metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- common_voice_8_0
model-index:
- name: xls-r_cv_ur
results: []
xls-r_cv_ur
This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the common_voice_8_0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.8811
- Wer: 0.5107
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 |
|---|---|---|---|---|
| 6.9256 | 5.68 | 1000 | 2.9843 | 1.0 |
| 1.4949 | 11.36 | 2000 | 0.9451 | 0.6099 |
| 0.6673 | 17.05 | 3000 | 0.8527 | 0.5463 |
| 0.4739 | 22.73 | 4000 | 0.8677 | 0.5215 |
| 0.399 | 28.41 | 5000 | 0.8811 | 0.5107 |
Framework versions
- Transformers 4.21.0
- Pytorch 1.11.0+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1