How to train new Waveglow model for diffirent language?

Ask questionsHow to train new Waveglow model for diffirent language?

As the title, I would like to know how to train a new model using another dataset, which have the same structure as LJ Speech dataset. What modifications need to be done for a diffirent language?

NVIDIA/waveglow

Answer questions Adizbek

@EuphoriaCelestial, I've installed successfully, how many hours (minimum) of audio need to generate correct spelled audio ?

useful!

Related questions

How do I increase the text limit? hot 1

Training fails with torch.jit.script hot 1

After steps from README.md for getting audio: ModuleNotFoundError: No module named 'librosa' hot 1

not able to export waveglow_old.pt into onnx format and keep getting RuntimeError: Only tuples, lists and Variables supported as JIT inputs, but got NoneType hot 1

Loss instability during training hot 1

source：https://uonfu.com/

answerer

Ergashev Adizbek Adizbek Tashkent, Uzbekistan Android, PHP, JS developer

repos

gists

followers

following