[asterisk-users] Speech To Text on linux with asterisk

[Nickolay V. Shmyrev]

В Втр, 14/09/2010 в 14:00 +0530, DHAVAL INDRODIYA пишет:
> Thanks for update.
> 
> is there any command for using sphinix to convert speech to text

Yes, first of all make sure you compiled latest snapshot. Then run

# sphinx_lm_sort <  lm_giga_20k_nvp_3gram.arpa >
lm_giga_20k_nvp_3gram.arpa.sorted

# sphinx_lm_convert -i lm_giga_20k_nvp_3gram.arpa.sorted -o
lm_giga_20k_nvp_3gram.lm.DMP

This will create a language model lm_giga_20k_nvp_3gram.lm.DMP

And finally convert audio

pocketsphinx_continuous -infile your_audio_file.wav -samprate 8000 \
-hmm Communicator_semi_40.cd_semi_6000 -lm lm_giga_20k_nvp_3gram.lm.DMP

--
Nexiwave - Speech Mining Solution For Call Centers
http://nexiwave.com
-------------- next part --------------
A non-text attachment was scrubbed...
Name: not available
Type: application/pgp-signature
Size: 198 bytes
Desc: This is a digitally signed message part
Url : http://lists.digium.com/pipermail/asterisk-users/attachments/20100914/52411161/attachment.pgp