WAXAL-orm_asr-w2v-bert-2.0
This model is a fine-tuned version of facebook/w2v-bert-2.0 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8218
- Cer: 0.1687
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: 5e-05
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|---|---|---|---|---|
| 3.9540 | 1.6969 | 300 | 0.9429 | 0.2234 |
| 1.5153 | 3.3909 | 600 | 0.9095 | 0.1915 |
| 1.2455 | 5.0850 | 900 | 0.8163 | 0.1864 |
| 1.0140 | 6.7819 | 1200 | 0.7887 | 0.1747 |
| 0.8312 | 8.4759 | 1500 | 0.8168 | 0.1693 |
| 0.8312 | 10.0 | 1770 | 0.8218 | 0.1687 |
Framework versions
- Transformers 5.12.1
- Pytorch 2.11.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2