There are 2 repositories under demucs topic.
Isolate vocals, drums, bass, and other instrumental stems from any song
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.
free website for client-side music demixing with Demucs + WebAssembly
🎛 Stemgen is a Stem file generator. Convert any track into a Stem and have fun with Traktor.
Dockerized Facebook Demucs library to make it easy its execution
C++17 port of Demucs v3 (hybrid) and v4 (hybrid transformer) models with ggml and Eigen3
Simplified installers for suno-ai/bark, musicgen, tortoise, RVC, demucs and vocos
Use DEMUCS to split songs into multiple sources
The Open Source AI Musical Toolkit
A deep learning lyrics-to-audio alignment system, generating synchronized lyrics from a song and its lyrics
Implements ML audio separation algorithm on audio from YouTube or Spotify resulting in "stems" for download (e.g. vocals, drums, bass) in MP3, WAV or FLAC.
youtube download, vocal remover, vocal extraction, karaoke video production, STT, automatic speech recognition, transcription, automatic subtitle, AI, yt-dlp, demucs, whisper, webui, gradio, windows
We implemented the DEMUCS model for speech enhancement in the time-frequency domain, and additionally implemented HD-DEMUCS.
The best gradio web-ui for vocal remover that uses demucs and mdx-net. Automatic subtitle creation using faster whisper. Easy one click installation. Fully portable.
The best gradio web-ui for creating cover song that uses mdx-net and rvc. Easy one click installation. Fully portable.
(Windows/Linux) Local WebUI with neural network models (LLM, Stable Diffusion, AudioCraft, AudioLDM2, TTS, Bark, Whisper, Demucs, LibreTranslate, ZeroScope2, TripoSR, Shap-E, GLIGEN, Wav2Lip, Roop, Rembg, CodeFormer, Moondream 2) on python (In Gradio interface)
Code to train a custom time-domain autoencoder to dereverb audio
Intelligent Sample Management and Processing
Demucast is a hybrid model for salving music genre classification problem.
Voice separation and conversion project using Demucs and RVC, with server-client architecture for efficient processing and communication.
A Gradio WebUI for audio utilities. Demucs, Whisper, Audio Slicer
A web application for generating music that sounds like the Grateful Dead.
Facebook团队的那个Demucs确实很好用,但是平常用命令行挺麻烦的不是吗?所以我用Python写了一个界面,基于Tkinter。
Code for the paper Hybrid Spectrogram and Waveform Source Separation