A unified, comprehensive and efficient recommendation library

This project is the official implementation of our accepted ICLR 2022 paper BiBERT: Accurate Fully Binarized BERT.

Provides Spotify-specific TensorFlow helpers

Set Expander for Any Language

Testing a differnt approach

Festvox voice building tools

⚠️ This project is not maintained anymore! Please go to https://github.com/visjs

Semi-supervised learning frameworks for python, which allow fitting scikit-learn classifiers to partially labeled data

Semi-supervised learning with graph embeddings

Offline Automatic Speech Recognition for Android 2.2+ using Sphinx (specifically PocketSphinx)

Speech recognition in JavaScript and WebAssembly

Port of the Festival-lite (Flite TTS) speech-synthesis engine to Android

Port of the Festival-lite (Flite TTS) speech-synthesis engine to Android