vit-base-vocalsound

This model is a fine-tuned version of google/vit-base-patch16-224 on VocalSound dataset. It achieves the following results on the evaluation set:

• accuracy: 81.5
• precision (micro): 86.9
• recall (micro): 76.4
• f1 score (micro): 81.3
• f1 score (macro): 81.2

Training and evaluation data

Training: VocalSound training split (#samples = 15570)

Evaluation: VocalSound test split(#samples = 3594)

Training hyperparameters

The following hyperparameters were used during training:

• optimizer: AdamW
  • weight_decay: 0
  • learning_rate: 5e-5
• batch_size: 32
• training_precision: float32

Framework versions

• Transformers 4.27.4
• TensorFlow 2.12.0
• Tokenizers 0.13.3