israelg99 / deepvoice

Deep Voice: Real-time Neural Text-to-Speech

   

A contributor to:      

My work is serving customers such as Bank of America, Wells Fargo, US Army, Citi, Disney, etc...
My Word2Vec work has been cited in 4 scientific and academic papers on Springer.
My blog (outdated)

Favorite tools:

deepvoice's Issues

How long does it take to synthesise an audio from text?

Dataset for TTS

Hi @israelg99,
Are you still working on this project ? I don't see any update in your project for long time. I guess you don't have any dataset to train TTS model. I think you can try Bibble dataset by @Kyubyong (https://github.com/Kyubyong/tacotron).
I hope that I can see some of your results soon :).

Tutorial? Documentation? Anything?

May I ask how to use it?

It is a great idea and contribution to code the deep voice as 99% people don't know how to use baidu's one.

May I ask how to use your deep voice? thanks.

Future plans

Hi, I have two questions:

1. What are your future plans for this repo?
2. And were you able to merge your code to the main Keras repo?

Thanks.

When will you release the code of wavenet-based architecture?

Thanks for your works! I have not good ideas to add the local conditioning to the wavenet. Would you please give me some advice or when will you release the code of wavenet-based architecture?