Is the pronounce binary under the logios tools ( https://sourceforge.net/p/cmusphinx/code/HEAD/tree/trunk/logios/Tools/MakeDict/bin/x86-linux/)
open source? I want to compile a 64-bit version of it. Also, as a
grapheme-to-phoneme tool, how does it compare to tools like Phonetisaurus?
Usability wise, pronounce has minimal dependencies (libc only), and is easy
to use, while Phonetisaurus feels a little bit complicated, so I feel like
avoiding it, but I'm not sure if I'm missing out by not choosing it. I'm
mainly using grapheme-to-phoneme as an intermediary step prior to
HDecode/HVite processing; which is mainly for generating phonemes for for
OOV words (apparently HVite throws an error and fail to speech-align a
sentence even if its just 1 word that's OOV).
Reginald
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
Is the pronounce binary under the logios tools (
https://sourceforge.net/p/cmusphinx/code/HEAD/tree/trunk/logios/Tools/MakeDict/bin/x86-linux/)
open source? I want to compile a 64-bit version of it. Also, as a
grapheme-to-phoneme tool, how does it compare to tools like Phonetisaurus?
Usability wise, pronounce has minimal dependencies (libc only), and is easy
to use, while Phonetisaurus feels a little bit complicated, so I feel like
avoiding it, but I'm not sure if I'm missing out by not choosing it. I'm
mainly using grapheme-to-phoneme as an intermediary step prior to
HDecode/HVite processing; which is mainly for generating phonemes for for
OOV words (apparently HVite throws an error and fail to speech-align a
sentence even if its just 1 word that's OOV).
No
Phonetisaurus is more accurate