bejuryu / deepvoice3 Public

forked from Kyubyong/deepvoice3

Notifications You must be signed in to change notification settings
Fork 0
Star 0

Tensorflow Implementation of Deep Voice 3

0 stars 113 forks Branches Tags Activity

Notifications

Name		Name	Last commit message	Last commit date
Latest commit History 8 Commits
README.md		README.md
data_load.py		data_load.py
hyperparams.py		hyperparams.py
modules.py		modules.py
networks.py		networks.py
prepro.py		prepro.py
synthesize.py		synthesize.py
test_sents.txt		test_sents.txt
train.py		train.py
utils.py		utils.py

Repository files navigation

Deep Voice 3

Work In Progress

This is a tensorflow implementation of DEEP VOICE 3: 2000-SPEAKER NEURAL TEXT-TO-SPEECH. For now I'm focusing on single speaker synthesis.

Data

I use The LJ Speech Dataset.

File Description

hyperparams.py: hyper parameters
prepro.py: creates inputs and targets, i.e., mel spectrogram, magnitude, and dones.
data_load.py
utils.py: several custom operational functions.
modules.py: building blocks for the networks.
networks.py: encoder, decoder, and converter
train.py: train
synthesize.py: inference
test_sents.txt: some test sentences in the paper.

About

Tensorflow Implementation of Deep Voice 3

Report repository

Releases

No releases published

Packages

No packages published

Languages

Python 100.0%