Unverified50% confidenceBenchmarkExact time
Granite Speech 5.0 2B ranks second on the Open ASR Leaderboard with an average English word error rate (WER) of 5.68%.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/22/2026
First Seen
Valid until: 11/5/2026
Sources
Related Entities
Related Claims
VerifiedASR models such as OpenAI Whisper and Google Speech-to-Text have compressed word error rates to below 5%.65% 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.62% similarUnverifiedspeechocean762 is a commonly used public benchmark dataset in the pronunciation assessment field, containing approximately 5,000 sentence-level recordings from native and non-native English speakers, annotated with human scoring labels at the phoneme, word, and sentence levels62% similarUnverifiedIn a balanced ASR test covering 13 dialects, the Tunisian dialect achieved a word error rate (WER) of 0.478, the highest among all dialects60% similarUnverifiedThe author emphasizes that 5.05% is a perplexity reduction at the language model validation level, not an improvement in benchmark accuracy.59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1084736API
curl https://kongchang.com/api/v1/knowledge/claims/1084736MCP
get_claim(id=1084736)