Unverified50% confidenceBenchmarkExact time
In the same fine-tuning, FLEURS English WER changed only from 11.04% to 10.42%, and FLEURS Arabic from 12.67% to 11.41%, so the original language capabilities degraded hardly at all.
1
Sources
50%
Confidence
Long-term
Relevance
10/17/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedParakeet Redux's English word error rate (WER) increased from 6.26 to 6.55, its multilingual score improved from 11.62 to 10.56, and its long-audio score improved from 2.71 to 2.51.67% similarUnverifiedIn a balanced ASR test covering 13 dialects, the Tunisian dialect achieved a word error rate (WER) of 0.478, the highest among all dialects65% similarUnverifiedIn general-purpose corpora such as Common Crawl, English typically accounts for more than 45%, while Portuguese accounts for less than 2%.64% similarUnverified通用大模型在多层嵌套从句、修辞性倒装等复杂阿拉伯语场景中准确率显著下降63% similarUnverifiedIn 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.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1053535API
curl https://kongchang.com/api/v1/knowledge/claims/1053535MCP
get_claim(id=1053535)