wav2vec-base-finetuned-SAVEE
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: 1.1859
- Accuracy: 0.5938
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- 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: 0.1
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 24 | 1.6243 | 0.3438 |
| No log | 2.0 | 48 | 1.4583 | 0.5 |
| 3.2176 | 3.0 | 72 | 1.3260 | 0.5 |
| 3.2176 | 4.0 | 96 | 1.2205 | 0.5625 |
| 2.4834 | 5.0 | 120 | 1.1859 | 0.5938 |
Framework versions
- Transformers 5.0.0
- Pytorch 2.11.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2