Take audit: xoyWmFECgxKrUNuqXWiBO
2026-08-22T09:39:31.889Z — 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 · 673 ms · verdict: unjudged
我也要,I want it too.
mini_auto_bare_deg gpt-4o-mini-transcribe · degraded · auto · bare
— MER accuracy pending Ground Truth · 678 ms · verdict: unjudged
我也要,I want it too.
mini_auto_bare_clean gpt-4o-mini-transcribe · clean · auto · bare
— MER accuracy pending Ground Truth · 792 ms · verdict: unjudged
我也要,I want it too.
mini_auto_prompt_deg gpt-4o-mini-transcribe · degraded · auto · mixed prompt
— MER accuracy pending Ground Truth · 728 ms · verdict: unjudged
我也要 I want it, too.
mini_auto_prompt_clean gpt-4o-mini-transcribe · clean · auto · mixed prompt
— MER accuracy pending Ground Truth · 743 ms · verdict: unjudged
我也要,I want it too.
mini_auto_prompt_64k gpt-4o-mini-transcribe · 64k · auto · mixed prompt
— MER accuracy pending Ground Truth · 755 ms · verdict: unjudged
我也要 I want it too.
mini_zh_prompt_deg gpt-4o-mini-transcribe · degraded · zh · mixed prompt
— MER accuracy pending Ground Truth · 706 ms · verdict: unjudged
我也要I want it too.
mini_zh_prompt_clean gpt-4o-mini-transcribe · clean · zh · mixed prompt
— MER accuracy pending Ground Truth · 695 ms · verdict: unjudged
我也要I want it too.
gpt_tw_en_bare_deg gpt-transcribe · degraded · zh-tw + en · bare
— MER accuracy pending Ground Truth · 662 ms · verdict: unjudged
我也要，I want it too.
gpt_tw_en_prompt_deg gpt-transcribe · degraded · zh-tw + en · mixed prompt
— MER accuracy pending Ground Truth · 833 ms · verdict: unjudged
我也要，I want it too.
gpt_tw_en_prompt_clean gpt-transcribe · clean · zh-tw + en · mixed prompt
— MER accuracy pending Ground Truth · 741 ms · verdict: unjudged
我也要，I want it too.
gpt_tw_en_prompt_64k gpt-transcribe · 64k · zh-tw + en · mixed prompt
— MER accuracy pending Ground Truth · 841 ms · verdict: unjudged
我也要，I want it too.
gpt_tw_only_prompt_deg gpt-transcribe · degraded · zh-tw · mixed prompt
— MER accuracy pending Ground Truth · 729 ms · verdict: unjudged
我也要，I want it too.
Winning configuration
Record the variant and rationale to hand to qa-rails after reviewing this Take.