# High Accuracy Model

Image classification model based on Swin Transformer Tiny architecture, fine-tuned for 50 epochs on a custom dataset with 79.73% accuracy

This model is an image classification model fine-tuned on the sudo-s/herbier_mesuem5 dataset based on google/vit-base-patch16-224-in21k, achieving an evaluation accuracy of 83.67%.

This is a Persian speech emotion recognition model based on the Wav2Vec 2.0 architecture, capable of identifying six basic emotional states.