wav2vec2-xls-r-300m-deepfake-V1
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2714
- Accuracy: 0.9449
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: 3e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.0005 | 1.0 | 7173 | 0.2714 | 0.9449 |
| 0.0001 | 2.0 | 14347 | 0.6709 | 0.8833 |
| 0.0003 | 3.0 | 21521 | 1.2249 | 0.8244 |
| 0.0 | 4.0 | 28695 | 0.7259 | 0.8746 |
| 0.0 | 5.0 | 35865 | 1.5079 | 0.8109 |
Framework versions
- Transformers 4.30.0
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.13.3