wav2vec2-xls-r-300m-nyanja-test_v2
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: inf
- Wer: 0.3734
- Cer: 0.0827
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: 0.001
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 400
- num_epochs: 15
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|---|---|---|---|---|---|
| 1.5816 | 0.62 | 400 | inf | 0.5702 | 0.1373 |
| 0.6341 | 1.24 | 800 | inf | 0.4383 | 0.1022 |
| 0.5103 | 1.86 | 1200 | inf | 0.3782 | 0.0895 |
| 0.4553 | 2.48 | 1600 | inf | 0.3734 | 0.0827 |
Framework versions
- Transformers 4.17.0
- Pytorch 1.12.1+cu113
- Datasets 1.18.3
- Tokenizers 0.13.2