AI Agent Skills

VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech

All-in-one training for vision models (YOLO, ViTs, RT-DETR, DINOv3): pretraining, fine-tuning, distillation.

Pytorch implementation of "EdgeCrafter: Compact ViTs for Edge Dense Prediction via Task-Specialized Distillation"