Audiobooks for DeepSpeech and how process audio books

Hello guys,

Any one can suggest solution to process audio books for DeepSpeech. I went through this article https://medium.com/@klintcho/creating-an-open-speech-recognition-dataset-for-almost-any-language-c532fb2bc0cf where guy suggest aeneas library.

Maybe there another way how process audio books, any help would be appreciated. Thank you

Can you explain more on what you are trying to achieve ?

Yes, I am trying to increase total hours of training data. Right now I have builded model on 8 hours and no more data is available. So I decided to convert audio books so DeepSpeech can understand it, looking for some guide lines how to do it.

I found some audio books and have seen single example how to do it (link above), I was wondering is there any other solutions as well available or some have dones something.

You should have a look at DSAlign that @Tilman_Kamp is working on

As usually thank you MEN! I will look at that solution