Unverified50% confidenceBenchmarkExact time
Marimba's speaker counting (0/1/2/3+) accuracy exceeds that of pyannote 3.1.
1
Sources
50%
Confidence
Long-term
Relevance
11/16/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedMarimba achieves 0.93 accuracy on the four-class Speech Commands task.76% similarUnverifiedVASPO improves average accuracy by 2.59 percentage points over PPO on Qwen3-4B and by 1.81 percentage points on OLMo3-7B.61% similarUnverifiedIn the task of determining the type of user utterance request, Qwen3.6-35B-A3B achieved an accuracy of 92.6%, with a judgment time of 306ms.60% similarUnverifiedOn the Joyo-Kanji-Yomi benchmark, Ruby-OPD achieves an accuracy of 97.13%, a Target Phoneme Error Rate (Target PER) of 2.02%, a Sentence-level Phoneme Error Rate (Sentence PER) of 0.70%, and a Sentence-level Character Error Rate (Sentence CER) of 4.21% under raw text input.60% similarUnverifiedMarimba's binary vocabulary judgment has a maximum ECE of 0.08.57% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1173847API
curl https://kongchang.com/api/v1/knowledge/claims/1173847MCP
get_claim(id=1173847)