v1.0.0
Major (breaking) change
- New base classes
ProcessorGroup
andLossGroup
inherit fromDAGLayer
(dags.py)- All ddsp.training layers [decoders, encoders, preprocessors] inherit from
DictLayer
(nn.py)
- Renamed classes to more precise terms
Additive
->Harmonic
DefaultPreprocessor
->F0LoudnessPreprocessor
TranscribingAutoencoder
->Inverse Synthesis
- New experimental
MidiAutoencoder
model (WIP) Evaluator
classes in eval_util (now configurable from gin instead of a big long series of if statements)- Minor bug fixes