From 7eb5eece148484b14afeb62f683b7018adf870de Mon Sep 17 00:00:00 2001 From: Grzegorz Karch Date: Wed, 26 Jun 2019 08:57:23 -0700 Subject: [PATCH] changed number of epochs in train scripts; removed number of epochs from readme for the audio samples --- PyTorch/SpeechSynthesis/Tacotron2/README.md | 3 +-- PyTorch/SpeechSynthesis/Tacotron2/scripts/train_tacotron2.sh | 2 +- PyTorch/SpeechSynthesis/Tacotron2/scripts/train_waveglow.sh | 2 +- 3 files changed, 3 insertions(+), 4 deletions(-) diff --git a/PyTorch/SpeechSynthesis/Tacotron2/README.md b/PyTorch/SpeechSynthesis/Tacotron2/README.md index d30687a6..893b7654 100644 --- a/PyTorch/SpeechSynthesis/Tacotron2/README.md +++ b/PyTorch/SpeechSynthesis/Tacotron2/README.md @@ -137,8 +137,7 @@ Ensure your loss values are comparable to those listed in the table in the Results section. For both models, the loss values are stored in the `./output/nvlog.json` log file. -After you have trained the Tacotron 2 model for 1500 epochs and the -WaveGlow model for 800 epochs, you should get audio results similar to the +After you have trained the Tacotron 2 and WaveGlow models, you should get audio results similar to the samples in the `./audio` folder. For details about generating audio, see the [Inference process](#inference-process) section below. diff --git a/PyTorch/SpeechSynthesis/Tacotron2/scripts/train_tacotron2.sh b/PyTorch/SpeechSynthesis/Tacotron2/scripts/train_tacotron2.sh index 6823a3b2..6b2bfdb4 100644 --- a/PyTorch/SpeechSynthesis/Tacotron2/scripts/train_tacotron2.sh +++ b/PyTorch/SpeechSynthesis/Tacotron2/scripts/train_tacotron2.sh @@ -1,2 +1,2 @@ mkdir -p output -python -m multiproc train.py -m Tacotron2 -o ./output/ -lr 1e-3 --epochs 2001 -bs 80 --weight-decay 1e-6 --grad-clip-thresh 1.0 --cudnn-benchmark=True --log-file ./output/nvlog.json --anneal-steps 500 1000 1500 --anneal-factor 0.1 --fp16-run +python -m multiproc train.py -m Tacotron2 -o ./output/ -lr 1e-3 --epochs 1500 -bs 80 --weight-decay 1e-6 --grad-clip-thresh 1.0 --cudnn-benchmark=True --log-file ./output/nvlog.json --anneal-steps 500 1000 1500 --anneal-factor 0.1 --fp16-run diff --git a/PyTorch/SpeechSynthesis/Tacotron2/scripts/train_waveglow.sh b/PyTorch/SpeechSynthesis/Tacotron2/scripts/train_waveglow.sh index ca1d21f3..e98e5d0a 100644 --- a/PyTorch/SpeechSynthesis/Tacotron2/scripts/train_waveglow.sh +++ b/PyTorch/SpeechSynthesis/Tacotron2/scripts/train_waveglow.sh @@ -1,2 +1,2 @@ mkdir -p output -python -m multiproc train.py -m WaveGlow -o ./output/ -lr 1e-4 --epochs 2001 -bs 8 --segment-length 8000 --weight-decay 0 --grad-clip-thresh 65504.0 --epochs-per-checkpoint 50 --cudnn-benchmark=True --log-file ./output/nvlog.json --fp16-run +python -m multiproc train.py -m WaveGlow -o ./output/ -lr 1e-4 --epochs 1000 -bs 8 --segment-length 8000 --weight-decay 0 --grad-clip-thresh 65504.0 --epochs-per-checkpoint 50 --cudnn-benchmark=True --log-file ./output/nvlog.json --fp16-run