Hello!

I need some help with moses training process.

1) What are the system specifications that are required for training
process? In the "Build a Baseline
System<http://www.statmt.org/moses/?n=Moses.Baseline>" section
it is said that example uses 120 Gb Ram. Is it a mistake? Or maybe I didn't
understood it correctly?
2) I'm trying to run the training process. I use the same corpuses from the
instructions. All corpuses are clean, tokenized and etc. I get the
following error message directly during the training:
*"ERROR: Giza did not produce the output file
/home/administrator/working/train/giza.fr-en/fr-en.A3.final. Is your corpus
clean (reasonably-sized sentences)? at
/home/administator/mosesdecoder/scripts/training/train-model.perl line
1166."*
I would be very grateful if you help me to solve this problem.

Sorry for my bad English, I'm from Russia.

Yours truly,
Ivanov Kirill
_______________________________________________
Moses-support mailing list
[email protected]
http://mailman.mit.edu/mailman/listinfo/moses-support

Reply via email to