forever-jukebox
An end-to-end Infinite Jukebox replacement that analyzes audio, serves it via an API, and plays it with tunable, interactive visualizations via Web and offline PWA.
- 48
- TypeScript
- MIT
- 3 d ago
An end-to-end Infinite Jukebox replacement that analyzes audio, serves it via an API, and plays it with tunable, interactive visualizations via Web and offline PWA.
A Julia package for advanced Matrix Diagonalization algorithms (PCA, Whitening, MCA, gMCA, CCA, gCCA, CSP, CSTP, AJD, mAJD)
C++ library for audio and music analysis, description and synthesis, including Python bindings
Transfer learning / domain adaptation / domain generalization / multi-task learning etc. Papers, codes, datasets, applications, tutorials.-迁移学习
给 AI Agent 做音乐视频的底座:画面交给模型,引擎管画面之外——和人一步步确认需求、分析歌曲(节拍、段落、逐词歌词)、逐帧出片、版本逐段挑选、检查和交付。AE 式零件和效果库可选。
Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translation and Keyword Spotting. Won NAACL2022 Best Demo Award.
Fast implementations of FastICA and DUET for blind source separation
List of articles related to deep learning applied to music
Train and evaluate embeddings for similarity search with PyTorch. Includes contrastive losses, hard example mining, samplers, and retrieval metrics.
Portable ISO C11 library and open APTA 1.0 standard for progressive, bounded waveform, tempo and beatgrid analysis on desktop and embedded systems
| Name | Stars | License | Language | Last change | In common | Compare |
|---|---|---|---|---|---|---|
| deezer/zeroNoteSamba | 29 | None declared | Python | 3 y ago | ||
| creightonlinza/forever-jukebox | 48 | MIT | TypeScript | 3 d ago | beat-tracking | Compare |
| Marco-Congedo/Diagonalizations.jl | 38 | None declared | Julia | 7 mo ago | blind-source-separation | Compare |
| MTG/essentia | 3.8k | AGPL-3.0 | C++ | 3 d ago | music-information-retrieval | Compare |
| jindongwang/transferlearning | 14k | MIT | Python | 21 mo ago | self-supervised-learning | Compare |
| xiaoming6680/xm-video-engine | 30 | GPL-3.0 | TypeScript | 8 d ago | beat-tracking | Compare |
| libAudioFlux/audioFlux | 3.4k | MIT | C | 9 mo ago | music-information-retrieval | Compare |
| PaddlePaddle/PaddleSpeech | 13k | Apache-2.0 | Python | 3 mo ago | self-supervised-learning | Compare |
| baggepinnen/IndependentComponentAnalysis.jl | 8 | None declared | Julia | 4 wk ago | blind-source-separation | Compare |
| ybayle/awesome-deep-learning-music | 3k | MIT | TeX | 3 y ago | music-information-retrieval | Compare |
| KevinMusgrave/pytorch-metric-learning | 6.3k | MIT | Python | 8 d ago | self-supervised-learning | Compare |
| dvucinozd/libapta-audio | 0 | Apache-2.0 | C | 3 wk ago | beat-tracking, music-information-retrieval | Compare |
| mdeff/fma | 2.7k | MIT | Jupyter Notebook | 4 y ago | music-information-retrieval | Compare |