Zhengxi Liu (刘正曦)

FastSpeech. The Implementation of FastSpeech based on pytorch.

FastVocoder. Include Basis-MelGAN, MelGAN, HifiGAN and Multiband-HifiGAN, maybe NHV in the future.

Transformer-TTS. TTS model based on Transformer.

FastSpeech2. The Implementation of FastSpeech2 Based on Pytorch.

ConvTasNet4BasisMelGAN. This repo contains conv-tasnet for basis-melgan. If you want to get code of basis-melgan, please refer to FastVocoder.

CLONE.

Tacotron2-Pytorch. follow NVIDIA, simplify it and support data parallel.

Lifelong-Learning-Tacotron2. MultiSpeaker Tacotron2 using LifeLong Learning.

tacotron2.xcmyz. new version of tacotron2 (old version: https://github.com/xcmyz/Tacotron2-Pytorch)

Hackathon-EnglishLearning. Voice Scoring System.

LM-Tacotron2. Tacotron2 Combine with Language Model (BERT).

SpeakerVerification. Speaker Verification (GE2E Loss)

Gobang-AI. A C++ Implementation of Gobang AI.

Speech-Resources. 语音方向实验室/公司/资源/实习等，欢迎推荐或自荐（排名不分先后）

Forced-Alignment. using montreal-forced-aligner.

bert-race. BERT/ALBERT based model for RACE dataset, support multi-worker, multi-GPU, FP16 and bind CPU.

AVX-programming. CPU acceleration using AVX (Advanced Vector Extensions)

xcmyz.

ExpressionTransformation. prefix expression, infix expression, postfix expression.

diffwave. DiffWave is a fast, high-quality neural vocoder and waveform synthesizer.

Large-Audio-Models. Keep track of big models in audio domain, including speech, singing, music etc.

Calculator. A Calculator implemented in Python.

VAE-Tacotron. A Pytorch Implementation of Tacotron Combined with VAE

FaceDetection. Python

Polynomial-Calculator. 基于Python实现的带有图形界面的多项式计算器