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

README.md: adding explanation on training from pre-trained model

experiments
rafaelvalle 2019-03-15 17:38:40 -07:00
parent 3869781877
commit bff304f432
1 changed files with 8 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
README.md
View File

@ -33,6 +33,13 @@ Visit our [website] for audio samples using our published [Tacotron 2] and
1. `python train.py --output_directory=outdir --log_directory=logdir`
2. (OPTIONAL) `tensorboard --logdir=outdir/logdir`
## Training using a pre-trained model
Training using a pre-trained model can lead to faster convergence
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 FP16 Training
1. `python -m multiproc train.py --output_directory=outdir --log_directory=logdir --hparams=distributed_run=True,fp16_run=True`
@ -69,3 +76,4 @@ Wang and Zongheng Yang.
[Tacotron 2]: https://drive.google.com/file/d/1c5ZTuT7J08wLUoVZ2KkUs_VdZuJ86ZqA/view?usp=sharing
[pytorch 1.0]: https://github.com/pytorch/pytorch#installation
[website]: https://nv-adlr.github.io/WaveGlow
[ignored]: https://github.com/NVIDIA/tacotron2/blob/master/hparams.py#L22