BS-RoFormer wind stem for slurper, fp16 Core ML with golden chunk

.gitattributes

@@ -33,3 +33,5 @@ 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
+golden_horns.f32 filter=lfs diff=lfs merge=lfs -text
+golden_raw.f32 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,20 @@
+---
+library_name: coreml
+tags:
+  - audio
+  - music-source-separation
+  - bs-roformer
+  - coreml
+base_model: noblebarkrr/BS-Roformer-MVSep-Mega-53-stems
+---
+
+# BSRoformer-Wind-CoreML
+
+The wind stem (brass and woodwinds) of the [MVSep Mega 53-stem BS-RoFormer](https://github.com/ZFTurbo/Music-Source-Separation-Training/releases/tag/v1.0.21), converted to Core ML for [slurper](https://github.com/trevors/slurper), where it produces the "horns" stem.
+
+- `bsr_wind_fp16.mlpackage`: the graph `frames[1,2,690,2048] -> recon[1,2,690,2048]` for one 8 s chunk at 44.1 kHz, framed with a 2048-sample periodic Hann window at hop 512: windowed DFT, band split, the axial rotary transformer, mask estimator, complex mask multiply and inverse DFT, all inside the model in float16. The host reflect-pads and frames the chunk and overlap-adds the output divided by the summed squared window.
+- `golden_raw.f32`, `golden_horns.f32`: an 8 s stereo chunk (channel-major float32) and PyTorch's output for it, used by slurper's tests. Core ML matches PyTorch on it at cosine 0.99998 (44.7 dB SDR).
+
+Produced by `scripts/convert_bs_roformer.py` in the slurper repository from the single-stem repack [noblebarkrr/BS-Roformer-MVSep-Mega-53-stems](https://huggingface.co/noblebarkrr/BS-Roformer-MVSep-Mega-53-stems) (`v1/bs_mega_53stem_wind_mvsep.ckpt`), with the model code from [Music-Source-Separation-Training](https://github.com/ZFTurbo/Music-Source-Separation-Training) (MIT). See the upstream release for the weights' terms.
+
+The golden chunk is 8 s from 0:32 of "Blues for Mundy" by The Airmen of Note, The United States Air Force Band (composed by Rick Whitehead), from *60 Years of the Airmen of Note* (2011), via [Wikimedia Commons](https://commons.wikimedia.org/wiki/File:Blues_for_Mundy_-_Airmen_of_Note_-_United_States_Air_Force_Band.mp3). As a work of the US federal government the recording is in the public domain.

bsr_wind_fp16.mlpackage/Data/com.apple.CoreML/model.mlmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbb26610e43376763231deaf8a52f3e296ce50213dd6bb8ac1a452c6f2c70e1e
+size 748990

bsr_wind_fp16.mlpackage/Data/com.apple.CoreML/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acc4dc39bc044f547da86ac399300fdf41f9fed5c114e901a0766b7c5e36fb32
+size 94421760

bsr_wind_fp16.mlpackage/Manifest.json

@@ -0,0 +1,18 @@
+{
+    "fileFormatVersion": "1.0.0",
+    "itemInfoEntries": {
+        "B0268636-0C8F-41A3-9A12-8E5E4EB52A7F": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Weights",
+            "name": "weights",
+            "path": "com.apple.CoreML/weights"
+        },
+        "F5730EEA-E431-4FBB-B005-B973B8041A83": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Specification",
+            "name": "model.mlmodel",
+            "path": "com.apple.CoreML/model.mlmodel"
+        }
+    },
+    "rootModelIdentifier": "F5730EEA-E431-4FBB-B005-B973B8041A83"
+}

golden_horns.f32

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f5ed9182b7d87deaabaa778cbbe7a42e68ac0d1379b0bcad50b436f88973eef
+size 2822400

golden_raw.f32

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e91dd446ccc25ce3c597d4aa8dee7f5e40ee76afcb08e56d0a07bca750ca37f
+size 2822400