Joseph Turian's Projects
Anticipatory Autoregressive Models
🗃 Open source self-hosted web archiving. Takes URLs/browser history/bookmarks/Pocket/Pinboard/etc., saves HTML, JS, PDFs, media, and more...
ArchiveBox blueprint for Render
Convert between Ardour XML and binary FXP VST2 preset files. [SAFER]
ASKBOT is a StackOverflow-like Q&A forum, based on CNPROG.
Web service to crowd-source audio discrimination data
Batch processing for audio-discrimination-crowdsource
Audio representations, dockerized
Audio pair JND
Implementation of AudioLM, a SOTA Language Modeling Approach to Audio Generation out of Google Research, in Pytorch
A Python library for audio data augmentation. Inspired by albumentations. Useful for machine learning.
Collection of audio-focused loss functions in PyTorch
Simple demonstration of auth0 authentication with Django.
Simple demonstration of auth0 authentication with a Flask app.
Label, clean and enrich text datasets with LLMs. Discord: https://discord.gg/fweVnRx6CU
Find the best model, using random hyperparameter optimization, using scikit-learn
Perform a biased sample of text data
A static file blog engine/compiler, inspired by jekyll
Boilerplate Removal using Deep Learning
Incredibly fast Whisper-large-v3, for replicate.com, with video
Common Python library, especially for text processing and controlling experimental runs
Common scripts, mainly for text processing and experimental control
PyTorch implementation of NVIDIA WaveGlow with constant memory cost.
Contrastive unpaired image-to-image translation, faster and lighter training than cyclegan (ECCV 2020, in PyTorch)
Train a CRF for syntactic chunking (CoNLL2000), and use word representations