Challenge Summary: Create a model to recognize 12 spoken words in a dataset that also includes words that are intended to be unrecognizable and silence.
Download dataset from: https://www.kaggle.com/c/tensorflow-speech-recognition-challenge/data
If link isn't available google "TensorFlow Speech Recognition Challenge".
Dependencies:
To run:
$ conda create env -f environment.yml
$ source activate sreg_venv
(sreg_venv)$ cd src
(sreg_venv)$ jupyter notebook...and once the notebook opens run, press shift+enter to run each cell.