search

huawei-noah / Speech-Backbones

This is the main repository of open-sourced speech technology by Huawei Noah's Ark Lab.
564 stars 118 forks source link

DOESN'T WORK #38

Open yukiarimo opened 3 months ago

yukiarimo commented 3 months ago

Tried to fine-tune Grad-TTS. Doesn't work. Random issues like: error: could not create 'model/monotonic_align/core.cpython-310-x86_64-linux-gnu.so': No such file or directory and so on

li1jkdaw commented 2 months ago

Monotonic alignment in Grad-TTS was borrowed from Glow-TTS. To find the solution you can check this issue in Glow-TTS repository, some of its users also face with the same problem.