A browser extension to read medium.com articles for free without membership.

Chinese text normalization for speech processing

(ARCHIVED) Geph (迷霧通) is a modular Internet censorship circumvention system designed specifically to deal with national filtering.

Code and model files for paper: I. Lourentzou et al., Adapting Sequence to Sequence models for Text Normalization in Social Media", ICWSM'19

Transform ML models into a native code (Java, C, Python, Go, JavaScript, Visual Basic, C#, R, PowerShell, PHP, Dart, Haskell, Ruby, F#, Rust) with zero dependencies

pytorch implementation of Attention is all you need

全中文注释.(The loss function of retinanet based on pytorch).(You can use it on one-stage detection task or classifical task, to solve data imbalance influence).用于one-stage目标检测算法,提升检测效果.你也可以在分类任务中使用该损失函…

《现代汉语大词典》字词头

《汉语大字典》字头检索表

A Demo of Mandarin/Chinese TTS frontend

A PyTorch Implementation of Focal Loss.

Train AI models efficiently on medical images using any framework

Anomaly detection related books, papers, videos, and toolboxes

[ICDE'20] ⚖️ A general, efficient ensemble framework for imbalanced classification. | 泛用，高效，鲁棒的类别不平衡学习框架

汉字拼音数据

词语拼音数据

汉字转拼音(pypinyin)

自美智能系统是基于树莓派、Python、HTML5、PHP、微信小程序打造出的一款物联网人工智能系统

SmoothNLP领域词汇示例 - 基于复旦公开新闻资讯库

每天阅读过的论文的简要笔记

一些基本的NLP相关算法

DaCiDian is an open-sourced chinese mandarin lexicon for automatic speech recognition(ASR)

中文语音识别; Mandarin Automatic Speech Recognition;

速度更快、效果更好的中文新词发现

中文人名语料库。人名生成器。中文姓名,姓氏,名字,称呼,日本人名,翻译人名,英文人名。可用于中文分词、人名实体识别。

中文常用停用词表（哈工大停用词表、百度停用词表等）

a simple, clear, clean and efficient non-recursive implementation of AVL tree in C.

”深蓝词库转换“ 一款开源免费的输入法词库转换程序

Chinese stopwords collection

Automatic extraction of relevant features from time series: