Open SibtainRazaJamali opened 5 years ago
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?
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?