docs: refresh parity note and validation status

README.md

@@ -1,14 +1,3 @@
----
-library_name: mlx
-tags:
-  - automatic-speech-recognition
-  - speech-to-text
-  - audio
-  - mlx
-  - safetensors
-license: other
----
-
 # cohere-transcribe-03-2026-mlx-8bit
 
 Quantized MLX weights for **beshkenadze/cohere-transcribe-03-2026-mlx-fp16**.
@@ -38,6 +27,22 @@ Sample: `Tests/media/conversational_a.wav`
 - Peak memory: **2.87 GB**
 - Output: `Coffee's story likely begins in Ethiopia, where legend tells of a goat herder named Kaldi, who noticed his goats became energetic after eating red berries from a particular bush; curious, he tried them himself and felt invigorated.`
 
+## Parity note
+
+This checkpoint has been re-validated against the current Swift and Python MLX runtimes.
+
+Verified semantic parity on an English fixture:
+
+> `This is a test recording in English. I am speaking clearly at a normal speed. Please transcribe this sentence exactly as I said.`
+
+Matched across:
+
+- Swift MLX fp16
+- Swift MLX 8-bit
+- Python MLX fp16
+- Python MLX 8-bit
+- official CUDA reference path (`transformers` native Cohere ASR)
+
 ## Quality note
 
 Matches fp16 on the repo sample while reducing memory substantially.