-
### Describe the bug
Generation of longer phrases seems to garble the output after about the 30 second timestamp. The resulting files sound random: one was 60 second long, while this attached lasts o…
-
### Describe the bug
After unzip of "vocoder_models--de--thorsten--hifigan_v1" the unzipped directory is: "vocoder_models--de-thorsten-hifigan_v1" could you please rename the zipped directory so that…
-
My training script for tacotron
python -m multiproc train.py -m Tacotron2 -o ./output/ -lr 1e-3 --epochs 1 -bs 32 --weight-decay 1e-6 --grad-clip-thresh 1.0 --cudnn-enabled --log-file nvlog.json --…
-
我最近也有这样的想法，因为gal语料很多，但是准备想用 fastspeech2或者tacotron2来尝试的，不知道大佬之前是否有做过调研？还是看这个模型出的比较近，感觉效果会更好一点？
-
我找来找去，都是只支持中文或者英文（不同语言会报错），就想问问能不能同时支持中英日三语的输出？（个人用Tacotron2
-
### 🚀 The feature, motivation and pitch
Requested by Nikita as a dependency for enabling nvfuser by default:
"... we should validte that it would not regress some common trainign workflows like:"
…
-
-
### Describe the bug
raceback (most recent call last):
File "/opt/conda/envs/coqui/lib/python3.8/site-packages/trainer-0.0.14-py3.8.egg/trainer/trainer.py", line 1533, in fit
self._fit()
F…
-
After this PR https://github.com/pytorch/benchmark/pull/1261 change https://github.com/pytorch/benchmark/commit/94078d9288ff99ef50557a3bd87970badbef0458#diff-fcf1c48cd82709b9bd6dc7881e2a425d15502a7592…
-
1. Why you set lr=0.00002, have you tried other settings, is lr=0.00002 the best?
2. In the paper, the time loss is an import point, but in my training, the time loss seems not decline.
I use my …