[EnCodec] Changes for 32kHz ckpt #24296
Merged
Conversation
This file contains 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
sanchit-gandhi
commented
Jun 15, 2023
src/transformers/models/encodec/convert_encodec_checkpoint_to_pytorch.py
Outdated
Show resolved
Hide resolved
|
The documentation is not available anymore as the PR was closed or merged. |
ArthurZucker
approved these changes
Jun 15, 2023
src/transformers/models/encodec/convert_encodec_checkpoint_to_pytorch.py
Outdated
Show resolved
Hide resolved
amyeroberts
approved these changes
Jun 15, 2023
src/transformers/models/encodec/convert_encodec_checkpoint_to_pytorch.py
Outdated
Show resolved
Hide resolved
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
What does this PR do?
Updates the EnCodec config and modelling code to allow two options for the residual connection in the Resnet block:
=> this change is required to use the latest 32kHz EnCodec model in the Music Gen model (#24109). It is tested for with a fast test, and confirmed to match the original implementation.