<!-- 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. -->
xls-r-300m-loz
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6844
- Wer: 0.3611
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: 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 |
---|---|---|---|---|
2.9569 | 4.31 | 500 | 0.5512 | 0.4857 |
0.3041 | 8.62 | 1000 | 0.4891 | 0.4169 |
0.1532 | 12.93 | 1500 | 0.5876 | 0.3848 |
0.0804 | 17.24 | 2000 | 0.6433 | 0.3765 |
0.0491 | 21.55 | 2500 | 0.6670 | 0.3643 |
0.0336 | 25.86 | 3000 | 0.6844 | 0.3611 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.9.0
- Tokenizers 0.13.2