Take audit: oMkp-tNR4_bW0aWFz_sH5

2026-08-22T09:40:48.148Z — 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 · 513 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 · 530 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 · 714 ms · verdict: unjudged

可以安和送牛,拜託

mini_auto_prompt_deg gpt-4o-mini-transcribe · degraded · auto · mixed prompt — MER accuracy pending Ground Truth · 705 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 · 726 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 · 774 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 · 727 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 · 715 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 · 588 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 · 785 ms · verdict: unjudged

Can I have some milk,拜託。

gpt_tw_en_prompt_clean gpt-transcribe · clean · zh-tw + en · mixed prompt — MER accuracy pending Ground Truth · 585 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 · 662 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 · 797 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.