WAXAL-wal_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: 1.1595
- Cer: 0.2217
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 |
|---|---|---|---|---|
| 3.7991 | 1.6322 | 300 | 1.0322 | 0.2493 |
| 1.1458 | 3.2616 | 600 | 1.0429 | 0.2345 |
| 0.9316 | 4.8937 | 900 | 0.9821 | 0.2269 |
| 0.7695 | 6.5232 | 1200 | 1.1250 | 0.2231 |
| 0.6165 | 8.1526 | 1500 | 1.1479 | 0.2221 |
| 0.4559 | 9.7847 | 1800 | 1.1580 | 0.2219 |
| 0.4559 | 10.0 | 1840 | 1.1595 | 0.2217 |
Framework versions
- Transformers 5.12.1
- Pytorch 2.11.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2