Add Mimi codebook embedding visualization script#1
Open
pshishodiaa wants to merge 1 commit into
Open
Conversation
Download kyutai/mimi from HuggingFace and visualize the acoustic codebook embeddings (2048 vocab, 256 dim) reduced to 2D via t-SNE for quantizer layers q=0,1,2,3,4,8,16,30. https://claude.ai/code/session_01E6s5UqmJZazkWtPAjQFwf1
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Download kyutai/mimi from HuggingFace and visualize the acoustic
codebook embeddings (2048 vocab, 256 dim) reduced to 2D via t-SNE
for quantizer layers q=0,1,2,3,4,8,16,30.
https://claude.ai/code/session_01E6s5UqmJZazkWtPAjQFwf1
Note
Low Risk
Adds an offline analysis script only; no changes to library/runtime behavior, though it executes
trust_remote_code=Truewhen downloading the model.Overview
Adds a standalone
visualize_mimi_codebooks.pyutility that downloadskyutai/mimifrom HuggingFace, extracts selected acoustic quantizer codebook embeddings, runs t-SNE to reduce them to 2D, and saves a multi-panel scatterplot image (mimi_codebook_tsne.png).Written by Cursor Bugbot for commit 5637a71. This will update automatically on new commits. Configure here.