A fast, local neural text to speech system

Android face detect and segmentation,facemesh by ncnn

Speech-to-text, text-to-speech, speaker diarization, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, Raspberry Pi, RISC-V, x86_64 …

Android human segmentation by ncnn

CainCamera is an Android Project to learn about development of beauty camera, image and short video

Android face detection 30+ FPS, pretrained weight 1MB.

EmotiVoice 😊: a Multi-Voice and Prompt-Controlled TTS Engine

The official repo of Qwen2-Audio chat & pretrained large audio language model proposed by Alibaba Cloud.

This work introduces WordArt Designer, a user-driven framework for artistic typography synthesis, relying on Large Language Models (LLM).

Metric depth estimation from a single image

---AWESOME--- C++学习笔记和常见面试知识点，C++11特性，包括智能指针、四种强制转换、function和bind、移动语义、完美转发、tuple、多态原理、虚表、友元函数、符号重载、函数指针、深浅拷贝、struct内存对齐、volatile以及union\static等各种关键字的用法等等

中文的C++ Template的教学指南。与知名书籍C++ Templates不同，该系列教程将C++ Templates作为一门图灵完备的语言来讲授，以求帮助读者对Meta-Programming融会贯通。(正在施工中)

TensorLy: Tensor Learning in Python.

高性能并行编程与优化 - 课件

Lightweight and Parallel Deep Learning Framework

Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.

Awesome Knowledge-Distillation. 分类整理的知识蒸馏paper(2014-2021)。

The Tensor Algebra SuperOptimizer for Deep Learning

Neural Network Compression Framework for enhanced OpenVINO™ inference

source code of the paper: Robust Quantization: One Model to Rule Them All

帮助大家进行FPGA的入门，分享FPGA相关的优秀文章，优秀项目

Image Signal Processor