From e3e678a0f2c42e96f0e9ad8c98d0f107b3869779 Mon Sep 17 00:00:00 2001 From: yusufipk Date: Sun, 26 Jul 2026 22:51:02 +0700 Subject: [PATCH] Apply the same filler rule to the English prompt The Turkish prompt stopped naming filler words and started weighing what a word does in its sentence, and the English one had the same flaw waiting: "like" and "you know" were listed as words that carry no meaning, which they are only half the time. A model reading that next to the MINIMUM interference rule leaves them where they are. It now reads like the Turkish one. Thinking sounds are their own line, everything else is dropped when the sentence survives without it and kept when it points at something or carries the clause, the listed words are examples rather than a closed set, and doubt resolves towards dropping. Measured over three dictated paragraphs written to mix both uses, same model and only the prompt swapped: 36 candidates in the raw text, 17 surviving the old prompt, 6 the new one, the survivors being real uses such as "works like a charm" and "you know the one I mean". The old default is fingerprinted as legacy alongside the Turkish one. --- config.py | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/config.py b/config.py index ca61a2e..03f0c13 100644 --- a/config.py +++ b/config.py @@ -23,7 +23,15 @@ CLEANUP_PROMPT_EN = """You clean up dictation transcripts. You are given the raw text of something spoken out loud. Make it readable with MINIMAL interference. DO: -- Remove filler sounds and words that carry no meaning ("uh", "um", "like", "you know") +- Remove thinking sounds such as "uh", "um", "er", "hmm" +- Remove filler words. What settles it is not which word it is but the job it + does in that sentence: drop it when the meaning survives without it ("it was, + like, three days" -> "it was three days", "you know, I tried that" -> "I tried + that"), keep it when it points at something or genuinely carries the clause ("a + tool like this one", "you know the one I mean"). "like", "you know", "I mean", + "well", "so", "actually", "basically" and "right" are the common ones, but the + list is not closed; judge the ones nobody listed by the same measure. When in + doubt, drop it; these words hardly ever earn their place in writing - Clean up stutters and involuntary repetitions ("a a a thing" -> "a thing") - When a sentence is abandoned and restarted, keep only the final version - Add punctuation and capitalisation; break into paragraphs where it helps @@ -139,6 +147,7 @@ LEGACY_PROMPTS = { "cd8b0a502b187137e7104c555b8099e200407d6e", # 1.1 English "a318043a6fef0022d969f3b15221b29de4ec8777", # 1.1 Turkish "2a8d55b8c9156944615ed988e0f27c5cc26e979f", # 1.2 Turkish + "154fc5aca1166f00eebda705f848f0391bfbf5fe", # 1.2 English } # Corners used to be stored with Turkish names.