Wooseok Han's repositories
End-to-End-TTS-Fine-Tune
Use FastSpeech2 and HiFi-GAN to easily perform end-to-end Korean speech synthesis.
FastSpeech2-Pytorch-Korean-Multi-Speaker
Multi-Speaker FastSpeech2 applicable to Korean. Description about train and synthesize in detail.
hwrg.github.io
Blog
AST-Real-time-Emergency-Classification
Real-time Audio Classification (with Emergency situation)
BAEKJOON_Record
Recorded BAEKJOON problem by rank
CATCHTHINGs
This project is a game written in Python. I used web crawling and socket programming. Think of it as a catch mind using photos.
Classification_voices_past_presidents
A project that converts the voice files of old Korean presidents and deep-learns them to recognize their voices.
Expressive-FastSpeech2
PyTorch Implementation of Non-autoregressive Expressive (emotional, conversational) TTS based on FastSpeech2, supporting English, Korean, and your own languages.
HiFi-GAN-Pytorch
If you have a wav & transcript, can train HiFi-GAN right now.
Python_Practice
Practice essential libraries such as matplotlib or numpy, and lacking classes.
Samsung_Card_Contest_2021
It is Samsung Card's second Data Analytic contest, which predict multi categories of customer reviews.
Speech_Synthesis_Code_Study
Review and study Speech Synthesis codes
Speech_Synthesis_Practice
Practices speech synthesis
StyleSpeech
PyTorch Implementation of Meta-StyleSpeech : Multi-Speaker Adaptive Text-to-Speech Generation
Tacotron-Wavenet-Vocoder-Korean
Tacotron, Korean, Wavenet-Vocoder, Korean TTS
Tensorflow_Practice
Learn TensorFlow to try out the voice processing techniques