decode-fix: MPS tensor and codebook bounds for macOS#23
Merged
Conversation
Collaborator
lmangani
commented
Jan 30, 2026
lmangani
commented
- Run HeartCodec on CPU on MPS to avoid 'invalid type: torch.mps.FloatTensor' during decode (detokenize/save path).
- Round-trip wav via numpy before torchaudio.save so backend gets plain CPU tensor.
- Clamp token IDs to codec codebook range [0, codebook_size-1] to avoid 'index X is out of bounds for dimension 1 with size 8192' in ResidualVQ.
- Document decoding step flow in comments.
- Run HeartCodec on CPU on MPS to avoid 'invalid type: torch.mps.FloatTensor' during decode (detokenize/save path). - Round-trip wav via numpy before torchaudio.save so backend gets plain CPU tensor. - Clamp token IDs to codec codebook range [0, codebook_size-1] to avoid 'index X is out of bounds for dimension 1 with size 8192' in ResidualVQ. - Document decoding step flow in comments.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.