wav2vec2-large-xls-r-1b-wolof-VoiceToText
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3951
- Wer: 0.3838
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: 32
- 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: 500
- num_epochs: 30
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 3.2047 | 14.29 | 400 | 0.4485 | 0.4602 |
| 0.1987 | 28.57 | 800 | 0.3951 | 0.3838 |
Framework versions
- Transformers 4.27.1
- Pytorch 1.10.0+cu113
- Datasets 1.18.3
- Tokenizers 0.13.2