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.
6 Commits
1 Branch
2.7 MiB
 
 
Tree: 25a267dfbb
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from '25a267dfbb'
${ noResults }
 ZIP  TAR.GZ
Rafael Valle 25a267dfbb inference.ipynb: adding notebook for griffin-lim inference 6 years ago
LICENSE adding readme and license 6 years ago
README.md README.md: add linking to apex repo 6 years ago
inference.ipynb inference.ipynb: adding notebook for griffin-lim inference 6 years ago
ljs_audio_text_test_filelist.txt adding txt files 6 years ago
ljs_audio_text_train_filelist.txt adding txt files 6 years ago
ljs_audio_text_val_filelist.txt adding txt files 6 years ago
requirements.txt adding txt files 6 years ago
tensorboard.png tensorboard.png: adding tensorboard image 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' *.txt
  5. Install pytorch 0.4
  6. Install python requirements or use docker container (tbd)
    • Install python requirements: pip install requirements.txt
    • OR
    • Docker container (tbd)

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

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 is inspired or uses code from the following repos: Ryuchi Yamamoto, Keith Ito, Prem Seetharaman.

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