[codex] Make real metric caches explicit#5
Closed
ftshijt wants to merge 120 commits into
Closed
Conversation
refactor versa in OO (major update)
Add WER metrics: Faster-Whisper, NeMo ASR, Facebook’s HuBERT-large-finetuned
# Conflicts: # versa/corpus_metrics/whisper_wer.py # versa/scorer_shared.py
Add metrics: Phoneme Error Rate
Update pseudo_mos.py for default data type
…result # Conflicts: # versa/utterance_metrics/sheet_ssqa.py
…m-show-result [codex] Fix Slurm result summary command
…t-clap-score [codex] Implement CLAP score metric
…ble-scoring Support resumable scoring
…able-scoring Document resumable scoring
…d-scoring Add metric-oriented scoring mode
Fix speaker metric import side effects
…ckaging-ci Refine packaging CI and metric summaries
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
7 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
tools/setup_huggingface_cache.shin the README and CI/testing docs.Root Cause
The real-model failures came from package availability checks passing while required model/checkpoint assets were missing or stored in hidden/inconsistent cache locations. Some pipeline checks also iterated over returned summary keys, so an empty metric output could look successful.
Validation
VERSA_HF_CACHE_DIR=$PWD/versa_cache/huggingface VERSA_DISCRETE_SPEECH_CACHE_DIR=$PWD/versa_cache/discrete_speech_metrics MPLCONFIGDIR=/private/tmp/matplotlib-cache .codex-test-venv/bin/python -m pytest --import-mode=importlib -q --tb=short test/test_metrics/test_discrete_speech.py test/test_metrics/test_emo_vad.py->14 passedVERSA_RUN_REAL_MODEL_TESTS=1 VERSA_HF_CACHE_DIR=$PWD/versa_cache/huggingface VERSA_DISCRETE_SPEECH_CACHE_DIR=$PWD/versa_cache/discrete_speech_metrics MPLCONFIGDIR=/private/tmp/matplotlib-cache .codex-test-venv/bin/python -m pytest --import-mode=importlib -q -rs test->221 passed, 5 skippedgit diff --check.codex-test-venv/bin/python -m compileall -q versa testbash -n tools/setup_huggingface_cache.shNotes
The remaining skipped real-model item is
scoreq_versawhen that optional package is not installed.