Skip to content
GitLab
Explore
Sign in
Tags
Tags give the ability to mark specific points in history as being important
This project is mirrored from
https://github.com/lucidrains/audiolm-pytorch
. Pull mirroring updated
Sep 19, 2024
.
1.1.4
95e0669d
·
fix embed text invoked on semantic transformer wrapper
·
May 31, 2023
1.1.2
58efa2e4
·
quick fix
·
May 30, 2023
1.1.1
0edf4c20
·
patch encodec
·
May 29, 2023
1.1.0
7b82d6ea
·
update multi-scale discriminator for soundstream, thanks to @haydenshively
·
May 29, 2023
1.0.6
7f973f1f
·
expose a setting for residual vq
·
May 24, 2023
1.0.5
d90bbb90
·
expose a setting for residual vq
·
May 24, 2023
1.0.4
cc811ac8
·
fix accelerate not liking nn.Parameter with zero elements, thanks to @lzl1456
·
May 19, 2023
1.0.2
e328bf14
·
need the codebook size for soundstorm
·
May 18, 2023
1.0.1
455c0735
·
need the codebook size for soundstorm
·
May 18, 2023
1.0.0
c2ca4ce0
·
1.0.0
·
May 17, 2023
0.30.7
5d8b7425
·
Merge pull request #189 from LWprogramming/fix_step
·
May 16, 2023
0.30.4
add2d2eb
·
0.30.4
·
May 16, 2023
0.30.3
9ec98366
·
fix coarse transformer wrapper loss if semantic loss weight set to 0
·
May 14, 2023
0.30.2
504a7e17
·
allow for curtailing a left part of the raw audio being passed into...
·
May 12, 2023
0.30.1
657790d6
·
allow the padding mode to be customizable in soundstream for causal conv
·
May 11, 2023
0.30.0
71fe13fb
·
add ability to train with grouped residual vq, from hifi-codec paper
·
May 10, 2023
0.29.0
bead0a38
·
add ability to train the soundstream to be denoising, as in the paper, may be...
·
Apr 28, 2023
0.28.2
d05c020f
·
allow for a custom reconstruction target in soundstream
·
Apr 28, 2023
0.28.1
c3fabc36
·
address
https://github.com/lucidrains/audiolm-pytorch/issues/177
·
Apr 27, 2023
0.28.0
d50ae9e3
·
do some improvisation and get a residual into the complex stft discriminator
·
Apr 26, 2023
Prev
1
2
3
4
5
6
7
8
9
…
17
Next