Update README.md

README.md

@@ -59,7 +59,22 @@ let embedding = out.featureValue(for: "embedding")!.multiArrayValue!
 ```
 
 ### Rust (objc2-core-ml)
-See [`scripts/convert-clap-to-coreml.py`](#how-it-was-built) reference repo for a Rust integration that loads this `.mlpackage`, runs sliding-window embedding for arbitrary-length audio, and mean-pools.
+The `objc2`/`objc2-core-ml` crates give direct Rust bindings to Core ML. Sketch:
+
+```rust
+use objc2_core_ml::{MLModel, MLModelConfiguration, MLMultiArray, MLMultiArrayDataType,
+                    MLDictionaryFeatureProvider, MLFeatureValue, MLComputeUnits};
+
+// Core ML wants a compiled .mlmodelc — compile the .mlpackage once,
+// then load with cpuAndGPU compute units.
+let compiled = unsafe { MLModel::compileModelAtURL_error(&mlpackage_url) }?;
+let config = unsafe { MLModelConfiguration::new() };
+unsafe { config.setComputeUnits(MLComputeUnits::CPUAndGPU) };
+let model = unsafe { MLModel::modelWithContentsOfURL_configuration_error(&compiled, &config) }?;
+
+// Build [1, 480000] float32 input, copy waveform via dataPointer,
+// wrap in MLFeatureValue + MLDictionaryFeatureProvider, run prediction.
+```
 
 ### Python (coremltools)
 ```python
@@ -83,7 +98,7 @@ embedding = out["embedding"]  # shape (1, 512)
 5. **Custom `fmod` MIL lowering** — HTSAT's relative-position arithmetic uses float modulo; coremltools has no built-in handler. Registered as `x - trunc(x/y) * y`.
 6. **`slice_scatter` override** — HTSAT's attention-mask builder generates empty-slice `slice_scatter` calls at deeper Swin stages (e.g. `slice(0, -window_size)` evaluates to `slice(0, 0)`). The built-in handler's shape check rejects these; registered override that no-ops empty slices and reduces non-empty ones to `slice_by_index + concat`.
 
-A full conversion script that applies all six patches is in the reference repo (link below).
+A full conversion script that applies all six patches is included in this repo: [`convert-clap-to-coreml.py`](./convert-clap-to-coreml.py). Run with `pip install coremltools>=8,<9 torch>=2.6,<2.10 transformers>=4.40 numpy>=1.24,<2` then `python convert-clap-to-coreml.py --output clap_audio_encoder.mlpackage`. Validation (cosine vs PyTorch reference) runs automatically.
 
 ## Validation