 Lengyue
|
2966ba9019
Support speaker finetune
|
%!s(int64=2) %!d(string=hai) anos |
|
Lengyue
|
c7cf70e904
Fix dataset and docker
|
%!s(int64=2) %!d(string=hai) anos |
|
Lengyue
|
05c342704b
Optimize auto clean text
|
%!s(int64=2) %!d(string=hai) anos |
|
Lengyue
|
7ae872018f
Add arg to disable g2p
|
%!s(int64=2) %!d(string=hai) anos |
|
Lengyue
|
c54eecc63f
Implement windowed repeat penalty
|
%!s(int64=2) %!d(string=hai) anos |
|
Lengyue
|
55ed0f91af
Optimize dataset & multi codebook training
|
%!s(int64=2) %!d(string=hai) anos |
|
Lengyue
|
9649873532
Update generate examples
|
%!s(int64=2) %!d(string=hai) anos |
|
Lengyue
|
9ac8edef1e
Support mix codebook training
|
%!s(int64=2) %!d(string=hai) anos |
|
Lengyue
|
f8cfbb4ac0
Greatly improved data loading speed
|
%!s(int64=2) %!d(string=hai) anos |
|
Lengyue
|
62710e34a4
Add llama inference tool chain
|
%!s(int64=2) %!d(string=hai) anos |
|
Lengyue
|
4b22991668
Implement parallel decoding llama
|
%!s(int64=2) %!d(string=hai) anos |
|
Lengyue
|
5ae08bd43b
Add dataset protobuf & parallel building
|
%!s(int64=2) %!d(string=hai) anos |
|
Lengyue
|
895ed8e748
Add new text to semantic model
|
%!s(int64=2) %!d(string=hai) anos |
|
Lengyue
|
ba1e088246
Implement text auto aug
|
%!s(int64=2) %!d(string=hai) anos |
|
Lengyue
|
66219b20cf
Updata llama pretain config (max 100 val epoch)
|
%!s(int64=2) %!d(string=hai) anos |
|
Lengyue
|
f7f2c03282
Support pytorch lightning
|
%!s(int64=2) %!d(string=hai) anos |
