<!-- 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_zu-run3-asr_xh-run4
This model is a fine-tuned version of lucas-meyer/xls-r-fleurs_zu-run3 on asr_xh. It achieves the following results on the evaluation set:
- Val WER: 0.5400
- Test WER: 0.5518
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0003
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 3
- total_train_batch_size: 12
- 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 |
|---|---|---|---|---|
| 3.7015 | 1.91 | 400 | 0.5528 | 0.7130 |
| 0.4744 | 3.83 | 800 | 0.3950 | 0.5397 |
| 0.2915 | 5.74 | 1200 | 0.4024 | 0.5549 |
| 0.2068 | 7.66 | 1600 | 0.4202 | 0.4947 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu117
- Datasets 2.14.4
- Tokenizers 0.13.3
