8000 Releases · lucidrains/spear-tts-pytorch · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

Releases: lucidrains/spear-tts-pytorch

0.4.8

30 Oct 17:24
Compare
Choose a tag to compare

0.4.7

02 Oct 17:02
Compare
Choose a tag to compare
omit the wav2vec parameters from optimizers

0.4.6

02 Oct 16:52
Compare
Choose a tag to compare
make sure wav2vec is done in eval mode and without gradients

0.4.5

02 Oct 14:18
Compare
Choose a tag to compare
address https://github.com/lucidrains/spear-tts-pytorch/pull/9

0.4.4

01 Oct 18:22
Compare
Choose a tag to compare
quick fix for spec decoding

0.4.3

30 Sep 19:33
Compare
Choose a tag to compare
fix default topk sampling filter threshold

0.4.2

30 Sep 18:31
2f40fe1
Compare
Choose a tag to compare
Update setup.py

0.4.1

30 Sep 17:47
Compare
Choose a tag to compare
take care of eos during spec decoding

0.4.0

30 Sep 16:38
Compare
Choose a tag to compare
finally complete speculative decoding with early exit strategy for mo…

0.3.14

30 Sep 15:07
Compare
Choose a tag to compare
give the early exit path an extra feedforward transformer block, and …
0