Remove evaluation set details from the org card

README.md

@@ -10,20 +10,19 @@ pinned: false
 desktop. Local speech to text, spoken answers, translation, and dictation cleanup, on
 Windows, macOS and Linux. Transcription runs on your own machine.
 
-This organisation publishes the models and evaluation sets behind it. Everything here is
-Apache-2.0 or CC-BY-4.0 and runs locally.
+This organisation publishes the models behind it. Everything here is Apache-2.0 and runs
+locally.
 
-- **speakoflow-mini-0.8b-GGUF**, a 0.8B dictation cleanup model that runs on a desktop CPU.
-  70.7% overall on the benchmark below, against 65.0% for a hosted frontier model and 50.0%
-  for doing nothing at all.
-- **dictation-cleanup-bench**, 150 held-out rows, 68 of them no-ops, scoring restraint and
-  edit accuracy as separate halves.
+**speakoflow-mini-0.8b-GGUF** is a 0.8B dictation cleanup model that runs on a desktop CPU.
+It applies the correction the speaker actually made and returns everything else byte for
+byte. On a held-out evaluation it scores 70.7% overall, against 65.0% for a hosted frontier
+model and 50.0% for doing nothing at all. Five quantisations are published and each one's
+cost is measured rather than estimated.
 
-Cleanup is the first piece published here because it is the part nobody measures.
-Grammatical error correction, ASR error correction and spoken-to-written conversion all
-score whether a required edit was *made*. None scores whether an unrequired edit was
-*withheld*, and that is the failure that ruins a dictation product. Four of the seven
-models measured score worse than leaving the transcript alone.
+That last number is the interesting one. Grammatical error correction, ASR error correction
+and spoken-to-written conversion all score whether a required edit was *made*. None scores
+whether an unrequired edit was *withheld*, and that is the failure that ruins a dictation
+product. Four of the seven systems measured do worse than leaving the transcript alone.
 
 Built by [Abhishek Barali](https://huggingface.co/AbhishekBarali) ·
 [speakoflow.com](https://speakoflow.com) ·