Weirenlan's Projects
Self-hostable web app for isolating the vocal, accompaniment, bass, and drums of any song. Supports Spleeter, D3Net, Demucs, Tasnet, X-UMX. Built with React and Django.
A practice to rewrite a caption translator based on openai api with rust
this is a repo to record the practice of self-supervised learning and some resources found on the networks
A full-fledged version of Pix2Seq
STAT 453: Intro to Deep Learning @ UW-Madison (Spring 2020)
Steerable discovery of neural audio effects
Welcome to **StoryStudio**! π Here, we're reimagining the art of storytelling by blending human imagination with the power of cutting-edge AI. Dive into an innovative experimets where stories are not just read, but experienced.
πΈSTT integration examples
Code for SuDoRm-Rf networks for efficient audio source separation. SuDoRm-Rf stands for SUccessive DOwnsampling and Resampling of Multi-Resolution Features which enables a more efficient way of separating sources from mixtures.
Symbolic Music Generation with Diffusion Models
Learn how to design systems at scale and prepare for system design interviews
Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.
Tacotron 2 - PyTorch implementation with faster-than-realtime inference
Productive & portable high-performance programming in Python.
Traditional Chinese LLMs for Taiwan
Boilerplate code for Teachable Machine
Explore how machine learning works, live in the browser. No coding required.
An template C++ project using CMake for build configuration and Catch/TravisCI for automated testing
A repo to set the pythonpath
This is a text adventure game that uses OpenAI's GPT-3 language model and DALL-E 2 image generation model to generate game content on the fly. Players can enter commands to progress the story and see new images generated by DALL-E 2.
Master the command line, in one page
Inspired by the `the missing semester class`
π Collaborative cheatsheets for console commands
Fast audio data augmentation in PyTorch. Inspired by audiomentations. Useful for deep learning.
PyTorch implementation of the Perceptual Evaluation of Speech Quality
Differentiable implementation of MSBG hearing loss model and MBSTOI intelligibility metric for Clarity Enhancement challenge.
Tiny, no-nonsense, self-contained, Tensorflow and ONNX inference
finetune llama2 with traditional chinese dataset