Jaehyeon Kim

vits. VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech

glow-tts. A Generative Flow for Text-to-Speech via Monotonic Alignment Search

MelGAN-Pytorch. A Pytorch Implementation of MelGAN

waveglow-vqvae. WaveGlow vocoder with VQVAE

linear-transformer-for-table-recognition. code for participation in ICDAR2021 Table Recognition track (Team Name: LTIAYN = Kaen Context)

Vector-Quantized-Autoencoders. Tensorflow Implementation of "Theory and Experiments on Vector Quantized Autoencoders"

Transformer-variations. "Variations of Transformer" running on Tensor2Tensor library

rl-atari-skiing. Solve Skiing-v0 by Using Deep Reinforcement Learning

Attention-Mechanisms. Implementations of attention mechanisms

deep-learning-studies. 2017 spring

Maths-for-ML. A Storage of mathematical proofs and models

Byte-Pair-Encoding. Byte Pair Encoding Implementation

jaywalnut310.github.io. https://jaywalnut310.github.io/

vits-demo. VITS Demo (Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech)

glow-tts-demo. Glow-TTS Demo