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
.
1.5.4
a1dd97b7
·
fix validation in trainers
·
Oct 05, 2023
1.5.3
8d4b50de
·
allow for setting init process timeout as well as an extra barrier
·
Oct 05, 2023
1.5.2
a3526832
·
address
https://github.com/lucidrains/audiolm-pytorch/issues/234
·
Oct 04, 2023
1.5.1
986e3830
·
patch
·
Sep 22, 2023
1.5.0
e11c3a32
·
speed up generation with kv caching across all 3 transformers
·
Sep 22, 2023
1.4.5
59287ff9
·
kv cache for coarse transformer
·
Sep 21, 2023
1.4.4
bfdc983a
·
beartype is fixed in 0.16.1
·
Sep 19, 2023
1.4.3
6cc4cd2f
·
take first step towards support for kv cache across all transformers, starting...
·
Sep 19, 2023
1.4.2
abe29a8a
·
pin beartype for now and also some project management
·
Sep 18, 2023
1.4.1
5e0261b9
·
address
https://github.com/lucidrains/audiolm-pytorch/issues/226
·
Aug 31, 2023
1.4.0
44ae4dea
·
update vq to latest version, given fixes to kmeans and linear projection when...
·
Aug 25, 2023
1.2.29
769c4475
·
allow for other bandwidths for encodec
·
Aug 10, 2023
1.2.28
188fe9e1
·
fix dataset collation fn when returning only one audio target sample hz
·
Aug 09, 2023
1.2.27
eec8a979
·
oops, reapply validation avg changes
·
Aug 07, 2023
1.2.25
9aba02ea
·
address
https://github.com/lucidrains/audiolm-pytorch/issues/224
, by taking...
·
Aug 07, 2023
1.2.26
c65bb976
·
bump
·
Aug 03, 2023
1.2.24
22951abe
·
allow for prompt audio to be passed in as `prime_wave_path` to `AudioLM`
·
Aug 01, 2023
1.2.23
9fd9e451
·
add ability to indicate input sample freq for the prime wav being offered to...
·
Aug 01, 2023
1.2.22
053bfe8c
·
add ability to resample input wav to encodec to 24k, through input_sample_hz keyword arg
·
Aug 01, 2023
1.2.21
a505f337
·
add a few asserts for dataset and validation dataset lengths
·
Jul 27, 2023
Prev
1
2
3
4
5
6
7
…
17
Next