ConsistencyVC/ConsistencyVC-voive-conversion
Using joint training speaker encoder with consistency loss to achieve cross-lingual voice conversion and expressive voice conversion
PythonMIT
Issues
- 2
pred_ppg_c
#22 opened by EmreOzkose - 3
- 1
About license
#20 opened by mycrazycracy - 6
- 1
- 4
Why is audio max duration is 29s?
#13 opened by skol101 - 2
XVC Performance on A2M/A2A
#17 opened by tarepan - 1
Multi GPU support
#16 opened by gandolfxu - 1
Can fine-tuned model be fine-tuned again?
#15 opened by skol101 - 3
如果从头训练的话大概需要多长时间呢
#14 opened by tppqt - 2
必须要运行10K个epoch吗
#12 opened by tppqt - 2
Why don't you calculate the speaker consistency loss in the first 1000 steps?
#11 opened by isletennos - 6
Uploaded model mistake
#8 opened by gandolfxu - 3
HiFiGAN not found
#10 opened by gandolfxu - 2
我如果想微调的话,是操作哪一步呢
#9 opened by tppqt - 5
ZeroDivisionError
#7 opened by tppqt - 1
Accent removal + voice cloning
#6 opened by oijoijcoiejoijce - 3
- 1
- 1
Is hifigan vocoder really used?
#3 opened by skol101 - 6
- 4
How to use this model?
#1 opened by tppqt