feat(dictate): use local socket-activated Parakeet

This commit is contained in:
jb
2026-08-26 12:38:45 -04:00
parent ea74dbc6a7
commit e234468a73
34 changed files with 6702 additions and 527 deletions
+10
View File
@@ -0,0 +1,10 @@
# Todos
## Investigate transient concurrent NeMo benchmark failures
During Dictate Phase 0 on 26AUG2026, repeated overlapping throwaway benchmark processes produced two one-off failures in the external `/srv/data/tools/parakeet-v3/.venv` environment:
1. `ASRModel.restore_from()` raised `MemoryError` while OmegaConf rebuilt `joint.vocabulary`. The exact clean/noisy/silence harness passed on its immediate rerun.
2. A later production-adapter check raised `ValueError: bad marshal data (invalid reference)` while importing `torch._tensor`. An immediate standalone `import torch` succeeded, and the cached `_tensor.cpython-312.pyc` passed `marshal.loads()`.
The production service serializes model loading and inference and therefore does not intentionally launch concurrent NeMo processes. Before treating concurrent workers as supported, build a repeatable cold-load stress loop, monitor process and cgroup memory, disable bytecode writes, and determine whether the failures come from NeMo/OmegaConf resource pressure or concurrent access to the external environment's bytecode cache.