Mel-Band RoFormer Karaoke (aufr33/viperx) β WebGPU-friendly ONNX
Re-export of bdsqlsz/mel_band_roformer_karaoke_aufr33-ONNX (checkpoint
mel_band_roformer_karaoke_aufr33_viperx_sdr_10.1956) with graph surgery so it
runs on onnxruntime-web's WebGPU EP:
- all 26
Einsumops replaced withMatMul/Mul/Transposesubgraphs; - two 60-output
Splitops (mel-band split) rebuilt as binary trees of 2-output splits.
Reason: the stock export produces shaders with 11+ storage buffers and hits
WebGPU's maxStorageBuffersPerShaderStage = 10 limit. The rewritten graph is
numerically identical (maxAbsDiff = 0.0 on probe inputs).
Interface (host-STFT)
- input
stft_features[1, frames, 4100]β frames-major packing:t*4100 + (2*freq + channel)*2 + (0=re, 1=im) - output
mask[1, 1, 2050, frames, 2]β single LEAD-vocal mask (backing = input β lead), packed bins2*freq + channel - STFT params: 44100 Hz, n_fft 2048, hop 441, center, periodic Hann
Used by KaraokeVideoEditor.
Surgery script: eval/fix-karaoke-onnx.mjs in the repo.
Inference Providers NEW
This model isn't deployed by any Inference Provider. π Ask for provider support