Stars
🐻❄️ A Headless, Utility-First, and Zero-Runtime UI Component Library ✨
Utility scripts for preprocessing Wikipedia texts for NLP
Render markdown on the CLI, with pizzazz! 💅🏻
Pytorch implementation and pre-trained Japanese model for CANINE, the efficient character-level transformer.
Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.
📝 A list of pre-trained BERT models for Japanese with word/subword tokenization + vocabulary construction algorithm information
Real-time video and audio processing on Streamlit
Sentence boundary disambiguation tool for Japanese texts (日本語文境界判定器)
Packaged, Pytorch-based, easy to use, cross-platform version of the CRAFT text detector
Ebitengine - A dead simple 2D game engine for Go
A curated list of pretrained sentence and word embedding models
Simple Unsupervised Document Labeling with MeCab and Pretrained Doc2Vec Model and some experiments about `Doc2Vec.infer_vector()`
Unofficial Implementation of Residual Attention Module
🌈 Implementation of Neural Network based Named Entity Recognizer (Lample+, 2016) using Chainer.
A familiar HTTP Service Framework for Python.
A Python implementation of the SimString, a simple and efficient algorithm for approximate string matching.
This is a repository of yohei's lecture pdf of 2018 Cookpad Summer Internship 5 DAY R&D.
A flexible framework of neural networks for deep learning
A tool for learning vector representations of words and entities from Wikipedia
Convert japanese from itaiji(異体字) to seijitai(正字体).