StreamDiffusion: A Pipeline-Level Solution for Real-Time Interactive Generation

A playbook for systematically maximizing the performance of deep learning models.

LLM101n: Let's build a Storyteller

🔥Highlighting the top ML papers every week.

Implementation of DDSP (PyTorch), Differentiable Digital Signal Processing (ICLR 2020)

PyTorch implementation of cross-cultural music transfer learning

Google, Naver multiprocess image web crawler (Selenium)

This repo contains Minsk, a handwritten compiler in C#. It illustrates basic concepts of compiler construction and how one can tool the language inside of an IDE by exposing APIs for parsing and ty…

Reference models and tools for Cloud TPUs.

Audio processing by using pytorch 1D convolution network

Official implementation of Highlight-Guided Diffusion

american fuzzy lop - a security-oriented fuzzer

Jamendo music dataset with time-aligned lyrics for lyrics alignment evaluation

Self-hosted YouTube downloader (web UI for youtube-dl / yt-dlp)

Codebase for 'A Real-Time Lyrics Alignment System Using Chroma And Phonetic Features For Classical Vocal Performance', ICASSP 2024

data leakage problem between large music datasets

Sync Toolbox - Python package with reference implementations for efficient, robust, and accurate music synchronization based on dynamic time warping (DTW)

MIDI, WAV domain music emotion recognition [ISMIR 2021]

Emotional conditioned music generation using transformer-based model.

Real-Time Music Tracking System in Wearable AR Display for Music Performance

Inference code for Llama models

A Production-ready Reinforcement Learning AI Agent Library brought by the Applied Reinforcement Learning team at Meta.

Landmark-based audio fingerprinting

Notebooks to investigate data set bias in audio embeddings

PNG files of scanned Jeongganbo