docs: align card with sole ReDimNet2 embedder wording

README.md

@@ -29,7 +29,7 @@ pure-Rust inference, **no Python at inference time**.
 
 ## ✨ Highlights
 
-- 🗣️ **OpenASR speaker embedder** — required capability pack for anonymous speaker labels on any ASR family (fail-closed when missing)
+- 🗣️ **OpenASR speaker embedder** — the only supported speaker-embedding pack for diarization and Voice ID; required for anonymous speaker labels on any ASR family
 - 🧬 **192-dim ReDimNet2-B6** — PalabraAI's dimension-reshaping speaker net (12.5M params) with a Chinese-enhanced vb2+vox2+cnc2 training mix
 - 🔒 **Diarization, not identification** — anonymous session-relative labels; embeddings stay local and are discarded after the request unless you explicitly enroll a local profile
 - 🎯 **Parity-gated packaging** — ggml-graph forward pass matches the upstream Python reference at cosine ≥ 0.9999 on held-out fixtures
@@ -61,8 +61,9 @@ ReDimNet2-B6 is PalabraAI's 12.5M-parameter speaker-embedding model from the
 ReDimNet2 family, trained on a VoxBlink2 + VoxCeleb2 + CN-Celeb2 mix so English and
 Chinese speakers share one embedding space. OpenASR packages the MIT-licensed
 checkpoint as a local `.oasr` capability pack and runs it through a ggml graph
-(not a pure-Rust hand-written forward). This is the sole public speaker-embedding pack for OpenASR diarization and Voice ID:
-without it, speaker-embedding paths fail closed (no legacy fallback). Embeddings are
+(not a pure-Rust hand-written forward). This is the only supported speaker-embedding
+stage for diarization and Voice ID: when the pack is missing, diarize/Voice ID
+requests fail closed rather than falling back to another embedder. Embeddings are
 192-d cosine vectors with a ReDimNet-specific calibration profile.
 
 ## ⚙️ How this pack was made