Control your media player with your face. Dataset creation, training, model selection and inference.
MPL-2.0 License
Real time python demonstrations for machine learning, image and signal processing
语音感情识别
Physionet 2020 challenge
Easiest way of fine-tuning HuggingFace video classification models
http://www.facegood.cc
AeCC: Autoencoders for Compressed Communication
Code and dataset for photorealistic Codec Avatars driven from audio
This repo contains, training material, dlib implementation, tensorflow implementation and an own ...
Skyhawk is a CLI tool that can run on any device with a camera to recognize faces. It is Built us...
Objective of this repo is to explain training process for tf2 and various state-of-the-art object...
Generative models for conditional audio generation
Audio super resolution using neural networks
Human-detection-and-Tracking
Audio Classification using Image Classification
Pytorch implementation of CS-Tacotron, a code-switching speech synthesis end-to-end generative TT...