Starred repositories
Mellea is a library for writing generative programs.
Modernized implementation of GPT-2 (under heavy development, don't expect this to work out of the box!)
A simple, performant, and scalable Jax LLM!
PORORO: Platform Of neuRal mOdels for natuRal language prOcessing
Open Korean NLP Dataset Curation for the Users All Around the Globe
Large scale unannotated Korean corpus for unsupervised tasks. (e.g. Language modeling)
Tantivy is a full-text search engine library inspired by Apache Lucene and written in Rust
Fast audio sample rate conversion with simplified BSD license
A Locality Sensitive Hashing (LSH) library with an emphasis on large, highly-dimensional datasets.
CNN Image Retrieval in MatConvNet: Training and evaluating CNNs for Image Retrieval in MatConvNet
Tensorflow toolbox implementing several learnable pooling architecture
Torch implementation of CVPR'17 - Local Binary Convolutional Neural Networks http://xujuefei.com/lbcnn.html
PyTorch implementation of convolutional neural networks-based text-to-speech synthesis models
A web application for crowdsourcing image annotations.
Lossless data compression codec with LZMA-like ratios but 1.5x-8x faster decompression speed, C/C++
A hands-on introduction to video technology: image, video, codec (av1, vp9, h265) and more (ffmpeg encoding). Translations: 🇺🇸 🇨🇳 🇯🇵 🇮🇹 🇰🇷 🇷🇺 🇧🇷 🇪🇸
Porting of Skip-Thoughts pretrained models from Theano to PyTorch & Torch7
Python implementation of TextRank algorithms ("textgraphs") for phrase extraction
The rich text editor for arbitrary HTML.
Apache ECharts is a powerful, interactive charting and data visualization library for browser
Talkback and Brailleback helpers for Opera Devices SDK for Android based on Chromevox.
Utility to ease bundling libraries into executables for OSX