Closed morevnaproject closed 3 years ago
We've got Rhubarb feature merged just now. - #50 ^__^
@morevnaproject Great! Can you kindly let me know how you are converting the phonemes to rhubarb shapes? I am trying to add a function to my project to convert the cmu-sphinx phonemes to rhubarb shapes.
I can get the phonemes from the cmu dictionary along with the time for each phonemes:
{ word: 'THANK', value: 'TH AE NG K' }
and I can get the shape set for the word:
A 0
C 0.26
A 0.46
B 0.065
What I am doing is grouping each shapes to some phonemes and look it up for each word's phoneme set. It works somewhat, but there are some issues sometimes:
/*A*/ ["P", "B", "M"],
/*B*/ ["K", "S", "T", "EE", "IY", "IH"],
/*C*/ ["EH", "AE", "AH", "Schwa", "EY", "AY", "HH", "G", "CH", "JH", "R", "Y"],
/*D*/ ["AA"],
/*E*/ ["AO", "ER", "SH", "ZH"],
/*F*/ ["UW", "OW", "W", "UH", "AW", "OY"],
/*G*/ ["F", "V"],
/*H*/ ["L", "N", "NG", "T", "D", "TH", "DH", "S", "Z", "D"],
my question now is how I can properly convert this to correct rhubarb shape set. There are some differences with Rhubarb's results and mine. I contacted Rhubarb author and he said, the algorithm is more complex than a simple lookup and suggested me to look into papagayo-ng.
It would be great if you could let me know what logic you are using for converting the phonemes to rhubarb shapes. I tried looking into the code, but I dont know python, so couldn't figure it out. :cry:
Thanks
nice
Interesting project to consider - https://github.com/DanielSWolf/rhubarb-lip-sync