v0.13.0 (last release before breaking change)

Refactor model. Optionally return dict from __call__(), remove get_co…

v0.12.0 (ICML 2020 workshop)

Release for reproducing the results from the 2020 ICML SAS workshop paper (https://openreview.net/forum?id=RlVTYWhsky7).

WIP code from the paper added with EXPERIMENTAL disclaimers.
Gin configs and details provided in ddsp/training/gin/papers/icml2020

v.0.10.0

• Custom cumsum operation to avoid phase accumulation errors for generating long sequences.
• Script to automatically update old gin configs.

v0.8.0

Add custom cumsum function that doesn't accumulate phase errors like tf.cumsum.

v0.7.0

• Updated pitch detection metrics (RPA, RCA)
• Sinusoidal Synthesizer
• Warm starting models (model_dir -> save_dir, restore_dir)

v0.5.1

Small fixes to bugs introduced by refactor :).

v0.5.0

Some bug fixes and a refactor of train_util and eval_util.

v0.4.0

• New data normalization in the demo colab notebooks.
• Tiny model config.
• Most (but not all) of the variable sample rate PRs.
• Tests and bug fixes.

v0.2.0

Simplify and refactor RnnFcDecoder.

• Requires old models to add a single line to their operative gin configs, or --gin_param, RnnFcDecoder.input_keys = ('f0_scaled', 'ld_scaled')

v0.1.0

• Models now use self._loss_dict to keep track of losses, and not the built-in keras self.losses (so that we can keep track of each loss name without needing a synced parallel list).