 |
| 0.403 | 12.5 | 1200 | 2.0300 | 0.6500 | 0.2674 |
| 0.2896 | 16.67 | 1600 | 2.0923 | 0.6024 | 0.2544 |
| 0.2176 | 20.83 | 2000 | 2.1371 | 0.5763 | 0.2449 |
| 0.1557 | 25.0 | 2400 | 2.3540 | 0.5906 | 0.2505 |
| 0.1089 | 29.17 | 2800 | 2.4856 | 0.5755 | 0.2446 |
Framework versions
- Transformers 4.11.3
- Pytorch 1.10.0+cu113
- Datasets 1.18.3
- Tokenizers 0.10.3