Take audit: ceWcThcjv9fAn0fbwKox5
2026-08-22T09:36:10.547Z — ray
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 · 932 ms · verdict: unjudged
買秀石是紅色的,do you like them?
mini_auto_bare_deg gpt-4o-mini-transcribe · degraded · auto · bare
— MER accuracy pending Ground Truth · 852 ms · verdict: unjudged
買秀是紅色的,do you like them?
mini_auto_bare_clean gpt-4o-mini-transcribe · clean · auto · bare
— MER accuracy pending Ground Truth · 1483 ms · verdict: unjudged
My shoes are red. Do you like them?
mini_auto_prompt_deg gpt-4o-mini-transcribe · degraded · auto · mixed prompt
— MER accuracy pending Ground Truth · 686 ms · verdict: unjudged
滿秀詞是紅色的,do you like them?
mini_auto_prompt_clean gpt-4o-mini-transcribe · clean · auto · mixed prompt
— MER accuracy pending Ground Truth · 638 ms · verdict: unjudged
My shoes are red, do you like them?
mini_auto_prompt_64k gpt-4o-mini-transcribe · 64k · auto · mixed prompt
— MER accuracy pending Ground Truth · 697 ms · verdict: unjudged
買秀石是紅色的,do you like them?
mini_zh_prompt_deg gpt-4o-mini-transcribe · degraded · zh · mixed prompt
— MER accuracy pending Ground Truth · 684 ms · verdict: unjudged
買秀石是紅色的,Do you like them?
mini_zh_prompt_clean gpt-4o-mini-transcribe · clean · zh · mixed prompt
— MER accuracy pending Ground Truth · 721 ms · verdict: unjudged
My shoes are red. Do you like them?
gpt_tw_en_bare_deg gpt-transcribe · degraded · zh-tw + en · bare
— MER accuracy pending Ground Truth · 636 ms · verdict: unjudged
買袖子是紅色的，Do you like them?
gpt_tw_en_prompt_deg gpt-transcribe · degraded · zh-tw + en · mixed prompt
— MER accuracy pending Ground Truth · 984 ms · verdict: unjudged
My shoes is red. Do you like them?
gpt_tw_en_prompt_clean gpt-transcribe · clean · zh-tw + en · mixed prompt
— MER accuracy pending Ground Truth · 646 ms · verdict: unjudged
My shoes 是紅色的,do you like them?
gpt_tw_en_prompt_64k gpt-transcribe · 64k · zh-tw + en · mixed prompt
— MER accuracy pending Ground Truth · 685 ms · verdict: unjudged
My shoes is red. Do you like them?
gpt_tw_only_prompt_deg gpt-transcribe · degraded · zh-tw · mixed prompt
— MER accuracy pending Ground Truth · 804 ms · verdict: unjudged
My shoes is red. Do you like them?
Winning configuration
Record the variant and rationale to hand to qa-rails after reviewing this Take.