pytorch implementation of DNN-HSMM for TTS

Large, modern dataset for speech recognition

Crystal - C++ implementation of a unified framework for multilingual TTS synthesis engine with SSML specification as interface.

Low-precision matrix multiplication

FSA/FST algorithms, differentiable, with PyTorch compatibility.

A Pytorch Implementation of Natural Gradient Descent

PyTorch implementation of LF-MMI for End-to-end ASR

Python Kaldi speech recognition with grammars that can be set active/inactive dynamically at decode-time

Deezer source separation library including pretrained models.

Espresso: A Fast End-to-End Neural Speech Recognition Toolkit

MTuner is a C/C++ memory profiler and memory leak finder for Windows, PlayStation 3/4/5, Nintendo Switch, Android and other platforms

WebSocket, gRPC and WebRTC speech recognition server based on Vosk and Kaldi libraries

This is the library for the Unbounded Interleaved-State Recurrent Neural Network (UIS-RNN) algorithm, corresponding to the paper Fully Supervised Speaker Diarization.

GStreamer plugin around Kaldi's online neural network decoder

High-performance, scalable time-series database designed for Industrial IoT (IIoT) scenarios

Python server for communicating with Kaldi from the browser using WebRTC

Attempt at tracking states of the arts and recent results (bibliography) on speech recognition.

A small Javascript library for browser-based real-time speech recognition, which uses Recorderjs for audio capture, and a WebSocket connection to the Kaldi GStreamer server for speech recognition.

Fork of the official kaldi.

Python IDE for signal/image processing. (The perfect IDE for switching from MATLAB to Python)

MagPhase Vocoder: Speech analysis/synthesis system for TTS and related applications.

Code for end-to-end ASR with neural networks, build with TensorFlow

Speech recognition software where the neural net is trained with TensorFlow and GMM training and decoding is done in Kaldi

A listen attend and spell reimplementation in tensorflow, using a custom attention mechanism.

Blind Source Separation for Audio Recognition Tasks

Real-time GCC-NMF Blind Speech Separation and Enhancement

A python package that make tensorflow be able to read "Kaldi" scp/ark in an elegant way. May kaldi user happy to enter tensorflow world.

End-to-End Speech Processing Toolkit

The best way to write secure and reliable applications. Write nothing; deploy nowhere.