model card: prompt-slot guidance — the FT repairs `auto` (base 50.58 -> 11.33 CER, best slot); all slots within ~0.7 CER

README.md

@@ -20,12 +20,25 @@ Supersedes v1 (which packaged the zero-training warm-start).
 
 ## Accuracy
 
-| build | CV zh-TW CER |
+| build | CV zh-TW CER (n=120) |
 |---|---|
-| fp32 fine-tuned model (reference) | 12.03 |
-| **this q4-mix LiteRT** | **13.90** (+1.87 INT4 cost) |
+| fp32 fine-tuned model (reference) | 11.33 |
+| **this q4-mix LiteRT** | **13.20** (+1.9 INT4 cost) |
 | v1 q4-mix (base warm-start) | ~38 |
 
+Per language-prompt slot on this build — all within ~0.7 CER, pick either:
+
+| slot | q4-mix CER | fp32 CER |
+|---|---|---|
+| `zh-CN` (4) | **13.20** | 11.57 |
+| `auto` (101) | 13.79 | **11.33** |
+| `zh-TW` (5) | 13.90 | 12.03 |
+
+`auto` was the *worst* slot on the base model (50.58 CER) and is repaired by the
+fine-tune — training used `prompt_mode: unified`, which trains the auto path
+alongside the explicit language ID. Use `auto` when the speaker may switch
+languages, or an explicit slot when you know it.
+
 Other languages (fp32 FT, vs base): ko/de/ja/hi/en all improve, ar flat,
 fr/es +1.5 — see the [source model card](https://huggingface.co/Luigi/nemotron-3.5-asr-streaming-0.6b-zhtw).
 
@@ -45,7 +58,8 @@ Port, runner and integration note:
 https://github.com/vieenrose/LiteRT/tree/nemotron/litert/samples/asr/nemotron
 
 ```bash
-python -m nemotron.runner --models ./ --wav clip.wav --lang zh-TW --s2t --itn
+python -m nemotron.runner --models ./ --wav clip.wav --lang zh-CN --s2t --itn
+# --lang auto also works well (see slot table); --s2t gives Traditional output
 ```
 
 **Output is Simplified Chinese** — the tokenizer cannot represent many common