g2p_model.sh

#!/bin/sh
# g2p model generates pronunciation of a words after it is trained. But for training it needs
# at least some words to pronunciation mapping. For our purpose we can use the cmudict already
# provided in Kaldi in $KALDI_HOME/egs/aspire/s5/data/local/dict/cmudict/sphinxdict directory.
# you should run this script from the above directory

g2p.py --train cmudict_SPHINX_40 --devel 5% --write-model model-1
 
g2p.py --train cmudict_SPHINX_40 --devel 5% --write-model model-1
g2p.py --model model-1 --test cmudict_SPHINX_40 > model-1-test
 
g2p.py --model model-1 --ramp-up --train cmudict_SPHINX_40 --devel 5% --write-model model-2
g2p.py --model model-2 --test cmudict_SPHINX_40 > model-2-test
 
g2p.py --model model-2 --ramp-up --train cmudict_SPHINX_40 --devel 5% --write-model model-3
g2p.py --model model-3 --test cmudict_SPHINX_40 > model-3-test
 
g2p.py --model model-3 --ramp-up --train cmudict_SPHINX_40 --devel 5% --write-model model-4
g2p.py --model model-4 --test cmudict_SPHINX_40 > model-4-test
 
g2p.py --model model-4 --ramp-up --train cmudict_SPHINX_40 --devel 5% --write-model model-5
g2p.py --model model-5 --test cmudict_SPHINX_40 > model-5-test
 
g2p.py --model model-5 --ramp-up --train cmudict_SPHINX_40 --devel 5% --write-model model-6
g2p.py --model model-6 --test cmudict_SPHINX_40 > model-6-test
 
g2p.py --model model-6 --ramp-up --train cmudict_SPHINX_40 --devel 5% --write-model model-7
g2p.py --model model-7 --test cmudict_SPHINX_40 > model-7-test

g2p.py --model model-7 --apply words.txt > words.dic