OpenSeq2Seq icon indicating copy to clipboard operation
OpenSeq2Seq copied to clipboard

Published 20 hours ago • verified publisher icon NVIDIA

language model quantization

Open SibtainRazaJamali opened this issue 5 years ago • 1 comments

SibtainRazaJamali avatar Mar 02 '19 17:03 SibtainRazaJamali

Why is the language model being quantized in script/build_lm.py? Is it a trade of between performance and error rate. How can we use trie and lm.binary file without quantizing?

SibtainRazaJamali avatar Mar 02 '19 17:03 SibtainRazaJamali