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.

Download demo audio trained on LJS and using Ryuchi Yamamoto's pre-trained Mixture of Logistics wavenet
"Scientists at the CERN laboratory say they have discovered a new particle."

1. NVIDIA GPU + CUDA cuDNN

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
   • Alternatively, set load_mel_from_disk=True in hparams.py and update mel-spectrogram paths
5. Install pytorch 0.4
6. Install python requirements or build docker image
   • Install python requirements: pip install -r requirements.txt
   • OR
   • Build docker image: docker build --tag tacotron2 .

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

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

When performing Mel-Spectrogram to Audio synthesis with a WaveNet model, make sure Tacotron 2 and WaveNet were trained on the same mel-spectrogram representation. Follow these steps to use a a simple inference pipeline using griffin-lim:

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

nv-wavenet: Faster than real-time wavenet inference

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.