vocalist 0.0.1.dev1

A package to convert speech to long-form work-flows, using plugable trained NLP models

Vocalist

This is a simple project still in very early development, meant to be used to parse speech into text. In its current state, it only works on Mac, and only where a compatible version of PortAudio has been installed.

It was built following the tutorial found here: https://realpython.com/python-speech-recognition/

Setup

Using Homebrew, install PortAudio:

$ brew install portaudio 

From there you can install dependencies as you normally would:

$ pip install -r requirements.txt

Usage

If you want to call it directly just run the package as is:

$ python ./main.py

It's not currently deployed for package management.