/Speech-Recognition-of-Digits-using-Tensorflow

Implementing LSTM Recurrent Neural Nets to recognize spoken digits using Tensorflow.

Primary LanguagePythonMIT LicenseMIT

# Speech Recognition of Digits using Tensorflow

This repository demonstrates a Tensorflow implementation of Speech Recognition. We build an LSTM recurrent neural network using the TFLearn high level Tensorflow-based library to train on a labeled dataset of spoken digits. Then we test it on spoken digits.

Dependencies

  1. tensorflow (https://www.tensorflow.org/versions/r0.12/get_started/os_setup.html)
  2. tflearn (http://tflearn.org/)
  3. future

Use pip to install any missing dependencies

Usage

python demo.py

  • Run this code line in terminal.
  • This downloads the dataset into the 'data' folder and initiates the training process.
  • It will take a couple hours to train fully.
  • You can then test the trained model on your own .wav samples of spoken digits.