tybian

transformer_tts

This is an implementation for "Neural Speech Synthesis with Transformer Network".

chineseocr

yolo3+ocr

CPlusPlusThings

C++那些事

CppCoreGuidelines

The C++ Core Guidelines are a set of tried-and-true guidelines, rules, and best practices about coding in C++

DCGAN-tensorflow

A tensorflow implementation of "Deep Convolutional Generative Adversarial Networks"

demucs

Code for the paper Music Source Separation in the Waveform Domain

espnet

End-to-End Speech Processing Toolkit

fairseq

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

faiss

A library for efficient similarity search and clustering of dense vectors.

FastSpeech

The Implementation of FastSpeech based on pytorch.

Fay

Fay是一个完整的开源项目，包含Fay控制器及数字人模型，可灵活组合出不同的应用场景：虚拟主播、现场推销货、商品导购、语音助理、远程语音助理、数字人互动、数字人面试官及心理测评、贾维斯、Her。 开源项目，非产品试用！！！

Guyu

pre-training and fine-tuning framework for text generation

HiddenMarkovModel_TensorFlow

TensorFlow: Viterbi, Forward-Backward and Baum Welch with a Hidden Markov Model (HMM)

jukebox

Code for the paper "Jukebox: A Generative Model for Music"

numpy-ml

Machine learning, in numpy

p5.js-sound

p5.sound brings the Processing approach to Web Audio and p5.js. Demos:

Parselmouth

Praat in Python, the Pythonic way

pianotrans

Simple GUI for ByteDance's Piano Transcription with Pedals

PyMO

A library for machine learning research on motion capture data

python_sound_open

语音信号处理试验教程，Python代码

Realtime_PyAudio_FFT

Realtime audio analysis in Python, using PyAudio and Numpy to extract and visualize FFT features from streaming audio.

rmstZ.github.io

Shenlan-ASR-Course

深蓝学院语音课程《语音识别从入门到精通》课程作业

sms-tools

Sound analysis/synthesis tools for music applications

SongNet

Code for ACL 2020 paper "Rigid Formats Controlled Text Generation"：https://arxiv.org/abs/2004.08022

speech-aligner

speech-aligner，是一个从“人声语音”及其“语言文本”，产生音素级别时间对齐标注的工具。speech-aligner, is a tool that generate phoneme-level alignment between human speech and its transcription

StyleGestures

tybian.github.io

voxceleb_trainer

In defence of metric learning for speaker recognition

waveglow

A Flow-based Generative Network for Speech Synthesis