Stars
基于PaddlePaddle实现端到端中文语音识别，从入门到实战，超简单的入门案例，超实用的企业项目。支持当前最流行的DeepSpeech2、Conformer、Squeezeformer模型
360 view on ai/ml/dl applications
Clone a voice in 5 seconds to generate arbitrary speech in real-time
🚀Clone a voice in 5 seconds to generate arbitrary speech in real-time
Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translatio…
[CVPR 2022] FaceFormer: Speech-Driven 3D Facial Animation with Transformers
implementation based on "Audio-Driven Facial Animation by Joint End-to-End Learning of Pose and Emotion"
📜 inspired by iscroll, and it supports more features and has a better scroll perfermance
Frontend Workshop from HTML/CSS/JS to TypeScript/React/Redux
🏆 Swiper component for @vuejs
🌎 Large-scale WebGL-powered Geospatial Data Visualization analysis engine.
A Deep Learning Approach for Generalized Speech Animation
Code for our paper "Synthesising 3D Facial Motion from “In-the-Wild” Speech"
포항공과대학교 과제연구 1 -Audio-driven 3D facial animation with BlendShape
📝A simple and elegant markdown editor, available for Linux, macOS and Windows.
papers about Face Detection; Face Alignment; Face Recognition && Face Identification && Face Verification && Face Representation; Face Reconstruction; Face Tracking; Face Super-Resolution && Face D…
Python tools for 3D face: 3DMM, Mesh processing(transform, camera, light, render), 3D face representations.
Live Speech Portraits: Real-Time Photorealistic Talking-Head Animation (SIGGRAPH Asia 2021)
ICASSP 2022: "Text2Video: text-driven talking-head video synthesis with phonetic dictionary".
Mocap Dataset of “Write-a-speaker: Text-based Emotional and Rhythmic Talking-head Generation”
Code for paper 'Audio-Driven Emotional Video Portraits'.
📖 A curated list of resources dedicated to talking face.
ECE 535 - Course Project, Deep Learning Framework
A Python implementation of the paper "Deformation Transfer for Triangle Meshes" with 3D views in the browser.
《剑指Offer》第二版源代码（Clone from: https://github.com/zhedahht/CodingInterviewChinese2）
Generating Talking Face Landmarks from Speech
Code for the paper "End-to-end Learning for 3D Facial Animation from Speech"