<!-- 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-run7
This model is a fine-tuned version of lucas-meyer/xls-r-fleurs_zu-run3 on an asr_xh. It achieves the following results on the evaluation set:
- Val WER: 0.4945
- Test WER: 0.4989
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 |
---|---|---|---|---|
5.4903 | 1.59 | 250 | 0.9489 | 0.7525 |
0.6278 | 3.18 | 500 | 0.4877 | 0.6284 |
0.3831 | 4.78 | 750 | 0.4181 | 0.5640 |
0.2639 | 6.37 | 1000 | 0.3858 | 0.5018 |
0.1961 | 7.96 | 1250 | 0.4228 | 0.4995 |
0.1579 | 9.55 | 1500 | 0.4363 | 0.4998 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu117
- Datasets 2.14.4
- Tokenizers 0.13.3