In this demo code, I've implemented Tensorflow's Sequence to Sequence model to train a chatbot on the Faulkner at Virginia: An Audio Archive.
- numpy
- scipy
- six
- tensorflow (https://www.tensorflow.org/versions/r0.12/get_started/os_setup.html)
Use pip to install any missing dependencies
To train the bot, edit the seq2seq.ini
file so that mode is set to train like so
mode = train
then run the code like so
python execute.py
To test the bot during or after training, edit the seq2seq.ini
file so that mode is set to test like so
mode = test
then run the code like so
python execute.py
Credit for the vast majority of code here goes to the TensorFlow authors. I've preprocessed the dataset and trained the system. I've also included a quick search function to retrieve results from The University of Virginia Libraries Faulkner at Virginia Audio Archive site. I've also added a objectionable language editing system to avoid the fate of Tay.