Take audit: EcII7AqeReXzCJYlf8ExM
2026-08-22T09:40:31.798Z — 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 · 806 ms · verdict: unjudged
我要穿shoes,可以進去嗎?
mini_auto_bare_deg gpt-4o-mini-transcribe · degraded · auto · bare
— MER accuracy pending Ground Truth · 824 ms · verdict: unjudged
我要穿shoes,可以進去嗎?
mini_auto_bare_clean gpt-4o-mini-transcribe · clean · auto · bare
— MER accuracy pending Ground Truth · 504 ms · verdict: unjudged
我要刷續費進去嗎?
mini_auto_prompt_deg gpt-4o-mini-transcribe · degraded · auto · mixed prompt
— MER accuracy pending Ground Truth · 754 ms · verdict: unjudged
我要穿shoes,可以進去嗎?
mini_auto_prompt_clean gpt-4o-mini-transcribe · clean · auto · mixed prompt
— MER accuracy pending Ground Truth · 652 ms · verdict: unjudged
我要刷訊可以進去嗎?
mini_auto_prompt_64k gpt-4o-mini-transcribe · 64k · auto · mixed prompt
— MER accuracy pending Ground Truth · 698 ms · verdict: unjudged
我要穿shoes可以進去嗎?
mini_zh_prompt_deg gpt-4o-mini-transcribe · degraded · zh · mixed prompt
— MER accuracy pending Ground Truth · 790 ms · verdict: unjudged
我要穿shoes,可以進去嗎?
mini_zh_prompt_clean gpt-4o-mini-transcribe · clean · zh · mixed prompt
— MER accuracy pending Ground Truth · 1015 ms · verdict: unjudged
我要刷新可以進去嗎?
gpt_tw_en_bare_deg gpt-transcribe · degraded · zh-tw + en · bare
— MER accuracy pending Ground Truth · 540 ms · verdict: unjudged
我要穿 shoes，可以進去嗎？
gpt_tw_en_prompt_deg gpt-transcribe · degraded · zh-tw + en · mixed prompt
— MER accuracy pending Ground Truth · 687 ms · verdict: unjudged
我要穿 shoes，可以進去嗎？
gpt_tw_en_prompt_clean gpt-transcribe · clean · zh-tw + en · mixed prompt
— MER accuracy pending Ground Truth · 1534 ms · verdict: unjudged
我要穿 shoes，可以進去嗎？
gpt_tw_en_prompt_64k gpt-transcribe · 64k · zh-tw + en · mixed prompt
— MER accuracy pending Ground Truth · 787 ms · verdict: unjudged
我要穿 shoes，可以進去嗎？
gpt_tw_only_prompt_deg gpt-transcribe · degraded · zh-tw · mixed prompt
— MER accuracy pending Ground Truth · 588 ms · verdict: unjudged
我要穿 shoes，可以進去嗎？
Winning configuration
Record the variant and rationale to hand to qa-rails after reviewing this Take.