Refresh README with official overview and MLX notes

README.md

@@ -19,9 +19,21 @@ language:
 
 Current variant: `4bit` (default entry)
 
-MLX export of `XiaomiMiMo/MiMo-V2.5-ASR` with `XiaomiMiMo/MiMo-Audio-Tokenizer`.
+MLX conversion of `XiaomiMiMo/MiMo-V2.5-ASR` for local inference on Apple silicon.
 
-## Variants
+## Overview
+
+MiMo-V2.5-ASR is an end-to-end speech recognition model from the Xiaomi MiMo team. The official release focuses on robust transcription across Mandarin Chinese, English, Chinese dialects, code-switched speech, lyrics, noisy recordings, meetings, and knowledge-intensive content. This repository keeps the original model scope and packages it as an MLX-ready variant built from the official release.
+
+Official resources:
+
+- Model: `XiaomiMiMo/MiMo-V2.5-ASR`
+- Tokenizer: `XiaomiMiMo/MiMo-Audio-Tokenizer`
+- Demo: `XiaomiMiMo/MiMo-V2.5-ASR` Space
+- Blog: `mimo.xiaomi.com/mimo-v2-5-asr`
+- Code: `XiaomiMiMo/MiMo-V2.5-ASR`
+
+## MLX Variants
 
 | Variant | Precision | Size | Local smoke time | Smoke result |
 | --- | --- | ---: | ---: | --- |
@@ -33,9 +45,9 @@ MLX export of `XiaomiMiMo/MiMo-V2.5-ASR` with `XiaomiMiMo/MiMo-Audio-Tokenizer`.
 
 ## Notes
 
-- Source model: `XiaomiMiMo/MiMo-V2.5-ASR`
-- Tokenizer: `XiaomiMiMo/MiMo-Audio-Tokenizer`
+- Base model: `XiaomiMiMo/MiMo-V2.5-ASR`
+- Required tokenizer: `XiaomiMiMo/MiMo-Audio-Tokenizer`
 - Conversion date: `2026-05-12`
-- License: `Apache-2.0`
-- Smoke test: `mlx-audio-swift` on `Tests/media/intention.wav`
+- Local validation: `mlx-audio-swift` on `Tests/media/intention.wav`
 - Recommended default: `MiMo-V2.5-ASR-MLX`
+- This repository is a community MLX conversion. For benchmark tables, demos, and the original project description, see the official release.