I want to build a custom set of phrases for a command-and control application. I guess I want to use CMU's SLM. The SLM documentation shows me this:
cat a.text | text2wfreq > a.wfreq cat a.wfreq | wfreq2vocab -top 20000 > a.vocab cat a.text | text2idngram -vocab a.vocab > a.idngram idngram2lm -idngram a.idngram -vocab a.vocab -binary a.binlm
So now I have a binary language model called a.binlm.
My question is: What steps do I need to take now to get this into sphinx2 ?
Thanks Jeff
Bin language model is used in DecoderIII of Sphinx, decoderII based on TXT language Model. You need read decoder III document.
Sir
I am getting some error during Language model. Help me out. Error
ahmad@HSRD14:~/Speech/CMU-Cam_Toolkit_v2/bin$ text2idngram -vocab $bn.tmp.vocab < $bn.tmp.closed > $bn.tmp.idngram text2idngram Vocab : weather.txt.tmp.vocab N-gram buffer size : 100 Hash table size : 200000 Temp directory : /usr/tmp/ Max open files : 20 FOF size : 10 n : 3 Initialising hash table... Reading vocabulary... Allocating memory for the n-gram buffer... Reading text into the n-gram buffer... 20,000 n-grams processed for each ".", 1,000,000 for each line. .................................................. ........................ Sorting n-grams... Writing sorted n-grams to temporary file /usr/tmp/text2idngram.temp.HSRD14.6331.1 rr_fopen: problems opening /usr/tmp/text2idngram.temp.HSRD14.6331.1 for "w".
Please let me where i m going wrong
ERROR..
Building task ncst Task not previously defined. User has to provide language model and supporting variables
Log in to post a comment.
I want to build a custom set of phrases for a command-and
control application. I guess I want to use CMU's SLM.
The SLM documentation shows me this:
cat a.text | text2wfreq > a.wfreq
cat a.wfreq | wfreq2vocab -top 20000 > a.vocab
cat a.text | text2idngram -vocab a.vocab > a.idngram
idngram2lm -idngram a.idngram -vocab a.vocab -binary a.binlm
So now I have a binary language model called a.binlm.
My question is: What steps do I need to take now to get
this into sphinx2 ?
Thanks
Jeff
Bin language model is used in DecoderIII of Sphinx, decoderII based on TXT language Model. You need read decoder III document.
Sir
I am getting some error during Language model.
Help me out.
Error
ahmad@HSRD14:~/Speech/CMU-Cam_Toolkit_v2/bin$ text2idngram -vocab $bn.tmp.vocab < $bn.tmp.closed > $bn.tmp.idngram
text2idngram
Vocab : weather.txt.tmp.vocab
N-gram buffer size : 100
Hash table size : 200000
Temp directory : /usr/tmp/
Max open files : 20
FOF size : 10
n : 3
Initialising hash table...
Reading vocabulary...
Allocating memory for the n-gram buffer...
Reading text into the n-gram buffer...
20,000 n-grams processed for each ".", 1,000,000 for each line.
..................................................
........................
Sorting n-grams...
Writing sorted n-grams to temporary file /usr/tmp/text2idngram.temp.HSRD14.6331.1
rr_fopen: problems opening /usr/tmp/text2idngram.temp.HSRD14.6331.1 for "w".
Please let me where i m going wrong
ERROR..
Building task ncst
Task not previously defined. User has to provide language model and supporting variables