Take audit: EYc9DU0cRXlIw3UPI7E2S
2026-08-22T09:34:07.100Z — 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 · 1570 ms · verdict: unjudged
Can I have some milk? 拜託
mini_auto_bare_deg gpt-4o-mini-transcribe · degraded · auto · bare
— MER accuracy pending Ground Truth · 700 ms · verdict: unjudged
Can I have some milk? 拜託
mini_auto_bare_clean gpt-4o-mini-transcribe · clean · auto · bare
— MER accuracy pending Ground Truth · 690 ms · verdict: unjudged
Can I have some milk? 拜託
mini_auto_prompt_deg gpt-4o-mini-transcribe · degraded · auto · mixed prompt
— MER accuracy pending Ground Truth · 667 ms · verdict: unjudged
Can I have some milk, 拜託
mini_auto_prompt_clean gpt-4o-mini-transcribe · clean · auto · mixed prompt
— MER accuracy pending Ground Truth · 735 ms · verdict: unjudged
Can I have some milk? 拜託
mini_auto_prompt_64k gpt-4o-mini-transcribe · 64k · auto · mixed prompt
— MER accuracy pending Ground Truth · 770 ms · verdict: unjudged
Can I have some milk? 拜託
mini_zh_prompt_deg gpt-4o-mini-transcribe · degraded · zh · mixed prompt
— MER accuracy pending Ground Truth · 684 ms · verdict: unjudged
Can I have some milk? 拜託
mini_zh_prompt_clean gpt-4o-mini-transcribe · clean · zh · mixed prompt
— MER accuracy pending Ground Truth · 687 ms · verdict: unjudged
Can I have some milk? 拜託
gpt_tw_en_bare_deg gpt-transcribe · degraded · zh-tw + en · bare
— MER accuracy pending Ground Truth · 676 ms · verdict: unjudged
Can I have some milk, 拜託.
gpt_tw_en_prompt_deg gpt-transcribe · degraded · zh-tw + en · mixed prompt
— MER accuracy pending Ground Truth · 583 ms · verdict: unjudged
Can I have some milk, please?
gpt_tw_en_prompt_clean gpt-transcribe · clean · zh-tw + en · mixed prompt
— MER accuracy pending Ground Truth · 833 ms · verdict: unjudged
Can I have some milk,拜託.
gpt_tw_en_prompt_64k gpt-transcribe · 64k · zh-tw + en · mixed prompt
— MER accuracy pending Ground Truth · 623 ms · verdict: unjudged
Can I have some milk,拜託。
gpt_tw_only_prompt_deg gpt-transcribe · degraded · zh-tw · mixed prompt
— MER accuracy pending Ground Truth · 729 ms · verdict: unjudged
Can I have some milk,拜託。
Winning configuration
Record the variant and rationale to hand to qa-rails after reviewing this Take.