V0.2.0

This release contains a major refactor. Unfortunately, it is breaking for training. The pretrained models should not be affected though. Overall, it's a better direction for the project and will enable me to add new models easily.

V0.1.8

This release adds cropping to the skip connections in the waveform models to enable the use of different max lengths than multples of 16384.

V0.1.7

This release changes model outputs from .logits to .audio

V0.1.6

Remove dependencies from pypi build

V0.1.5

Patch release. torchaudio not found via pip during pypi publish.

V0.1.4

This release introduces a new model UNet1DModel. There is currently a pretrained checkpoint on the huggingface hub. It is still training, but beats the waveunet checkpoints across the board.

V0.1.3

Update pyproject.toml

V0.1.2

Update pyproject.toml

V0.1.0

Update pyproject.toml

V0.0.3

Update pyproject.toml