Tacotron - pytorch implementation

Prerequisite

LJ Speech 1.1, female single speaker dataset.
I follow Kyubyong's DCTTS repo with TensorFlow for preprocessing speech signal data. It actually worked well.

Download the above dataset and modify the path in config.py. And then run the below command. 1st arg: signal prepro, 2nd arg: metadata (train/test split)
```
python prepro.py 1 1
```
The model needs to train 100k+ steps (10+ hours).
```
python train.py
```
After training, you can synthesize some speech from text.
```
python synthesize.py
```

In speech synthesis, the attention module is important. If the model is normally trained, then you can see the monotonic attention like the follow figures.

Name		Name	Last commit message	Last commit date
Latest commit History 11 Commits
assets		assets
samples		samples
.gitignore		.gitignore
README.md		README.md
config.py		config.py
data.py		data.py
lj_eval_idx.npy		lj_eval_idx.npy
model.py		model.py
module.py		module.py
network.py		network.py
prepro.py		prepro.py
synthesize.py		synthesize.py
test_sents.txt		test_sents.txt
train.py		train.py
utils.py		utils.py