Upload README.md

README.md

@@ -43,7 +43,7 @@ repository: https://github.com/AutoArk/open-audio-opd
 
 </div>
 
-> **TL;DR** ARK-ASR-0.6B is a 0.6B-parameter automatic speech recognition model trained with teacher-data adaptation and on-policy distillation. The accompanying training, inference, and evaluation code is available at [AutoArk/open-audio-opd](https://github.com/AutoArk/open-audio-opd).
+> **TL;DR** ARK-ASR-0.6B is an automatic speech recognition model trained with teacher-data adaptation and on-policy distillation, using a compact 0.6B-scale decoder LLM together with a dedicated audio encoder and adapter. The accompanying training, inference, and evaluation code is available at [AutoArk/open-audio-opd](https://github.com/AutoArk/open-audio-opd).
 
 ## Abstract
 
@@ -65,7 +65,7 @@ Chinese, English, German, Japanese, French, Korean, Spanish, Polish, Italian, Ro
   <p><strong>Figure 1: ARK-ASR architecture.</strong> Audio is encoded by a Whisper-style encoder with RoPE, merged through an MLP adapter, and injected into a Qwen2 decoder by replacing audio placeholder token embeddings before transcript generation.</p>
 </div>
 
-- **Model size:** 0.6B parameters
+- **Model size:** 0.6B decoder LLM parameters, with a separate 0.6B-scale Whisper-style audio encoder and MLP adapter
 - **Task:** automatic speech recognition
 - **Architecture:** audio-capable autoregressive Transformers model with custom `arkasr` remote code
 - **Checkpoint format:** `safetensors`
@@ -94,7 +94,7 @@ The following results are from the `open-audio-opd` evaluation. Lower CER/WER is
 | Qwen3-ASR-0.6B | 2.07% | 5.57% | 5.45% | 4.36% |
 | Qwen3-ASR-1.7B | 1.50% | 4.69% | 4.55% | 3.58% |
 
-`Ark-ASR` is the 0.6B ASR checkpoint trained with teacher-data adaptation and on-policy distillation from `open-audio-opd`.
+`Ark-ASR` is the 0.6B-scale ASR checkpoint trained with teacher-data adaptation and on-policy distillation from `open-audio-opd`.
 
 ## Inference