Take audit: 9G0NAeOe-z1uHUNwuGe5e
2026-08-22T09:41:29.324Z — 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 · 674 ms · verdict: unjudged
That is not mine. 那個不是我的。
mini_auto_bare_deg gpt-4o-mini-transcribe · degraded · auto · bare
— MER accuracy pending Ground Truth · 1301 ms · verdict: unjudged
That is not mine. 那個不是我的。
mini_auto_bare_clean gpt-4o-mini-transcribe · clean · auto · bare
— MER accuracy pending Ground Truth · 763 ms · verdict: unjudged
That is not mine. 那個不是我的。
mini_auto_prompt_deg gpt-4o-mini-transcribe · degraded · auto · mixed prompt
— MER accuracy pending Ground Truth · 714 ms · verdict: unjudged
That is not mine. 那個不是我的。
mini_auto_prompt_clean gpt-4o-mini-transcribe · clean · auto · mixed prompt
— MER accuracy pending Ground Truth · 704 ms · verdict: unjudged
That is not mine. 那個不是我的。
mini_auto_prompt_64k gpt-4o-mini-transcribe · 64k · auto · mixed prompt
— MER accuracy pending Ground Truth · 667 ms · verdict: unjudged
That is not mine. 那個不是我的。
mini_zh_prompt_deg gpt-4o-mini-transcribe · degraded · zh · mixed prompt
— MER accuracy pending Ground Truth · 865 ms · verdict: unjudged
That is not mine. 那個不是我的。
mini_zh_prompt_clean gpt-4o-mini-transcribe · clean · zh · mixed prompt
— MER accuracy pending Ground Truth · 690 ms · verdict: unjudged
That is not mine. 那個不是我的。
gpt_tw_en_bare_deg gpt-transcribe · degraded · zh-tw + en · bare
— MER accuracy pending Ground Truth · 595 ms · verdict: unjudged
That is not mine. 那個不是我的。
gpt_tw_en_prompt_deg gpt-transcribe · degraded · zh-tw + en · mixed prompt
— MER accuracy pending Ground Truth · 594 ms · verdict: unjudged
That is not mine. 那個不是我的。
gpt_tw_en_prompt_clean gpt-transcribe · clean · zh-tw + en · mixed prompt
— MER accuracy pending Ground Truth · 626 ms · verdict: unjudged
That is not mine. 那個不是我的。
gpt_tw_en_prompt_64k gpt-transcribe · 64k · zh-tw + en · mixed prompt
— MER accuracy pending Ground Truth · 585 ms · verdict: unjudged
That is not mine. 那個不是我的。
gpt_tw_only_prompt_deg gpt-transcribe · degraded · zh-tw · mixed prompt
— MER accuracy pending Ground Truth · 507 ms · verdict: unjudged
That is not mine. 那個不是我的。
Winning configuration
Record the variant and rationale to hand to qa-rails after reviewing this Take.