ai-tube-model-musicgen-1 / CHANGELOG.md
adefossez's picture
new version
c16da55
|
raw
history blame
576 Bytes

Changelog

All notable changes to this project will be documented in this file.

The format is based on Keep a Changelog.

[0.0.2a] - TBD

Improved demo, fixed top p (thanks @jnordberg).

Compressor tanh on output to avoid clipping with some style (especially piano). Now repeating the conditioning periodically if it is too short.

More options when launching Gradio app locally (thanks @ashleykleynhans).

Testing out PyTorch 2.0 memory efficient attention.

[0.0.1] - 2023-06-09

Initial release, with model evaluation only.