update custom message

constants.py

@@ -101,9 +101,11 @@ CUSTOM_MESSAGE = """## Legend:
 This space is a fork of the original [hf-audio/open_asr_leaderboard](https://huggingface.co/spaces/hf-audio/open_asr_leaderboard). It aims to demonstrate how the CommonVoice Test Set provides a relatively accurate approximation of the average WER/CER (Word Error Rate/Character Error Rate) at a significantly lower computational cost.
 
 #### Why is this useful?
-This space offers a way to achieve standardized test set for most languages, enabling us to programmatically select a reasonably effective model for any language supported by CommonVoice.
+This opens way the to achieve standardized test set for most languages, enabling us to programmatically select a reasonably effective model for any language supported by CommonVoice.
 
-Model, RTF (1e-3) ⬇️, and Average WER ⬇️ were sourced from [hf-audio/open_asr_leaderboard](https://huggingface.co/spaces/hf-audio/open_asr_leaderboard) using the version from September 7, 2023.
+Columns `Model`, `RTF`, and `Average WER` were sourced from [hf-audio/open_asr_leaderboard](https://huggingface.co/spaces/hf-audio/open_asr_leaderboard) using the version from September 7, 2023.
+
+Models are sorted by consistancy in there results across testset. (by increasing order of absolute delta between average WER and CommonVoice WER) 
 
 ### Results
 The CommonVoice Test provides a Word Error Rate (WER) within a 20-point margin of the average WER.