Views
No views yet
htdemucs (4 stems) exported to ONNX without the STFT/iSTFT
(complex FFT ops are not ONNX-exportable). The caller computes the STFT and
iSTFT outside the graph — see export_onnx.py / verify_onnx.py in the
karoke-maker repo for the
reference implementation and the parity gate this model passed
(0.00% rel err vs PyTorch, voice-leak 0.055 == PyTorch reference).mix float32 (1, 2, 343980) — raw 44.1kHz stereo waveform segment (7.8s)mag float32 (1, 4, 2048, 336) — CaC spectrogram of the same segment
(nfft 4096, hop 1024, periodic Hann, torch.stft normalized=True, channels
ordered [L.re, L.im, R.re, R.im])spec_out float32 (1, 4, 4, 2048, 336) — per-source CaC spectrogramswave_out float32 (1, 4, 2, 343980) — per-source time-branch waveforms[drums, bass, other, vocals].
Reconstruction: stems = istft(spec_out) + wave_out.