zhishenyang's Projects
Evaluation on video-guided machine translation dataset (VATEX)
A very simple framework for state-of-the-art Natural Language Processing (NLP)
MediaPipe is the simplest way for researchers and developers to build world-class ML solutions and applications for mobile, edge, cloud and the web.
A modular framework for vision & language multimodal research from Facebook AI Research (FAIR)
Multi-modal Neural Machine Translation in PyTorch
NLPδΈζζη¨
Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and deployment among server, mobile, embedded and IoT devices)
ππ―pySBD (Python Sentence Boundary Disambiguation) is a rule-based sentence boundary detection that works out-of-the-box.
SemEval 2020 task 10 datasets
Fast and customizable text tokenization library
Code for Transform and Tell paper in CVPR 2020.
Automatically exported from code.google.com/p/tstools
PyTorch tutorials.
Config files for my GitHub profile.