Take audit: YiruBSERPOj43FmXFx5eg
2026-08-22T09:21:12.955Z — 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 · 655 ms · verdict: unjudged
I'm eight years old 我八歲了
mini_auto_bare_deg gpt-4o-mini-transcribe · degraded · auto · bare
— MER accuracy pending Ground Truth · 704 ms · verdict: unjudged
I'm eight years old. 我八歲了。
mini_auto_bare_clean gpt-4o-mini-transcribe · clean · auto · bare
— MER accuracy pending Ground Truth · 542 ms · verdict: unjudged
I'm eight years old. 我八歲了。
mini_auto_prompt_deg gpt-4o-mini-transcribe · degraded · auto · mixed prompt
— MER accuracy pending Ground Truth · 712 ms · verdict: unjudged
I'm eight years old. 我八歲了。
mini_auto_prompt_clean gpt-4o-mini-transcribe · clean · auto · mixed prompt
— MER accuracy pending Ground Truth · 691 ms · verdict: unjudged
I'm eight years old. 我八歲了。
mini_auto_prompt_64k gpt-4o-mini-transcribe · 64k · auto · mixed prompt
— MER accuracy pending Ground Truth · 685 ms · verdict: unjudged
I'm eight years old. 我八歲了。
mini_zh_prompt_deg gpt-4o-mini-transcribe · degraded · zh · mixed prompt
— MER accuracy pending Ground Truth · 970 ms · verdict: unjudged
I'm eight years old. 我八歲了。
mini_zh_prompt_clean gpt-4o-mini-transcribe · clean · zh · mixed prompt
— MER accuracy pending Ground Truth · 1133 ms · verdict: unjudged
I'm eight years old. 我八歲了。
gpt_tw_en_bare_deg gpt-transcribe · degraded · zh-tw + en · bare
— MER accuracy pending Ground Truth · 735 ms · verdict: unjudged
I'm eight years old. 我八歲了。
gpt_tw_en_prompt_deg gpt-transcribe · degraded · zh-tw + en · mixed prompt
— MER accuracy pending Ground Truth · 768 ms · verdict: unjudged
I'm eight years old. 我八歲了。
gpt_tw_en_prompt_clean gpt-transcribe · clean · zh-tw + en · mixed prompt
— MER accuracy pending Ground Truth · 685 ms · verdict: unjudged
I'm eight years old. 我八歲了。
gpt_tw_en_prompt_64k gpt-transcribe · 64k · zh-tw + en · mixed prompt
— MER accuracy pending Ground Truth · 770 ms · verdict: unjudged
I'm eight years old. 我八歲了。
gpt_tw_only_prompt_deg gpt-transcribe · degraded · zh-tw · mixed prompt
— MER accuracy pending Ground Truth · 653 ms · verdict: unjudged
I'm eight years old. 我八歲了。
Winning configuration
Record the variant and rationale to hand to qa-rails after reviewing this Take.