Unverified50% confidenceBenchmarkExact time
On the test-other set, B-WER was reduced by 23.9% relative to the CTC-Filter baseline.
1
Sources
50%
Confidence
Long-term
Relevance
9/25/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedCaveman's fixed benchmark test results from 54 runs show a 33.2% reduction in input tokens, with all 18/18 correctness checks passing.66% similarUnverifiedIn tests on 2,456 held-out prompts, increasing the sampling steps from 20 to 50 improved FID only from 27.0 to 26.6 (a gain of 0.4), while removing the shift caused FID to rise from 27.0 to 27.3 and FD-DINOv2 to rise from 218 to 228.62% similarUnverifiedOn the LibriSpeech test-clean benchmark, Whisper large-v3's WER has dropped to around 2%, approaching or in some cases surpassing human annotators (approximately 4–5%).59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/949147API
curl https://kongchang.com/api/v1/knowledge/claims/949147MCP
get_claim(id=949147)