Take audit: fTMUnCPDUDURCN7rSgSqh
2026-08-22T09:17:46.463Z — 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 · 907 ms · verdict: unjudged
我有這一本書,can you see?
mini_auto_bare_deg gpt-4o-mini-transcribe · degraded · auto · bare
— MER accuracy pending Ground Truth · 714 ms · verdict: unjudged
我有這一本書,can you see?
mini_auto_bare_clean gpt-4o-mini-transcribe · clean · auto · bare
— MER accuracy pending Ground Truth · 2798 ms · verdict: unjudged
我有三本書,Can you see?
mini_auto_prompt_deg gpt-4o-mini-transcribe · degraded · auto · mixed prompt
— MER accuracy pending Ground Truth · 664 ms · verdict: unjudged
我有這一本書,can you see?
mini_auto_prompt_clean gpt-4o-mini-transcribe · clean · auto · mixed prompt
— MER accuracy pending Ground Truth · 1062 ms · verdict: unjudged
我有三本書,can you see?
mini_auto_prompt_64k gpt-4o-mini-transcribe · 64k · auto · mixed prompt
— MER accuracy pending Ground Truth · 893 ms · verdict: unjudged
我有三本書,Can you see?
mini_zh_prompt_deg gpt-4o-mini-transcribe · degraded · zh · mixed prompt
— MER accuracy pending Ground Truth · 729 ms · verdict: unjudged
我有這一本書,Can you see?
mini_zh_prompt_clean gpt-4o-mini-transcribe · clean · zh · mixed prompt
— MER accuracy pending Ground Truth · 829 ms · verdict: unjudged
我有three本書,Can you see?
gpt_tw_en_bare_deg gpt-transcribe · degraded · zh-tw + en · bare
— MER accuracy pending Ground Truth · 840 ms · verdict: unjudged
我有 three 本書，can you see?
gpt_tw_en_prompt_deg gpt-transcribe · degraded · zh-tw + en · mixed prompt
— MER accuracy pending Ground Truth · 877 ms · verdict: unjudged
我有 three 本書，can you see?
gpt_tw_en_prompt_clean gpt-transcribe · clean · zh-tw + en · mixed prompt
— MER accuracy pending Ground Truth · 806 ms · verdict: unjudged
我有 three 本書, can you see?
gpt_tw_en_prompt_64k gpt-transcribe · 64k · zh-tw + en · mixed prompt
— MER accuracy pending Ground Truth · 621 ms · verdict: unjudged
我有 three 本書，can you see?
gpt_tw_only_prompt_deg gpt-transcribe · degraded · zh-tw · mixed prompt
— MER accuracy pending Ground Truth · 725 ms · verdict: unjudged
我有 three 本書，can you see?
Winning configuration
Record the variant and rationale to hand to qa-rails after reviewing this Take.