Take audit: -PxDaY9JXpXTEe1yJSsri

2026-08-20T05:55:10.886Z — no tester given

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 · latency — · verdict: unjudged

Engine failed: Variant was not run for this Take

mini_auto_bare_deg gpt-4o-mini-transcribe · degraded · auto · bare — MER accuracy pending Ground Truth · latency — · verdict: unjudged

Engine failed: Variant was not run for this Take

mini_auto_bare_clean gpt-4o-mini-transcribe · clean · auto · bare — MER accuracy pending Ground Truth · latency — · verdict: unjudged

Engine failed: Variant was not run for this Take

mini_auto_prompt_deg gpt-4o-mini-transcribe · degraded · auto · mixed prompt — MER accuracy pending Ground Truth · latency — · verdict: unjudged

Engine failed: Variant was not run for this Take

mini_auto_prompt_clean gpt-4o-mini-transcribe · clean · auto · mixed prompt — MER accuracy pending Ground Truth · latency — · verdict: unjudged

Engine failed: Variant was not run for this Take

mini_auto_prompt_64k gpt-4o-mini-transcribe · 64k · auto · mixed prompt — MER accuracy pending Ground Truth · latency — · verdict: unjudged

Engine failed: Variant was not run for this Take

mini_zh_prompt_deg gpt-4o-mini-transcribe · degraded · zh · mixed prompt — MER accuracy pending Ground Truth · latency — · verdict: unjudged

Engine failed: Variant was not run for this Take

mini_zh_prompt_clean gpt-4o-mini-transcribe · clean · zh · mixed prompt — MER accuracy pending Ground Truth · latency — · verdict: unjudged

Engine failed: Variant was not run for this Take

gpt_tw_en_bare_deg gpt-transcribe · degraded · zh-tw + en · bare — MER accuracy pending Ground Truth · latency — · verdict: unjudged

Engine failed: Variant was not run for this Take

gpt_tw_en_prompt_deg gpt-transcribe · degraded · zh-tw + en · mixed prompt — MER accuracy pending Ground Truth · latency — · verdict: unjudged

Engine failed: Variant was not run for this Take

gpt_tw_en_prompt_clean gpt-transcribe · clean · zh-tw + en · mixed prompt — MER accuracy pending Ground Truth · latency — · verdict: unjudged

Engine failed: Variant was not run for this Take

gpt_tw_en_prompt_64k gpt-transcribe · 64k · zh-tw + en · mixed prompt — MER accuracy pending Ground Truth · latency — · verdict: unjudged

Engine failed: Variant was not run for this Take

gpt_tw_only_prompt_deg gpt-transcribe · degraded · zh-tw · mixed prompt — MER accuracy pending Ground Truth · latency — · verdict: unjudged

Engine failed: Variant was not run for this Take

Winning configuration

Record the variant and rationale to hand to qa-rails after reviewing this Take.