It depends on sentence length, alphabet size, and probably other dataset characteristics, so thereโs not much guidance we can give from scratch. You should try it and learn how the model behaves on your data. Training a model on a new dataset is not a turn key solution that you can just apply without experimentation.
Yep, just specify an empty value for the scorer flag when training: --scorer_path ''
On older versions this was the LM binary flag: --lm_binary_path ''