Open-Unmix UMX-L — ONNX Stem Separation Models
4 source-specific ONNX models for stem separation, exported from Open-Unmix UMX-L.
Models
| File | Source | Size | Format |
|---|---|---|---|
umxl_vocals.onnx | Vocals | ~108 MB | ONNX opset 17 |
umxl_drums.onnx | Drums | ~108 MB | ONNX opset 17 |
umxl_bass.onnx | Bass | ~108 MB | ONNX opset 17 |
umxl_other.onnx | Other | ~108 MB | ONNX opset 17 |
Architecture
Open-Unmix operates in the spectrogram domain (not waveform). Each model:
- Input: Magnitude spectrogram
(batch, 2, 2049, nb_frames)— stereo, 2049 frequency bins - Output: Masked spectrogram
(batch, 2, 2049, nb_frames)— same shape - Internal: Linear → BatchNorm → LSTM (3 layers) → Linear → Output scaling → ReLU masking
Usage
STFT and ISTFT must be performed on-device:
- STFT:
n_fft=4096,n_hop=1024, sample rate44100 Hz - Magnitude: Compute
|STFT(audio)|→(1, 2, 2049, frames) - Model: Run each source model on the magnitude spectrogram
- Reconstruct: Multiply masked spectrogram with complex STFT phase
- ISTFT: Invert back to waveform
Config
config.json contains STFT parameters:
{
"n_fft": 4096,
"n_hop": 1024,
"nb_bins": 2049,
"sample_rate": 44100,
"sources": ["vocals", "drums", "bass", "other"],
"model": "umxl"
}
Verification
All models verified with ONNX Runtime (max absolute diff < 0.00001 vs PyTorch).
For DJNed App
These models are used by the DJNed Android app for on-device stem separation. Download is managed by the app's Model Manager.