card: Shenava-1 v1.0 family

README.md

@@ -35,14 +35,14 @@ datasets:
 
 # Shenava — Rizeh v1.0 (32M) · CoreML fp16
 
-CoreML **fp16** mlprogram export of [`Shenava-Rizeh-v1.0`](https://huggingface.co/Reza2kn/Shenava-Rizeh-v1.0) (its parent). `minimum_deployment_target=macOS13`, for iOS/macOS.
+CoreML **fp16** mlprogram export of [`Shenava-Rizeh-v1.0`](https://huggingface.co/Reza2kn/Shenava-Rizeh-v1.0). macOS13+.
 
 ## The Shenava‑1 family
 
 A knowledge‑distillation cascade of on‑device Persian ASR models — one teacher distilled down to a 6.9M student. This model is one member; its siblings:
 
-- [`Reza2kn/Shenava-Koochik-1.0`](https://huggingface.co/Reza2kn/Shenava-Koochik-1.0) — **Koochik 1.0** (114M) · teacher / flagship
-- [`Reza2kn/Shenava-Rizeh-v1.0`](https://huggingface.co/Reza2kn/Shenava-Rizeh-v1.0) — **Rizeh v1.0** (32M) · mid-tier student ◀ **you are here (or its parent)**
+- [`Reza2kn/Shenava-Koochik-v1.0`](https://huggingface.co/Reza2kn/Shenava-Koochik-v1.0) — **Koochik v1.0** (114M) · teacher / flagship — on-device WER record
+- [`Reza2kn/Shenava-Rizeh-v1.0`](https://huggingface.co/Reza2kn/Shenava-Rizeh-v1.0) — **Rizeh v1.0** (32M) · mid-tier student ◀ **this model (or its parent)**
 - [`Reza2kn/Shenava-Rizeh-Pizeh-v1.0`](https://huggingface.co/Reza2kn/Shenava-Rizeh-Pizeh-v1.0) — **Rizeh Pizeh v1.0** (6.9M) · tiniest — real-time on a 2015 Cortex-A7
 
 ## Benchmark — fair WER/CER
@@ -51,14 +51,16 @@ ITN + Persian‑digit normalizer (the [double‑benchmark](https://huggingface.c
 
 | Member | golden‑6669 WER | CER | FLEURS‑fa WER | CER |
 |---|---|---|---|---|
-| Koochik 1.0 (114M) | 7.49% | 2.30% | 10.64% | 3.79% |
+| Koochik v1.0 (114M) | **7.49%** | 2.30% | **10.64%** | 3.79% |
 | Rizeh v1.0 (32M) | 12.11% | 3.94% | 14.45% | 5.10% |
 | Rizeh Pizeh v1.0 (6.9M) | 24.55% | 8.89% | 26.95% | 10.22% |
 
-## Parity (269‑gold, fp16 vs fp32 source)
+Koochik v1.0 is **#2 on the public double‑benchmark, behind only cloud Gemini** — the best on‑device Persian ASR, beating a 1.5B Whisper‑Persian by >2× WER at 1/13 the size.
 
-exact transcript **257/269**, argmax‑step agreement **0.9977**, mean char‑sim 0.9981, 52 MB.
+## Parity (269‑gold)
 
-**Fixed‑window contract:** `processed_signal` `[1,80,2005]`, `processed_signal_length` `[1]` → `logits` `[1,~252,1025]`, `encoded_lengths` `[1]`. Sidecars (`tokens.json`, `preprocessor.json`, `mel_filters_slaney_80x257.json`) are regenerated from the parent `.nemo`.
+exact **257/269**, argmax **0.9977**, char‑sim 0.9981, 52 MB.
 
-Tokenizer: ve_tok_v4 (SentencePiece BPE‑1024 +blank, digit/punct/«»‑aware). Numbers are emitted in **spoken form**; apply ITN at display for digits. Part of [VisualEars / Shenava](https://shenava.app).
+**Fixed‑window contract:** `processed_signal` `[1,80,2005]`, `processed_signal_length` `[1]` → `logits` `[1,~252,1025]`, `encoded_lengths` `[1]`. Sidecars regenerated from the parent `.nemo`.
+
+Tokenizer: ve_tok_v4 (SentencePiece BPE‑1024 +blank, digit/punct/«»‑aware). Numbers are **spoken‑form**; apply ITN at display for digits. Part of [VisualEars / Shenava](https://shenava.app).