Instructions?

[jakelewis3d]

First off, a big thank you for posting this code.

So far I've compiled the Air app in FlashDevelop and ran it in the standalone player. I 'Load neural network' then 'Run network' to hear the default speech and see a list of what I assume are numbered visemes , with spaces for the silence between words. Nice.

What I'd like to see next is the 3d avatar speak some of my own test audios. I can see all the 3d .as classes , but I'm not sure how to build anything. I see several classes that extend Sprite, is there another project file that I'm missing?

Many thanks, Jake

[s-soltys]

Hi Jake!

Thanks for your interest in this project. I uploaded the code after quite some time since I last used it, so I'll need to take a closer look. I'll get back to you during the weekend with a clear instruction on how to compile and properly use it. Thanks for your patience!

Szymon

[jakelewis3d]

Great.

I have a large selection of TTS audio that I already have phoneme data for (albeit likely in a different selection to those you use) and I'd like to use them as training data for the neural network.

Regards, Jake

On Wed, Feb 10, 2016 at 4:13 PM, s-soltys [email protected] wrote:

Hi Jake!

Thanks for your interest in this project. I uploaded the code after quite some time since I last used it, so I'll need to take a closer look. I'll get back to you during the weekend with a clear instruction on how to compile and properly use it. Thanks for your patience!

Szymon

— Reply to this email directly or view it on GitHub https://github.com/s-soltys/LipSync/issues/1#issuecomment-182584157.

[madhawav]

@jakelewis3d Did you get it working? Or did you find an alternate solution?