You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
This template is only for usage issues encountered.
I have thoroughly reviewed the project documentation but couldn't find information to solve my problem.
I have searched for existing issues, including closed ones, and couldn't find a solution.
I confirm that I am using English to submit this report in order to facilitate communication.
Environment Details
python=3.10.12
torch=2.3.0
Steps to Reproduce
I trained model with 800 hours and about 1M7 iters for see the result.
You can hear the beginning is a bit choppy. This happens by default when I provide quite long input text.
My inference parameters:
speed: 0.8
cross_fade_duration: 0.5
remove_silence: True
ref text: con đầu tiên này là nâu sọc trắng nè.
gen_text: con đầu tiên này là nâu sọc trắng nè. con thứ hai là nâu sọc đen. con thứ ba là màu cam và con cuối cùng là màu tím nè. con đầu tiên này là nâu sọc trắng nè. con thứ hai là nâu sọc đen. con thứ ba là màu cam và con cuối cùng là màu tím nè.
output.mov
Any help is appreciated. Many thanks.
✔️ Expected Behavior
No choppy
❌ Actual Behavior
No response
The text was updated successfully, but these errors were encountered:
Checks
Environment Details
python=3.10.12
torch=2.3.0
Steps to Reproduce
output.mov
Any help is appreciated. Many thanks.
✔️ Expected Behavior
No choppy
❌ Actual Behavior
No response
The text was updated successfully, but these errors were encountered: