Deep Voice 3

Fork of https://github.com/Kyubyong/deepvoice3 implementation

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

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.

Name		Name	Last commit message	Last commit date
Latest commit History 53 Commits
.ipynb_checkpoints		.ipynb_checkpoints
fn_utils		fn_utils
.gitignore		.gitignore
README.md		README.md
__init__.py		__init__.py
cmudict.dict.txt		cmudict.dict.txt
data_load.py		data_load.py
data_load2.py		data_load2.py
hyperparams.py		hyperparams.py
modules.py		modules.py
networks.py		networks.py
prepro.py		prepro.py
synthesize.py		synthesize.py
temp.txt		temp.txt
test_sents.txt		test_sents.txt
todo.txt		todo.txt
train.py		train.py
utils.py		utils.py