Fix org card: 3-repo split, dead link, Yunlin, drop Space frontmatter

README.md

@@ -1,72 +1,48 @@
----
-title: WeeMed AI
-emoji: 🩺
-colorFrom: blue
-colorTo: green
----
-
 # WeeMed AI
 
-**Building a globally standardized, AI-driven digital health and long-term care platform
-for aging societies.**
+**Building a globally standardized, AI-driven digital health and long-term care platform for aging societies.**
 
-FHIR-first. Integrated health data, intelligent decision support, personalized preventive
-medicine — deployed in real clinics, health-screening centers, and community long-term
-care sites in Taiwan.
+FHIR-first. Integrated health data, intelligent decision support, personalized preventive medicine — deployed in real clinics, health-screening centers, and community long-term care sites in Taiwan.
 
 > **AI accelerates digitization; it isn't the product.**
 
-Based in Taichung, Taiwan.
+Based in Yunlin, Taiwan.
 
 <!-- PENDING APPROVAL from Prof. Chuan-Yu Chang before publishing:
-A spin-off of the **Medical Image Processing Laboratory (MIPL)**, National Yunlin
-University of Science and Technology — a lab that has built AI-assisted diagnostic
-systems with National Taiwan University Hospital Yunlin Branch, National Cheng Kung
-University Hospital, and Dalin Tzu Chi Hospital since 2003.
--->
+A spin-off of the Medical Image Processing Laboratory (MIPL), National Yunlin
+University of Science and Technology. -->
 
 ---
 
 ## What we release here
 
-We ship models that fall out of real deployment problems, and we publish the
-**measurements**, not just the weights.
+We ship models that fall out of real deployment problems, and we publish the **measurements**, not just the weights.
 
-### 🎙️ [Breeze-ASR-26-edge](https://huggingface.co/weemed/Breeze-ASR-26-edge)
+### 🎙️ Breeze-ASR-26 — Taigi + Mandarin ASR for the edge
 
-Taiwanese Hokkien (台語) + Mandarin speech recognition, quantized for the edge, in two
-runtimes — with a measured benchmark telling you which to pick:
+Quantized redistributions of [MediaTek-Research/Breeze-ASR-26](https://huggingface.co/MediaTek-Research/Breeze-ASR-26) (Apache-2.0) in three runtimes — pick by your constraint:
 
-| Runtime | RTF (CPU, 4 threads) | Real-time? |
-|---|---|---|
-| CTranslate2 / faster-whisper | **0.18 – 0.23** | ✅ |
-| ONNX / sherpa-onnx | 1.17 – 1.76 | ❌ (but runs on Android/iOS/WASM) |
+| Repo | Runtime | Peak RSS | RTF (CPU) | Best for |
+|---|---|---|---|---|
+| [Breeze-ASR-26-ct2](https://huggingface.co/weemed/Breeze-ASR-26-ct2) | faster-whisper | ~2.9 GB | **0.21** | servers, GPU, 8 GB+ hosts |
+| [Breeze-ASR-26-GGML](https://huggingface.co/weemed/Breeze-ASR-26-GGML) | whisper.cpp / MacWhisper | **1.85 GB** | 0.40 | 4 GB hosts, desktop apps |
+| [Breeze-ASR-26-ONNX](https://huggingface.co/weemed/Breeze-ASR-26-ONNX) | sherpa-onnx | — | 1.3 | Android / iOS / WASM |
 
-Measured on real multi-speaker meeting audio, not synthetic clips. Derived from
-[MediaTek-Research/Breeze-ASR-26](https://huggingface.co/MediaTek-Research/Breeze-ASR-26)
-(Apache-2.0) — all credit for the model to MediaTek Research.
+Measured on real multi-speaker Mandarin meeting audio. Mandarin does not regress; Taigi is transcribed as Mandarin meaning, not verbatim Taigi characters.
 
 ---
 
 ## Why this matters to us
 
-Taiwan is aging fast, and the people doing the caring — nurses at screening centers,
-care managers at community sites, elders themselves — mostly do not speak to each other
-in written Mandarin. They speak **Taigi**, in noisy rooms, on tablets held in one hand.
-
-Health tech that only understands clean written Mandarin does not meet them where they
-are. So we work on the unglamorous end of clinical AI: the languages actually spoken,
-the devices actually held, the constraints actually present.
+Taiwan is aging fast, and the people doing the caring — nurses at screening centers, care managers at community sites, elders themselves — mostly do not speak in written Mandarin. They speak **Taigi**, in noisy rooms, on tablets held in one hand. Health tech that only understands clean written Mandarin does not meet them where they are.
 
 ---
 
 ## How we publish
 
-- **Honest benchmarks.** We report the number that survives scrutiny, including when it
-  kills our own hypothesis. Our ASR card documents the measurement traps we fell into
-  before publishing (short clips and repetitive audio both give flattering, wrong RTFs).
+- **Honest benchmarks.** We report the number that survives scrutiny, including when it kills our own hypothesis.
 - **Named gaps.** What we could not measure is written down as an open gap, not omitted.
-- **Real audio, real clinics.** Benchmarks on synthetic data tell you about synthetic data.
+- **Real audio, real clinics.** Benchmarks on synthetic data only tell you about synthetic data.
 
 ---