Neutral wording, single-machine caveat, correct project link

README.md

@@ -21,17 +21,13 @@ Speech enhancement at 16 kHz. This model was converted to MLX format from
 | --- | ---: | --- |
 | `model_fp32.safetensors` | 56 MB | the weights |
 | `FRCRN_SE_16K.yaml` | 614 B | upstream model configuration |
-| `weights.npz` | 110 MB | superseded, see below |
+| `weights.npz` | 110 MB | superseded |
 
 fp32 only; no half-precision or quantized conversion is published.
 
-`weights.npz` predates the safetensors conversion and is kept only so that
-anything already referring to it keeps working. It is not what loads: use
-`model_fp32.safetensors`.
+`weights.npz` predates the safetensors conversion and is kept so that anything
+already referring to it keeps working. Load `model_fp32.safetensors`.
 
-## Use
+## Used by
 
-Consumed by [AudioToolSwift](https://github.com/starkdmi) as
-`ModelRepository.frcrnSE16K`, which pins this repository to an exact revision and
-verifies the SHA-256 of every file it downloads. The loader reads the safetensors
-and nothing else — the YAML is provided for reference.
+[AudioToolSwift](https://github.com/starkdmi/AudioToolSwift)