flyw
Follow
Stars
MFCC-based LipSync plug-in for Unity using Job System and Burst Compiler
Rhubarb Lip Sync is a command-line tool that automatically creates 2D mouth animation from voice recordings. You can use it for characters in computer games, in animated cartoons, or in any other p…
Share a single keyboard and mouse between multiple computers.
Phoneme Recognition using pre-trained models Wav2vec2, HuBERT and WavLM. Throughout this project, we compared specifically three different self-supervised models, Wav2vec (2019, 2020), HuBERT (2021…
speech enhancement\speech seperation\sound source localization
ncnn is a high-performance neural network inference framework optimized for the mobile platform
A Python application that does noise cancellation
整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。
A sample project to demonstrate how to build a .wav file with raw pcm sound from microphone of android device
Robust realtime face and facial landmark tracking on CPU with Unity integration
Code for "Audio-driven Talking Face Video Generation with Learning-based Personalized Head Pose" (Arxiv 2020) and "Predicting Personalized Head Movement From Short Video and Speech Signal" (TMM 2022)
I recorded the process of learning about Kubernetes over there
A single-file library for working with Apple Live Photos
内网穿透，c++实现，无需公网IP，小巧，易用，快速，安全，最好的多链路聚合（p2p+proxy）模式，不做之一...这才是你真正想要的内网穿透工具！
Pixano App is a web-based smart-annotation tool for computer vision applications.
Experience macOS just like before
Client and server applications to perform inter-process communication. AIDL, Messenger and Broadcast performed in one app.
Annotation processing library for type-safe Jetpack Compose navigation with no boilerplate.
Image Polygonal Annotation with Python (polygon, rectangle, circle, line, point and image-level flag annotation).
This will identify images of cats and dogs, given the network is trained with appropriate datasets.