metadata
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: XLS-R_53_english
results: []
XLS-R_53_english
This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.8306
- Wer: 0.6991
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: 0.0001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- num_epochs: 30
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 6.1059 | 5.56 | 250 | 3.2801 | 1.0 |
| 3.0169 | 11.11 | 500 | 3.1509 | 1.0 |
| 2.9173 | 16.67 | 750 | 2.8107 | 1.0 |
| 2.1179 | 22.22 | 1000 | 1.1816 | 0.8956 |
| 1.0037 | 27.78 | 1250 | 0.8306 | 0.6991 |
Framework versions
- Transformers 4.17.0
- Pytorch 1.12.1+cu113
- Datasets 1.18.3
- Tokenizers 0.12.1