An open API service indexing awesome lists of open source software.

https://github.com/parthvadhadiya/tensorflow-speech-recognition-challenge

this repository contains end to end python script to train speech data provided by google, evaluate testing data, and submite to competition
https://github.com/parthvadhadiya/tensorflow-speech-recognition-challenge

competition kaggle-competition keras librosa spectrum speech-data speech-recognition tensorflow

Last synced: 3 months ago
JSON representation

this repository contains end to end python script to train speech data provided by google, evaluate testing data, and submite to competition

Awesome Lists containing this project

README

          


# TensorFlow-Speech-Recognition-Challenge

this repository contains end-to-end pipe line to train different speech data provided by google, evaluate testing data, and submite to kaggle competition. (https://www.kaggle.com/c/tensorflow-speech-recognition-challenge)

## Getting Started


clone repo. :- git clone https://github.com/parthvadhadiya/TensorFlow-Speech-Recognition-Challenge

download dataset :- https://www.kaggle.com/c/tensorflow-speech-recognition-challenge/data

### Installing Prerequisites

=> Python3 -3.5.2

=> NumPy -1.13.1

for store and manupulate multidimensional array,

installing numpy:- sudo pip3 install numpy (obviously for windows you can enter without sudo command).

=> librosa -0.5.1

for audio analysis

installing librosa:- sudo pip3 install librosa(you can also use scipy's wav module)

=> keras -2.0.6

high-level neural networks API

installing keras:- https://keras.io/#installation

=> tqdm -4.19.4

an awsome progress meter in terminal

intalling tqdm :- sudo pip3 install tqdm