Seung-won Park's repositories
RandWireNN
Implementation of: "Exploring Randomly Wired Neural Networks for Image Recognition"
ghudegy-chain
Nth commit must have commit hash with N leading zeros - 진짜 구데기컵 2018
awesome-tts-samples
Awesome list of TTS papers with audio samples
awesome-model-cards
Resources related to the model cards for ML
istft-pytorch
Two different PyTorch implementation of Inverse-STFT for discussion at https://github.com/keunwoochoi/torchaudio-contrib/issues/27
can-google-ocr-this
Will these images/videos eventually show up in the google search results?
LearningToProtect
Implementation of "Learning to Protect Communications with Adversarial Neural Cryptography" in PyTorch
mediapipe_arch_vis
Collection of naive visualization of tflite models from MediaPipe
seungwonpark.github.io
Seung-won Park's homepage
userscripts
Personal collection of userscripts (I use Tampermonkey)
extension-getting-started
Hello World for Extensions
fairseq_files_cache
Code snippet for creating a local cache of checkpoints provided within fairseq
GitHubGraduation-2022
Join the GitHub Graduation Yearbook and "walk the stage" on June 11.
griffin_lim
Implementation of the Griffin and Lim algorithm to recover an audio signal from a magnitude-only spectrogram.
model-cards-and-datasheets
A collection of machine learning model cards and datasheets.
speech-resynthesis
An official reimplementation of the method described in the INTERSPEECH 2021 paper - Speech Resynthesis from Discrete Disentangled Self-Supervised Representations.
spinningup
An educational resource to help anyone learn deep reinforcement learning.
voicefilter
voicefilter demo webpage