search

calpoly-csai / swanton

Swanton Pacific Ranch chatbot with a knowledge graph
MIT License
3 stars 1 forks source link

Mozilla Text-To-Speech #19

Open chidiewenike opened 4 years ago

chidiewenike commented 4 years ago

Objective

Test the Mozilla Text-To-Speech module as an offline TTS option which sounds more natural and human-like.

Key Result

A function which takes a string as input to the function and outputs the string as audio.

Details

The current TTS solution provides decent output with preferred memory usage & runtime. The next step would be a deep-learning approach which traditionally allows for more natural-sounding speech. Mozilla's Text-To-Speech module shows promise and could be a possible solution. The output audio will need to be tested/analyzed as well as benchmarking memory usage/runtime.

chidiewenike commented 4 years ago

Discovered by @snekiam and ran by @gwholland3 to setup TTS on a Mac:

  1. python3 -m pip install -r requirements.txt

  2. python3 setup.py develop

gwholland3 commented 4 years ago

Docker image of Mozilla's TTS system using LJSpeech Tacotron2 English model and Multiband MelGAN vocoder:

https://github.com/synesthesiam/docker-mozillatts

Install Docker and follow the "Using" instructions on the README.