Downloads · 30 days
0
windowed-roformer-onnx
mtsmfm/windowed-roformer-onnx
windowed-roformer-onnx is a audio-to-audio model from mtsmfm. Use it for the audio-to-audio task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
ONNX conversions of smulelabs/windowed-roformer (checkpoint mbr-win10-sink8; code and weights are MIT) for vocals/BGM separation.
Access
Public
Updated Aug 7, 2026
Repo size
3.9 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.onnx2.4 GB · 100%
At a glance
- Task
- Audio-to-Audio
- License
- mit
- Access
- Public
- Created
- Aug 6, 2026
- Updated
- Aug 7, 2026
- SHA
- 7ab881ac
Model card
From the Hugging Face model README
windowed-roformer-onnx
ONNX conversions of smulelabs/windowed-roformer
(checkpoint mbr-win10-sink8; code and weights are MIT) for vocals/BGM separation.
Files
| File | What it is |
|---|---|
windowed-roformer.onnx | Plain fp32 conversion. Runs on stock ONNX Runtime. FlexAttention is replaced with an equivalent block-local + sink attention, and STFT/iSTFT are moved outside the model — I/O is stft_in / masked_stft (1, 2, 1025, 801, 2) (n_fft 2048, hop 441, 44.1kHz, 8-second chunks). |
wagiri/wagiri-roformer.onnx | fp16, heavily optimized for WebGPU in wagiri. Not runnable on stock ONNX Runtime: the graph uses com.microsoft ops with app-specific semantics that require wagiri's patched onnxruntime-web kernels. |
wagiri/wagiri-roformer-fp32.onnx | Same as above in fp32, for GPUs without shader-f16. |
The conversion pipeline (with numerical-equivalence checks at every stage) lives in
wagiri's conversion/.
License
MIT, same as the original code and weights.
- Task
- Audio-to-Audio
- License
- mit
- Created
- Aug 6, 2026
- Updated
- Aug 7, 2026