qgzang's repositories
awesome-imbalanced-learning
A curated list of awesome imbalanced learning papers, codes, frameworks and libraries. | 类别不平衡学习：论文/代码/框架/库
awesome-semi-supervised-learning
:scroll: A curated list of awesome semi-supervised learning methods & papers.
AwesomeCpp
---AWESOME--- C++学习笔记和常见面试知识点，C++11特性，包括多态、虚表、移动语义、友元函数、符号重载、完美转发、智能指针、const和static、数组指针和指针数组、struct内存对齐、enum和union关键字等等
book-text-to-speech
A book about Text-to-Speech (TTS) in Chinese.
course
高性能并行编程与优化 - 课件
ddsp
DDSP: Differentiable Digital Signal Processing
DeepSpeechRecognition
A Chinese Deep Speech Recognition System 包括基于深度学习的声学模型和基于深度学习的语言模型
DynamicAudioNormalizer
Dynamic Audio Normalizer
epidemic-sentence-pair
天池 疫情相似句对判定大赛 线上第一名方案
fairseq
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
genbmm
CUDA kernels for generalized matrix-multiplication in PyTorch
Guyu
pre-training and fine-tuning framework for text generation
Leetcode
Play Leetcode with different Programming language
machine-learning-reference
常见的机器学习参考资料，包括书籍、公开课等
masr
中文语音识别，高识别率预训练模型，支持docker快速安装 Chinese Speech Recognition; Mandarin Automatic Speech Recognition;
ml-system-design-pattern
System design patterns for machine learning
PKD-for-BERT-Model-Compression
pytorch implementation for Patient Knowledge Distillation for BERT Model Compression
PPASR
基于PaddlePaddle2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。
rapidstring
Maybe the fastest string library ever.
sentencepiece
Unsupervised text tokenizer for Neural Network-based text generation.
shanghai_house_knowledge
2020年11月在上海买房经历总结出来的买房购房做的一些功课分享给大家，技术人帮助技术人，希望对大家有所帮助。启发来自这个兄弟17年做的杭州购房分享https://github.com/houshanren/hangzhou_house_knowledge。
TurboTransformers
a fast and user-friendly tool for transformer inference on CPU and GPU
voicebook
🗣️ A book and repo to get you started programming voice computing applications in Python - 10 chapters and 200+ scripts.
wumei-smart
物美智能是一套开源的软硬件系统，可用于二次开发和学习，快速搭建自己的智能家居系统。硬件工程师可以把自己的设备集成到系统；软件工程师可以使用项目中的设备熟悉软硬件交互。
zhvoice
Chinese voice corpus. 中文语音语料，语音更加清晰自然，包含8个开源数据集，3200个说话人，900小时语音，1300万字。