domerin0 / rnn-speech

Character level speech recognizer using ctc loss with deep rnns in TensorFlow.
MIT License
77 stars 31 forks source link

Merged to one launcher #18

Closed AMairesse closed 8 years ago

AMairesse commented 8 years ago

Hi, I merged train.py into stt.py which seems an appropriate name for a generic launcher. I have also a fix for tensorflow 0.10rc0

I changed my workflow to pr from my master branch, should be easier to follow but github is listing every commit since my first and I hope you won't encounter any trouble to merge...

Next I will probably work to enable tensorboard and add a few graphs in order to see the learning process progress.

Antoine.