wavlm-finetuned-SAVEE
This model is a fine-tuned version of microsoft/wavlm-base-plus on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.6940
- Accuracy: 0.3542
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: 8
- seed: 42
- gradient_accumulation_steps: 4
- 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 | 1.9312 | 0.2188 |
| No log | 2.0 | 48 | 1.8608 | 0.3125 |
| 7.6509 | 3.0 | 72 | 1.7555 | 0.3333 |
| 7.6509 | 4.0 | 96 | 1.7167 | 0.3333 |
| 6.9743 | 5.0 | 120 | 1.6940 | 0.3542 |
Framework versions
- Transformers 5.12.0
- Pytorch 2.11.0+cu128
- Datasets 5.0.0
- Tokenizers 0.22.2