Take audit: HnIzu1rBf0fMoWaH0OHYS
2026-08-22T09:15:27.333Z — 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 · 830 ms · verdict: unjudged
這個起司很好吃,Can I have more?
mini_auto_bare_deg gpt-4o-mini-transcribe · degraded · auto · bare
— MER accuracy pending Ground Truth · 718 ms · verdict: unjudged
這個起司很好吃,Can I have more?
mini_auto_bare_clean gpt-4o-mini-transcribe · clean · auto · bare
— MER accuracy pending Ground Truth · 635 ms · verdict: unjudged
這個cheese很好吃,Can I have more?
mini_auto_prompt_deg gpt-4o-mini-transcribe · degraded · auto · mixed prompt
— MER accuracy pending Ground Truth · 841 ms · verdict: unjudged
這個cheese很好吃,Can I have more?
mini_auto_prompt_clean gpt-4o-mini-transcribe · clean · auto · mixed prompt
— MER accuracy pending Ground Truth · 734 ms · verdict: unjudged
這個cheese很好吃,Can I have more?
mini_auto_prompt_64k gpt-4o-mini-transcribe · 64k · auto · mixed prompt
— MER accuracy pending Ground Truth · 694 ms · verdict: unjudged
這個cheese很好吃,Can I have more?
mini_zh_prompt_deg gpt-4o-mini-transcribe · degraded · zh · mixed prompt
— MER accuracy pending Ground Truth · 997 ms · verdict: unjudged
這個cheese很好吃,Can I have more?
mini_zh_prompt_clean gpt-4o-mini-transcribe · clean · zh · mixed prompt
— MER accuracy pending Ground Truth · 838 ms · verdict: unjudged
這個cheese很好吃,can I have more?
gpt_tw_en_bare_deg gpt-transcribe · degraded · zh-tw + en · bare
— MER accuracy pending Ground Truth · 624 ms · verdict: unjudged
這個起司很好吃，Can I have more?
gpt_tw_en_prompt_deg gpt-transcribe · degraded · zh-tw + en · mixed prompt
— MER accuracy pending Ground Truth · 662 ms · verdict: unjudged
這個起司很好吃，Can I have more?
gpt_tw_en_prompt_clean gpt-transcribe · clean · zh-tw + en · mixed prompt
— MER accuracy pending Ground Truth · 647 ms · verdict: unjudged
這個起司很好吃，Can I have more?
gpt_tw_en_prompt_64k gpt-transcribe · 64k · zh-tw + en · mixed prompt
— MER accuracy pending Ground Truth · 674 ms · verdict: unjudged
這個起司很好吃，Can I have more?
gpt_tw_only_prompt_deg gpt-transcribe · degraded · zh-tw · mixed prompt
— MER accuracy pending Ground Truth · 698 ms · verdict: unjudged
這個起司很好吃，Can I have more?
Winning configuration
Record the variant and rationale to hand to qa-rails after reviewing this Take.