Unverified50% confidenceBenchmarkExact time
When using the Prompt-SLAM-ASR-7B model with a 2,000-word bias list, B-WER on the test-clean set was reduced by 23.4% relative to the CTC-Filter baseline.
1
Sources
50%
Confidence
Long-term
Relevance
9/25/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIn real-environment A/B testing, the post-trained checkpoint reduced the tool-call failure rate by 21.2% relatively compared to the earlier version.71% similarUnverifiedOn Track B, the flat RAG baseline can detect 76%–97% of true contradictions, but produces false positives on 16%–43% of surface-similar safe drafts (the specific ratio depends on the backend).63% similarUnverified当前主流 ASR 引擎的通用词错率（WER）已降至5%以下，但在医疗垂直领域的专有名词上错误率可能飙升至15%-30%，除非进行领域微调和自定义词典配置63% similarUnverified4-bit quantization compared to FP16 typically results in a 0.5–2% drop in benchmark accuracy.62% similarUnverified如果模型跑BF16训练但DCGM_FI_PROF_PIPE_TENSOR_ACTIVE指标长期低于30%，基本可以断定算力被严重浪费61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/949146API
curl https://kongchang.com/api/v1/knowledge/claims/949146MCP
get_claim(id=949146)