Open-Unmix vs StemDeck

Open-Unmix is a PyTorch reference implementation for music source separation, aimed at researchers, audio engineers, and artists. Its ready-to-use models split pop music into vocals, drums, bass, and other instruments; a separate model, umxse, is for speech enhancement and was trained on the 28-speaker Voicebank+DEMAND corpus. Pre-trained choices include umxl, umxhq, umx, and umxse, with spectrogram variants also available. Each source model uses a three-layer bidirectional LSTM, a design the project says cannot run online or in real time. The code supports reproducing results, developing architectures, and adding data, while training is documented separately from the package. Install through pip or use the Docker container; pre-trained models can be loaded in Python or through torch.hub, and a Colab notebook supports online experimentation without local setup. The command line handles WAV, FLAC, and OGG, not MP3; stempeg can extend formats, including STEMS export. The software is MIT-licensed; umxl weights are non-commercial under CC BY-NC-SA 4.0.

StemDeck separates songs into stems for practice, study, transcription, remixing, and other creative audio work. Its Demucs htdemucs_6s model separates vocals, drums, bass, guitar, piano, and other sounds. Files accepted include MP3, WAV, FLAC, OGG/Opus, MP4, and M4A, and songs can also be supplied by YouTube URL. The workspace provides waveform lanes, mute and solo controls, volume adjustment, and looping; users can export individual stems or a custom mix in WAV or MP3. Song analysis includes BPM, key, scale, confidence, integrated LUFS, and sample peak level. StemDeck says audio processing runs locally and the app does not transmit, store, cache, or redistribute audio. Internet access is needed for YouTube downloads and an initial model fetch of about 170 MB, which is cached afterward. The project documents Docker and Unraid deployment, source-based web-server use, and a local REST API. It is free, with no account, quota, uploads, or subscription, but handles one job at a time, supports up to six stems, and has no mobile app.