wav2vec2-finetuned
This model is a fine-tuned version of facebook/wav2vec2-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8726
- Accuracy: 0.6222
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: 1e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.9787 | 0.3333 | 30 | 1.1320 | 0.5667 |
| 0.9434 | 0.6667 | 60 | 1.0071 | 0.5667 |
| 0.9341 | 1.0 | 90 | 0.9410 | 0.5667 |
| 0.9587 | 1.3333 | 120 | 0.9137 | 0.6333 |
| 0.8414 | 1.6667 | 150 | 0.9752 | 0.5 |
| 1.2455 | 2.0 | 180 | 0.8845 | 0.5778 |
| 0.8723 | 2.3333 | 210 | 0.8830 | 0.6333 |
| 0.7279 | 2.6667 | 240 | 0.8724 | 0.6111 |
| 1.3587 | 3.0 | 270 | 0.8726 | 0.6222 |
Framework versions
- Transformers 4.52.3
- Pytorch 2.7.0+cu126
- Datasets 3.6.0
- Tokenizers 0.21.1