Add the A2 WaveNet architecture and make it the default - #1
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
This adds NAM's current default WaveNet architecture (A2: one LeakyReLU layer array with per-layer kernel sizes and a 16-tap head conv), selectable via --arch in the CLI and a dropdown in the GUI, with A2 standard as the new default. A1 models keep exporting the classic v0.5.4 schema while A2 exports the current v0.7.0 one, and both schemas load back; parity against the reference PyTorch implementation is tested for both architectures.