Add Colab listening evidence export - #65
Merged
Merged
Conversation
There was a problem hiding this comment.
Pull request overview
This PR adds a Colab-only workflow to export a deterministic, blinded MUSHRA listening-test bundle from the LibriSpeech real-speech evidence matrices, and updates project documentation/roadmap/changelog to reflect the completed evidence-export deliverable.
Changes:
- Add
examples/colab_listening_export.pyto runaudio-super-res eval listening-export, verify the manifests, and package an archive for download. - Document the blind manifest vs. answer-key boundary and accelerator workflow steps for exporting the listening bundle.
- Update roadmap and changelog entries to mark the listening-bundle export deliverable complete.
Reviewed changes
Copilot reviewed 5 out of 5 changed files in this pull request and generated 4 comments.
Show a summary per file
| File | Description |
|---|---|
| ROADMAP.md | Marks the P2 evidence-export deliverable complete and documents the deterministic MUSHRA bundle properties. |
| examples/colab_listening_export.py | New Colab script to export, verify, summarize, and archive the blinded listening bundle. |
| docs/EVALUATION.md | Adds documentation tying the MUSHRA export (seed/trials/stimuli and SHA256) to reproducible evaluation evidence. |
| docs/ACCELERATORS.md | Adds Colab CLI commands to export/download the listening archive before ending the session. |
| CHANGELOG.md | Notes the addition of the Colab-only verified MUSHRA bundle export workflow. |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
Comment on lines
+54
to
+55
| if {stimulus["blind_id"] for stimulus in public_stimuli} != {stimulus["blind_id"] for stimulus in answer_stimuli}: | ||
| raise ValueError("public and answer-key blind IDs differ") |
Comment on lines
+59
to
+63
| expected_roles = {"reference": len(public["trials"]), "anchor": len(public["trials"]), "system": 16} | ||
| if dict(role_counts) != expected_roles: | ||
| raise ValueError(f"unexpected listening roles: {dict(role_counts)}") | ||
| if backend_counts["sinc-resample"] != 8 or backend_counts["lavasr-compat"] != 8: | ||
| raise ValueError(f"unexpected backend counts: {dict(backend_counts)}") |
Comment on lines
+88
to
+92
| def _archive() -> None: | ||
| with tarfile.open(ARCHIVE_PATH, "w:gz") as archive: | ||
| archive.add(LISTENING_DIR, arcname="listening-mushra") | ||
| archive.add(EVIDENCE_DIR / "listening-summary.json", arcname="listening-summary.json") | ||
| print(f"[colab-listening] evidence archive: {ARCHIVE_PATH}", flush=True) |
Comment on lines
+139
to
+141
| finally: | ||
| if LISTENING_DIR.is_dir(): | ||
| _archive() |
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
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.
Summary
Colab evidence
0832(4per trial)8reference,8anchor,16system8sinc,8LavaSRblind_id,pathonly56ce14404d8b90ba2dd4ee1f62dfd7779894b0849c448af82b82dec1283561a65d93e2848adf3f65c3c9acf803d8dde332fb059c79b1fbbbbe02c7eca0745156All model inference and audio generation ran remotely through Colab CLI. Local verification was limited to lightweight lint/format/diff checks.
Verification
git diff --checkpixi run lintpixi run format-check163 passed, 6 skipped