Hey There,
i do understand what deepspeech is and what it stands for and how it works
ive also download exmaples and pre trained models and ran them and it worked

Currently im trying to build my own model from wav files of my voice
my problem is the following:
i dont understand what each file stands for
for example binary.lm and tire and alphabet.txt and vocabulary
AND the correct way to create them or fill data inside them

Also can i train a model on one word for example have alot of wav files of the same word and train the model on that word or have alot of words to train on but with more than one wav file for one specific word…

Thanks for everyone.
Best Regards

This talk should give you some sort of introduction and you can build upon it reading the docs on github.