Quellentrennung

Open-Unmix HQ teilt eine Stereo-Musikaufnahme in vier unabhängige Stems — Gesang, Drums, Bass und Rest. Vier unabhängige BiLSTM-Modelle (pro Stem eines) erzeugen Magnitudenmasken über dem Mix-STFT; ein optionaler Wiener-Nachfilter versöhnt sie. Läuft via MLX auf Apple Silicon.

Worum es geht

• 4 stems per track — vocals, drums, bass, other. Each is a 2-channel 44.1 kHz stem file.
• Magnitude-mask model — each stem model predicts a non-negative mask applied to the mixture spectrogram; phase is taken from the mixture.
• Wiener post-filter (optional) — soft-mask refinement across all 4 stems so they sum coherently back to the mixture. Adds ~0.5 dB SDR.
• Small footprint — 8.9M params per stem, ~136 MB total for all 4 stems.
• Apache-2.0 — upstream weights under MIT, our CoreML/MLX conversion under Apache-2.0.

Architektur

Four independent stems, each a copy of the same network:

Modell

Schnellstart — Swift

import SourceSeparation
import AudioCommon

let separator = try await SourceSeparator.fromPretrained()

let stereo = try AudioFileLoader.loadStereo(
    url: URL(fileURLWithPath: "song.wav"),
    targetSampleRate: 44100
)

let stems = separator.separate(audio: stereo, sampleRate: 44100)
// stems[.vocals], stems[.drums], stems[.bass], stems[.other]
// Each is [[Float]] — left channel, right channel.

try WAVWriter.writeStereo(
    left: stems[.vocals]![0],
    right: stems[.vocals]![1],
    sampleRate: 44100,
    to: URL(fileURLWithPath: "vocals.wav")
)

Pass wiener: true (default) for best quality. Pass targets: [.vocals] to extract only a subset of stems and skip the other models.

CLI

speech separate song.wav                              # all 4 stems into song_stems/
speech separate song.wav --stems vocals               # vocals only
speech separate song.wav --stems vocals,drums         # subset
speech separate song.wav --output-dir /tmp/stems/     # custom output dir
speech separate song.wav --verbose                    # show timing

Wann verwenden