Take audit: mrmB8C1Vw-4DEtSGqpAne
2026-08-22T09:14:47.738Z — Mika
0/13 judged · keyboard: Space play/pause, ↑/↓ focus, P pass, T Translation failure, F fail
Do a blind check (transcripts hidden)
Ground Truth
What the Tester actually said. Never pre-filled from an Engine — type what you hear.
Transcripts
mini_prod_baseline gpt-4o-mini-transcribe · degraded · en · bare
— MER accuracy pending Ground Truth · 768 ms · verdict: unjudged
請把袖子脫掉可以嗎?
mini_auto_bare_deg gpt-4o-mini-transcribe · degraded · auto · bare
— MER accuracy pending Ground Truth · 517 ms · verdict: unjudged
請把袖子脫掉可以嗎?
mini_auto_bare_clean gpt-4o-mini-transcribe · clean · auto · bare
— MER accuracy pending Ground Truth · 987 ms · verdict: unjudged
請把袖子撲掉可以嗎?
mini_auto_prompt_deg gpt-4o-mini-transcribe · degraded · auto · mixed prompt
— MER accuracy pending Ground Truth · 721 ms · verdict: unjudged
請把 shoes 脫掉可以嗎?
mini_auto_prompt_clean gpt-4o-mini-transcribe · clean · auto · mixed prompt
— MER accuracy pending Ground Truth · 2384 ms · verdict: unjudged
請把秀撲掉可以嗎?
mini_auto_prompt_64k gpt-4o-mini-transcribe · 64k · auto · mixed prompt
— MER accuracy pending Ground Truth · 671 ms · verdict: unjudged
請把 shoes 脫掉可以嗎?
mini_zh_prompt_deg gpt-4o-mini-transcribe · degraded · zh · mixed prompt
— MER accuracy pending Ground Truth · 715 ms · verdict: unjudged
請把shoes脫掉可以嗎?
mini_zh_prompt_clean gpt-4o-mini-transcribe · clean · zh · mixed prompt
— MER accuracy pending Ground Truth · 937 ms · verdict: unjudged
請把袖子脫掉可以嗎?
gpt_tw_en_bare_deg gpt-transcribe · degraded · zh-tw + en · bare
— MER accuracy pending Ground Truth · 644 ms · verdict: unjudged
請把 shoes 脫掉可以嗎？
gpt_tw_en_prompt_deg gpt-transcribe · degraded · zh-tw + en · mixed prompt
— MER accuracy pending Ground Truth · 728 ms · verdict: unjudged
請把 shoes 脫掉可以嗎？
gpt_tw_en_prompt_clean gpt-transcribe · clean · zh-tw + en · mixed prompt
— MER accuracy pending Ground Truth · 799 ms · verdict: unjudged
請把 shoes 脫掉可以嗎？
gpt_tw_en_prompt_64k gpt-transcribe · 64k · zh-tw + en · mixed prompt
— MER accuracy pending Ground Truth · 644 ms · verdict: unjudged
請把 shoes 脫掉可以嗎？
gpt_tw_only_prompt_deg gpt-transcribe · degraded · zh-tw · mixed prompt
— MER accuracy pending Ground Truth · 828 ms · verdict: unjudged
請把 shoes 脫掉可以嗎？
Winning configuration
Record the variant and rationale to hand to qa-rails after reviewing this Take.