Yep it worked without the dash (thank youu!!!):
Reading words.arpa
----5โ10โ15โ20โ25โ30โ35โ40โ45โ50โ55โ60โ65โ70โ75โ80โ85โ90โ95โ100
Identifying n-grams omitted by SRI
----5โ10โ15โ20โ25โ30โ35โ40โ45โ50โ55โ60โ65โ70โ75โ80โ85โ90โ95โ100
Quantizing
----5โ10โ15โ20โ25โ30โ35โ40โ45โ50โ55โ60โ65โ70โ75โ80โ85โ90โ95โ100
Writing trie
----5โ10โ15โ20โ25โ30โ35โ40โ45โ50โ55โ60โ65โ70โ75โ80โ85โ90โ95โ100
SUCCESS
But generate_package gives me the error
4860 unique words read from vocabulary file.
Doesnโt look like a character based model.
Package created in kenlm.scorer
Now it doesnโt say anything about the missing the header. In the vocabulary file I placed all my transcripts, and they are sentences in Romanian, we have some special characters like ฤ, รฎ, ล, ลฃ, รข. I also placed them in the alphabetโฆ