A TensorFlow Implementation of Tacotron: A Fully End-to-End Text-To-Speech Synthesis Model

Tacotron, Korean, Wavenet-Vocoder, Korean TTS

😝 TensorFlowTTS: Real-Time State-of-the-art Speech Synthesis for Tensorflow 2 (supported including English, French, Korean, Chinese, German and Easy to adapt for other languages)

Pre-Training with Whole Word Masking for Chinese BERT（中文BERT-wwm系列模型）

10W首中文歌词数据库

chatbot based on music region using method including es and music kb.基于14W歌曲知识库的问答尝试，功能包括歌词接龙，已知歌词找歌曲以及歌曲歌手歌词三角关系的问答。

The most comprehensive database of Chinese poetry 🧶最全中华古诗词数据库, 唐宋两朝近一万四千古诗人, 接近5.5万首唐诗加26万宋诗. 两宋时期1564位词人，21050首词。

非常全的古诗词数据，收录了从先秦到现代的共计85万余首古诗词。

中英文敏感词、语言检测、中外手机/电话归属地/运营商查询、名字推断性别、手机号抽取、身份证抽取、邮箱抽取、中日文人名库、中文缩写库、拆字词典、词汇情感值、停用词、反动词表、暴恐词表、繁简体转换、英文模拟中文发音、汪峰歌词生成器、职业名称词库、同义词库、反义词库、否定词库、汽车品牌词库、汽车零件词库、连续英文切割、各种中文词向量、公司名字大全、古诗词库、IT词库、财经词库、成语词库、地名词库、…

Code for the paper "Language Models are Unsupervised Multitask Learners"

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

GPT2 for Multiple Languages, including pretrained models. GPT2 多语言支持, 15亿参数中文预训练模型

A curated list of resources for Learning with Noisy Labels

The official Keras implementation of ACL 2020 paper "Pre-train and Plug-in: Flexible Conditional Text Generation with Variational Auto-Encoders".

Conditional Transformer Language Model for Controllable Generation

此项目是机器学习(Machine Learning)、深度学习(Deep Learning)、NLP面试中常考到的知识点和代码实现，也是作为一个算法工程师必会的理论基础知识。

Tensorflow Implementation of Expressive Tacotron

ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators

Datasets, SOTA results of every fields of Chinese NLP

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

Leetcode解题

Virtual adversarial training with Tensorflow

个人中文简历 Latex 源码 https://hijiangtao.github.io/

A challenge to explore adversarial robustness of neural networks on MNIST.

算法工程师(人工智能CV方向)面试问题及相关资料

Pointer Networks is a new neural architecture to learn the conditional probability of an output sequence with elements that are discrete tokens corresponding to positions in an input sequence.

Language Understanding Evaluation benchmark for Chinese: datasets, baselines, pre-trained models,corpus and leaderboard

Must-read Papers on pre-trained language models.

A library for Multilingual Unsupervised or Supervised word Embeddings

This toolkit was designed for the fast and efficient development of modern machine comprehension models, including both published models and original prototypes.