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
.
0.1.4
8dacdeff
·
0.1.4
·
Dec 06, 2022
0.1.2
6bf92afa
·
add more informative error messsage
·
Dec 06, 2022
0.1.0
4abc58ed
·
use bias-less layernorm, normformer extra norm in feedforward, remove wip as nearly ready
·
Dec 01, 2022
0.0.68
8c4d01ad
·
only during training
·
Dec 01, 2022
0.0.67
440f4e84
·
implement forgetful causal masking for free improvement
·
Dec 01, 2022
0.0.66
cef37369
·
0.0.66
·
Nov 28, 2022
0.0.65
3ff361d5
·
release ability to customize heads, thanks to @eonglints !
·
Nov 28, 2022
0.0.64
06eecbdb
·
bump vq version
·
Nov 26, 2022
0.0.63
7009188c
·
release random initial time sampling of audio, from @eonglints
·
Nov 25, 2022
0.0.62
dfd4b803
·
address
https://github.com/lucidrains/audiolm-pytorch/issues/18
·
Nov 25, 2022
0.0.61
e0a4fd94
·
fix to RVQ
·
Nov 23, 2022
0.0.60
74c93f5a
·
take care of masking out fine token ids in the same sequence positions where...
·
Nov 22, 2022
0.0.59
6a77a50c
·
add some deps
·
Nov 22, 2022
0.0.58
29566957
·
add some deps
·
Nov 22, 2022
0.0.57
65d9c407
·
resolve issue with eos, maybe
·
Nov 19, 2022
0.0.56
d2932c75
·
cleanup coarse transformer
·
Nov 18, 2022
0.0.55
5c2ebd6a
·
0.0.55
·
Nov 18, 2022
0.0.54
ddb40ee3
·
give semantic transformer a training wrapper too, refactor and do things right
·
Nov 18, 2022
0.0.53
96800b81
·
preliminary training code for all attention nets completed, project management
·
Nov 18, 2022
0.0.52
31edfade
·
first pass at fine transformer trainer
·
Nov 18, 2022
Prev
1
…
10
11
12
13
14
15
16
17
Next