Core: - Run preflight passes probe/framework to audio_runtime_compatibility - STT model_type gate extended (vibevoice, audio) - MLX 0.30.x compat: catch Exception in whisper_tokenizer - Embedding-gate unit tests (3 tests) - Removed get_encoding duplication (-45 LOC) Benchmark: - GPU analysis section in reports
Audio/Whisper works with pip install - no Git workaround needed. See CHANGELOG.md for details. Tested: 647 passed, 11 skipped (Python 3.10-3.12)