That looks like an IRSTLM-format binary file. You might need the "--text
yes" flag for compile-lm.
You can confirm that the file is in the right format by opening it with a
text viewer such as "less". The ARPA format is defined here:
http://www-speech.sri.com/projects/srilm/manpages/ngram-format.5
Hello again,
I ran compile-lm against the model.lm.es.gz and got the output
model.lm.es.blm but when using 8 0 5 in my moses.ini it crashes with this:
0
> " not blank File: model.es.lm.blm
> Aborted
Is this down to bad artefacts in the language model?
Kind regards,
Lee Ball
Infrastructure Ma
FYI we resolved the problem off-list. KenLM does not load IRST's iARPA
format. You must first run IRST"s compile-lm to generate an ARPA. I
might add an error message specific to this case.
On 07/27/11 09:27, Lee Ball (Applied Language) wrote:
> Hi guys,
>
> I just tried using KenLM out of inte
Hi,
Which ASCII character sequence represents newline in your file? Try
converting to UNIX newlines. Also can you send me the output of
zcat /home/moses/languagemodels/model.es.lm.gz |head -n 10 |gzip >send.gz
(I'm asking you to rezip so that your mail client doesn't convert the
enter
Hi guys,
I just tried using KenLM out of interest for the first time with an old set
of models that were using IRSTLM.
Based on this: http://kheafield.com/code/kenlm/moses/ I changed the settings
from:
[lmodel-file]
1 0 5 /home/moses/languagemodels/model.es.lm.gz
to
[lmodel-file]
8 0 5 /home/m
