Remove comparison-to-earlier-checkpoint note

README.md

@@ -64,10 +64,6 @@ normalized by removing punctuation.
 - **CER (corpus)** = total edit distance ÷ total reference characters (micro-average).
 - **CER (avg)** = mean of per-clip CER (macro-average).
 
-On the out-of-domain set, this model roughly halves the CER of an earlier,
-smaller-data checkpoint (≈16% → ≈8%), showing the fine-tuning generalizes
-beyond the training domain.
-
 ## Usage
 
 Install the [`qwen-asr`](https://pypi.org/project/qwen-asr/) package (transformers backend):
@@ -141,7 +137,7 @@ If you use this model, please cite:
 ```bibtex
 @misc{yath2026qwen3asrkhmer,
   title  = {Qwen3-ASR-0.6B-Khmer},
-  author = {Seanghay},
+  author = {Yath, Seanghay},
   year   = {2026},
   howpublished = {\url{https://huggingface.co/seanghay/Qwen3-ASR-0.6B-Khmer}}
 }