Take audit: M0cuTMDOKHMGMDb955rwV
2026-08-22T09:33:38.425Z — ray
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 · 660 ms · verdict: unjudged
can I have two 跟你一樣嗎?
mini_auto_bare_deg gpt-4o-mini-transcribe · degraded · auto · bare
— MER accuracy pending Ground Truth · 678 ms · verdict: unjudged
Can I have two 跟你一樣嗎?
mini_auto_bare_clean gpt-4o-mini-transcribe · clean · auto · bare
— MER accuracy pending Ground Truth · 570 ms · verdict: unjudged
Can I have two 跟你一樣嗎?
mini_auto_prompt_deg gpt-4o-mini-transcribe · degraded · auto · mixed prompt
— MER accuracy pending Ground Truth · 725 ms · verdict: unjudged
Can I have two 跟你一樣嗎?
mini_auto_prompt_clean gpt-4o-mini-transcribe · clean · auto · mixed prompt
— MER accuracy pending Ground Truth · 702 ms · verdict: unjudged
Can I have two? 跟你一樣嗎?
mini_auto_prompt_64k gpt-4o-mini-transcribe · 64k · auto · mixed prompt
— MER accuracy pending Ground Truth · 827 ms · verdict: unjudged
Can I have two 跟你一樣嗎?
mini_zh_prompt_deg gpt-4o-mini-transcribe · degraded · zh · mixed prompt
— MER accuracy pending Ground Truth · 656 ms · verdict: unjudged
Can I have two 跟你一樣嗎?
mini_zh_prompt_clean gpt-4o-mini-transcribe · clean · zh · mixed prompt
— MER accuracy pending Ground Truth · 751 ms · verdict: unjudged
Can I have two 跟你一樣嗎?
gpt_tw_en_bare_deg gpt-transcribe · degraded · zh-tw + en · bare
— MER accuracy pending Ground Truth · 607 ms · verdict: unjudged
Can I have two? 跟你一樣嗎？
gpt_tw_en_prompt_deg gpt-transcribe · degraded · zh-tw + en · mixed prompt
— MER accuracy pending Ground Truth · 738 ms · verdict: unjudged
Can I have two? 跟你一樣嗎？
gpt_tw_en_prompt_clean gpt-transcribe · clean · zh-tw + en · mixed prompt
— MER accuracy pending Ground Truth · 753 ms · verdict: unjudged
Can I have two 跟你一樣嗎?
gpt_tw_en_prompt_64k gpt-transcribe · 64k · zh-tw + en · mixed prompt
— MER accuracy pending Ground Truth · 754 ms · verdict: unjudged
Can I have two 跟你一樣嗎?
gpt_tw_only_prompt_deg gpt-transcribe · degraded · zh-tw · mixed prompt
— MER accuracy pending Ground Truth · 772 ms · verdict: unjudged
Can I have two? 跟你一樣嗎？
Winning configuration
Record the variant and rationale to hand to qa-rails after reviewing this Take.