wav2vec2-nigerian-lid-v4
This model is a fine-tuned version of drrobot9/wav2vec2-nigerian-language-identifier-v7 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0076
- Accuracy: 0.9989
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: 5e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.0007 | 1.0 | 137 | 0.0087 | 0.9983 |
| 0.0002 | 2.0 | 274 | 0.0171 | 0.9972 |
| 0.0001 | 3.0 | 411 | 0.0106 | 0.9983 |
| 0.0001 | 4.0 | 548 | 0.0078 | 0.9989 |
| 0.0000 | 5.0 | 685 | 0.0076 | 0.9989 |
Framework versions
- Transformers 5.0.0
- Pytorch 2.11.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2
- Downloads last month
- 72
Model tree for drrobot9/wav2vec2-nigerian-language-identifier-v8
Base model
facebook/wav2vec2-large-xlsr-53