<!-- 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. -->
seq-xls-r-fleurs_nl-run2-asr_af-run6
This model is a fine-tuned version of lucas-meyer/xls-r-fleurs_nl-run2 on asr_af. It achieves the following results:
- Val WER: 0.3517
- Test WER: 0.3749
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0003
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- 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 (Train) |
|---|---|---|---|---|
| 7.4776 | 0.59 | 100 | 3.2848 | 1.0 |
| 3.0414 | 1.17 | 200 | 2.9526 | 0.9998 |
| 2.4266 | 1.76 | 300 | 1.4622 | 0.9233 |
| 0.9817 | 2.35 | 400 | 0.6617 | 0.5501 |
| 0.6079 | 2.93 | 500 | 0.5610 | 0.4919 |
| 0.442 | 3.52 | 600 | 0.4928 | 0.4326 |
| 0.3558 | 4.11 | 700 | 0.4437 | 0.3960 |
| 0.274 | 4.69 | 800 | 0.4604 | 0.3875 |
| 0.2558 | 5.28 | 900 | 0.4671 | 0.3984 |
| 0.2169 | 5.87 | 1000 | 0.3875 | 0.3520 |
| 0.1769 | 6.45 | 1100 | 0.4117 | 0.3546 |
| 0.1724 | 7.04 | 1200 | 0.4498 | 0.3583 |
| 0.1455 | 7.62 | 1300 | 0.4170 | 0.3475 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu117
- Datasets 2.14.4
- Tokenizers 0.13.3
