WAVENET FOR SPEECH TO TEXT CONVERSON

WHAT IS IT?

Wavenet speech to text conversation .This is a tensorflow implementation of speech recognition based on DeepMind's WaveNet: A Generative Model for Raw Audio.The main ingredient of WaveNet are causal convolutions. By using causal convolutions, it make sure the model cannot violate the ordering in which we model the data

HOW TO USE?

To run The Inference Script run this command python run.py model-path mp3 path

Sample Command

python run.py asset/train asset/train/sample.mp3

First Argument             MODELPATH            Mention the model path

Second Argument        Input                          Path of Input audio file.

WHAT ARE THE REQUIREMENTS?

To get all the requirements and dependencies installed run the command For GPU - pip install -r gpu_requirements.txt For CPU - pip install -r cpu_requirements.txt

Note

Only Cuda 8 is supported for GPU inference Make Sure to install these depecndecies as admin to all the users sudo apt-get -qq -y install libsndfile-dev sudo apt-get -qq -y install ffmpeg