szcom

rnnlib

RNNLIB is a recurrent neural network library for sequence learning problems. Forked from Alex Graves work http://sourceforge.net/projects/rnnl/

samplernn

nips2015_vrnn

caffe

Caffe

curlendpoint

Kurento Media Server Module to stream raw audio over HTTP POST

crikey

Research experiments

iwae

Code to train Importance Weighted Autoencoders on MNIST and OMNIGLOT

kafka

Mirror of Apache Kafka

kms-core

Core library of Kurento Media Server

libnice

mimic2

Text to Speech engine based on the Tacotron architecture, initially implemented by Keith Ito. Few minor changes on model architecture, and speech synthesizing

rtpengine

The Sipwise media proxy for Kamailio

sipp

The SIPp testing tool

speaker

speech-to-text-nodejs

:microphone: Sample Node.js Application for the IBM Watson Speech to Text Service

speech_recognition

Speech recognition module for Python, supporting Google Speech Recognition, Wit.ai, IBM Speech to Text, and AT&T Speech to Text.

tacotron_pytorch

PyTorch implementation of Tacotron speech synthesis model.

ws

`ws`: The fastest RFC-6455 WebSocket implementation for Node.js.