wav2vec2-large-xls-r-300m-galician
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the MOZILLA-FOUNDATION/COMMON_VOICE_7_0 - GL dataset. It achieves the following results on the evaluation set:
- Loss: 0.1525
- Wer: 0.1542
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: 7e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 20.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 3.0067 | 4.35 | 500 | 2.9632 | 1.0 |
| 1.4939 | 8.7 | 1000 | 0.5005 | 0.4157 |
| 0.9982 | 13.04 | 1500 | 0.1967 | 0.1857 |
| 0.8726 | 17.39 | 2000 | 0.1587 | 0.1564 |
Framework versions
- Transformers 4.16.0.dev0
- Pytorch 1.10.1+cu102
- Datasets 1.17.1.dev0
- Tokenizers 0.11.0