Update model card: add transcribe_cpp metadata block (raw WER/RTF + capabilities)

README.md

@@ -47,9 +47,27 @@ tags:
   - qwen3
   - audio-llm
   - multilingual
+transcribe_cpp:
+  wer_librispeech_test_clean:
+    bf16: 1.74
+    f16: 1.74
+    q8_0: 1.74
+    q6_k: 1.69
+    q5_k_m: 1.77
+    q4_k_m: 1.89
+  rtf_m4_max:
+    metal: 68
+    cpu: 16
+  rtf_ryzen_4750u:
+    vulkan: 9
+    cpu: 4.5
+  streaming: false
+  translate: false
+  lang_detect: false
+  timestamps: none
 ---
 
-# Fun-ASR-MLT-Nano-2512 — transcribe.cpp GGUF
+# Fun-ASR-MLT-Nano-2512: transcribe.cpp GGUF
 
 GGUF conversions of [FunAudioLLM/Fun-ASR-MLT-Nano-2512](https://huggingface.co/FunAudioLLM/Fun-ASR-MLT-Nano-2512) for use
 with [transcribe.cpp](https://github.com/handy-computer/transcribe.cpp).
@@ -72,7 +90,10 @@ parameters: frozen SenseVoiceEncoderSmall + 2-layer audio adaptor +
 bundled Qwen3-0.6B LLM); trained on a smaller multilingual corpus
 ("hundreds of thousands of hours" per the model card, vs Nano's
 "tens of millions"). Takes a 16 kHz mono WAV and emits text. Not
-streaming, no translation, no timestamps.
+streaming, no translation, no timestamps. ITN (inverse text
+normalization) is supported by the model and exposed via the
+`--itn` CLI flag and `transcribe_funasr_nano_params { use_itn }`
+in the library API.
 
 
 ## Downloads