htdemucs on Core AI, float32

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+htdemucs_fp32.aimodel/main.mlirb filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,47 @@
+---
+license: mit
+tags:
+  - audio
+  - source-separation
+  - music
+  - demucs
+  - core-ai
+---
+
+# htdemucs on Core AI
+
+Meta's [Hybrid Transformer Demucs](https://github.com/facebookresearch/demucs) (`htdemucs`: drums, bass, other, vocals) converted to a Core AI model for macOS 27 on Apple Silicon. It is the drum, bass and other separator in slurper, a stem-splitting command-line tool.
+
+## Graph
+
+`htdemucs_fp32.aimodel`, float32, one function `main`, fixed shapes for one 7.8 s segment at 44.1 kHz:
+
+| | Name | Shape | Contents |
+|---|---|---|---|
+| in | `mix` | `[1, 2, 343980]` | stereo audio |
+| in | `spec` | `[1, 4, 2048, 336]` | `HTDemucs._magnitude(HTDemucs._spec(mix))`: left real, left imaginary, right real, right imaginary |
+| out | `time` | `[1, 8, 343980]` | time branch, 4 sources × 2 channels |
+| out | `freq` | `[1, 16, 2048, 336]` | frequency branch, 4 sources × 2 channels × real/imaginary |
+
+The graph is `HTDemucs.forward` from its normalization to just before `_mask`; both outputs are denormalized. The complex STFT stays on the host, so a caller:
+
+1. computes `spec` as demucs does: reflect-pad by 1536 samples plus the remainder of the last hop, take a centered, normalized STFT (4096-sample periodic Hann, hop 1024), and keep bins 0..<2048 of frames 2..<338;
+2. runs `main`;
+3. inverts each source and channel of `freq` with `HTDemucs._ispec` (zero Nyquist bin, two zero frames each side, normalized inverse STFT, trim) and adds `time`.
+
+For whole songs, split into 7.8 s segments overlapping by a quarter with triangular crossfades, as demucs's `apply_model` does. Source order is drums, bass, other, vocals.
+
+float16 overflows to NaN in the frequency branch. Running two inferences at once on one loaded model corrupted the outputs, so run segments one at a time.
+
+## Verification
+
+- A synthetic segment through Core AI on the GPU against PyTorch `HTDemucs.forward`: 114 dB (drums), 129 dB (bass), 114 dB (other), 100 dB (vocals) SDR.
+- A 135 s song through slurper's Swift host against PyTorch `apply_model` (no shifts, overlap 0.25): 113-120 dB SDR per stem.
+
+## Conversion
+
+`scripts/convert_htdemucs.py` in slurper: demucs 4.1.0, torch 2.13.0, coreai-torch 0.4.2 (coreai-core 1.0.0b2). It exports the core with `torch.export`, converts it with `TorchConverter`, and checks the Core AI output against PyTorch before saving.
+
+## License
+
+MIT, as are the htdemucs weights in facebookresearch/demucs.

htdemucs_fp32.aimodel/main.mlirb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fea0ebe002d1182f0ab4ad6cd933e35385e28a2cc2784e989dcee18479f5433
+size 168673164

htdemucs_fp32.aimodel/metadata.json

@@ -0,0 +1,5 @@
+{
+  "producer" : "coreai-core 1.0.0b2",
+  "assetVersion" : "2.0",
+  "creationDate" : "20260914T160315Z"
+}