hey tom, you can turn off reordering in the decoding by setting this in the ini file: [distortion-limit] 0
also, if you don't need a language model, you don't have to specify 1 in the ini file. i'm not entirely sure if the training script allows no language model but it should be easy to change this behaviour, or just ignore the resulting language model > > > Tom Hoar wrote: >> I've used Moses to build a letter-to-sound rules "black box" for use >> in a text-to-speech and ASR systems. The translation model is trained >> from phrase pairs of orthography (typical words) as the source data >> and phonetic symbols as the target data. In my custom tokenization >> script, I replace all spaces (word boundaries) with a reserved >> character and then inserted spaces between each character such that >> each character in the orthograph and phonetic spellings is one token. >> >> I've build a working translation model using the standard >> train-factored-phrase-model.perl script. My bleu scores are in the >> .97 range but I believe this is irrelavent. In actual use, the >> translations are great. >> >> I'm looking to reduce the training times and speed the translations >> during runtime. In this data the "word" (token) order never changes >> between source and target. So, would it make more sense to use the >> recaser script or possibly even another script that eliminates both >> reordering and language model processing, if such a script exists? >> Can you point me to an appropriate training/tuning scripts and >> training paramaters that would be appropriate for this use? >> >> Thanks. >> Tom >> ------------------------------------------------------------------------ >> >> _______________________________________________ >> Moses-support mailing list >> [email protected] >> http://mailman.mit.edu/mailman/listinfo/moses-support >> > > _______________________________________________ Moses-support mailing list [email protected] http://mailman.mit.edu/mailman/listinfo/moses-support
