feizi

alignment-handbook

Robust recipes for to align language models with human and AI preferences

asteroid

The PyTorch-based audio source separation toolkit for researchers || Pretrained models available

Audiomer-PyTorch

A Convolutional Transformer for Keyword Spotting

Datadriven-GPVAD

The codebase for Data-driven general-purpose voice activity detection.

deepvac

PyTorch Project Specification.

edge-tts

Microsoft Edge's TTS

esp-box

The ESP-BOX is a new generation AIoT development platform released by Espressif Systems.

esp-idf

Espressif IoT Development Framework. Official development framework for ESP32.

esp-skainet

Espressif intelligent voice assistant

feizi.github.io

flatcc

FlatBuffers Compiler and Library in C for C

flite

A small fast portable speech synthesis system

gcc-nmf

Real-time GCC-NMF Blind Speech Separation and Enhancement

huxpro.github.io

My Blog / Jekyll Themes / PWA

iSTFTNet-pytorch

iSTFTNet : Fast and Lightweight Mel-spectrogram Vocoder Incorporating Inverse Short-time Fourier Transform

kaldi

This is the official location of the Kaldi project.

NATSpeech

A Non-Autoregressive Text-to-Speech (NAR-TTS) framework, including official PyTorch implementation of PortaSpeech (NeurIPS 2021) and DiffSpeech (AAAI 2022)

pb_chime5

Speech enhancement system for the CHiME-5 dinner party scenario

porcupine

On-device wake word detection powered by deep learning.

py-vox-recorder

Python based sound-activated audio recorder (Wx Python)

pytorch-kaldi

pytorch-kaldi is a project for developing state-of-the-art DNN/RNN hybrid speech recognition systems. The DNN part is managed by pytorch, while feature extraction, label computation, and decoding are performed with the kaldi toolkit.

README

README文件语法解读，即Github Flavored Markdown语法介绍

sound-separation

tensor2tensor

Library of deep learning models and datasets designed to make deep learning more accessible and accelerate ML research.

toolbox-for-speech-signal-processing

A collection of some tools for research on speech signal processing

tortoise-tts

A multi-voice TTS system trained with an emphasis on quality

unified2021

A UNIFIED SPEECH ENHANCEMENT FRONT-END FOR ONLINE DEREVERBERATION, ACOUSTIC ECHO CANCELLATION, AND SOURCE SEPARATION

UnitSpeech

An official implementation of "UnitSpeech: Speaker-adaptive Speech Synthesis with Untranscribed Data"

WavAugment

A library for speech data augmentation in time-domain

wer_are_we

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