dan
/
tacotron2
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
32 Commits
1 Branch
2.7 MiB
 
 
Tree: b20765a3dc
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from 'b20765a3dc'
${ noResults }
 ZIP  TAR.GZ
Raul Puri b20765a3dc 0.4 scalar tensor padding update 6 years ago
filelists changing structure for better organization 6 years ago
text text/: adding Keith Itos text pre-processing 6 years ago
Dockerfile Dockerfile: adding dockerfile 6 years ago
LICENSE Update license such that it appears on repo fron tpage 6 years ago
README.md README.md: updating readme to include docker setup 6 years ago
audio_processing.py adding python files 6 years ago
data_utils.py adding python files 6 years ago
distributed.py adding python files 6 years ago
fp16_optimizer.py adding python files 6 years ago
hparams.py hparams.py: adapting to new structure, deleting filelists from main 6 years ago
inference.ipynb inference.ipynb: updating 6 years ago
layers.py adding python files 6 years ago
logger.py adding python files 6 years ago
loss_function.py adding python files 6 years ago
loss_scaler.py adding python files 6 years ago
model.py 0.4 scalar tensor padding update 6 years ago
multiproc.py adding python files 6 years ago
plotting_utils.py adding python files 6 years ago
requirements.txt requirements.txt: updating tensorflow requirements 6 years ago
stft.py adding python files 6 years ago
tensorboard.png tensorboard.png: adding tensorboard image 6 years ago
train.py train.py: layout changes 6 years ago
utils.py mask utils update for 0.4 cuda 6 years ago

README.md

Tacotron 2 (without wavenet)

Tacotron 2 PyTorch implementation of Natural TTS Synthesis By Conditioning Wavenet On Mel Spectrogram Predictions.

This implementation includes distributed and fp16 support and uses the LJSpeech dataset.

Distributed and FP16 support relies on work by Christian Sarofeen and NVIDIA's Apex Library.

Alignment, Predicted Mel Spectrogram, Target Mel Spectrogram

Pre-requisites

  1. NVIDIA GPU + CUDA cuDNN

Setup

  1. Download and extract the LJ Speech dataset
  2. Clone this repo: git clone https://github.com/NVIDIA/tacotron2.git
  3. CD into this repo: cd tacotron2
  4. Update .wav paths: sed -i -- 's,DUMMY,ljs_dataset_folder/wavs,g' filelists/*.txt
  5. Install pytorch 0.4
  6. Install python requirements or build docker image
    • Install python requirements: pip install requirements.txt
    • OR
    • Build docker image: docker build --tag tacotron2 .

Training

  1. python train.py --output_directory=outdir --log_directory=logdir
  2. (OPTIONAL) tensorboard --logdir=outdir/logdir

Multi-GPU (distributed) and FP16 Training

  1. python -m multiproc train.py --output_directory=outdir --log_directory=logdir --hparams=distributed_run=True,fp16_run=True

Inference

  1. jupyter notebook --ip=127.0.0.1 --port=31337
  2. load inference.ipynb

Related repos

nv-wavenet: Faster than real-time wavenet inference

Acknowledgements

This implementation uses code from the following repos: Keith Ito, Prem Seetharaman as described in our code.

We are inspired by Ryuchi Yamamoto's Tacotron PyTorch implementation.

We are thankful to the Tacotron 2 paper authors, specially Jonathan Shen, Yuxuan Wang and Zongheng Yang.