search

karanvivekbhargava / obamanet

ObamaNet : Photo-realistic lip-sync from audio (Unofficial port)
MIT License
235 stars 71 forks source link

Where is the Char2wav in your implementation ? #1

Closed mazzzystar closed 6 years ago

mazzzystar commented 6 years ago

I read the paper and the author said, he used Char2wav to train the audio to make using obama's voice to speak other words, but I didn't find this part of using Obama's voice to train text2voice, could you help to find that ?

karanvivekbhargava commented 6 years ago

Hey @fancoo this project was finished in approximately three weeks. Hence I didn't have the time to make all the models. I do plan to do it later.

lvZic commented 2 years ago

Hey @fancoo this project was finished in approximately three weeks. Hence I didn't have the time to make all the models. I do plan to do it later.

hi, have u added the Char2wav part yet?

mazzzystar commented 2 years ago

@lvZic sorry I didn't finished that in this project. But there are a lot of methods to construct a text2voice for a specific person, such as Tacotron.

lvZic commented 2 years ago

@lvZic sorry I didn't finished that in this project. But there are a lot of methods to construct a text2voice for a specific person, such as Tacotron.

thanks, Tacotron can do it too. Actually, what I need is the Vocoder feature, and I will have a look.