Unverified50% confidenceBenchmarkExact time
In code-switching scenarios, the word error rate (WER) of current best-in-class speech recognition models remains between 15–25%, compared to within 5% for English monolingual scenarios.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/11/2026
First Seen
Valid until: 12/10/2026
Sources
Related Entities
Related Claims
VerifiedASR models such as OpenAI Whisper and Google Speech-to-Text have compressed word error rates to below 5%.70% similarUnverifiedIn a balanced ASR test covering 13 dialects, the Tunisian dialect achieved a word error rate (WER) of 0.478, the highest among all dialects70% similarUnverified传统三段式语音管线中每个模块独立训练，误差会逐级累积，且文字化过程会不可逆地丢失说话者的语调、停顿、情绪等副语言信息69% similarUnverified端侧多语种语音识别在处理夹杂英文技术名词的非英语口述时，会将英文术语按发音音译成本地文字69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/891707API
curl https://kongchang.com/api/v1/knowledge/claims/891707MCP
get_claim(id=891707)