malarinv
/
tacotron2
mirror of https://github.com/malarinv/tacotron2
1
0
Fork 0
Code Issues Releases Wiki Activity

README.md: clarifying terminology

experiments
rafaelvalle 2019-04-03 14:59:20 -07:00
parent e3d2d0a5ef
commit c76ac3b211
1 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
README.md
View File

@ -3,10 +3,10 @@
PyTorch implementation of [Natural TTS Synthesis By Conditioning
Wavenet On Mel Spectrogram Predictions](https://arxiv.org/pdf/1712.05884.pdf).
This implementation includes **distributed** and **mixed precision** support
This implementation includes **distributed** and **automatic mixed precision** support
and uses the [LJSpeech dataset](https://keithito.com/LJ-Speech-Dataset/).
Distributed and Mixed Precision support relies on NVIDIA's [Apex] and [AMP].
Distributed and Automatic Mixed Precision support relies on NVIDIA's [Apex] and [AMP].
Visit our [website] for audio samples using our published [Tacotron 2] and
[WaveGlow] models.
@ -40,7 +40,7 @@ By default, the dataset dependent text embedding layers are [ignored]
1. Download our published [Tacotron 2] model
2. `python train.py --output_directory=outdir --log_directory=logdir -c tacotron2_statedict.pt --warm_start`
## Multi-GPU (distributed) and Mixed Precision Training
## Multi-GPU (distributed) and Automatic Mixed Precision Training
1. `python -m multiproc train.py --output_directory=outdir --log_directory=logdir --hparams=distributed_run=True,fp16_run=True`
## Inference demo
@ -78,4 +78,4 @@ Wang and Zongheng Yang.
[website]: https://nv-adlr.github.io/WaveGlow
[ignored]: https://github.com/NVIDIA/tacotron2/blob/master/hparams.py#L22
[Apex]: https://github.com/nvidia/apex
[AMP]: https://github.com/NVIDIA/apex/tree/master/apex/amp
[AMP]: https://github.com/NVIDIA/apex/tree/master/apex/amp