mirror of
https://github.com/jamiepine/voicebox.git
synced 2026-09-16 05:10:42 -07:00
* fix(offline): guard inference paths with HF_HUB_OFFLINE (#462) PR #443 wrapped the model *load* path with `force_offline_if_cached` so cached models don't phone home at startup. The context manager restores `HF_HUB_OFFLINE` on exit, which left inference paths (generate, transcribe, voice-prompt creation) unguarded — and `qwen_tts`, `mlx_audio`, and `transformers` perform lazy tokenizer/processor/config lookups during inference. With internet on, those lookups are near-instant and invisible; with internet off, `requests` hangs on DNS or connect until the network returns. This is exactly what users in #462 describe: model shows "Loaded", internet drops, generation "thinks" forever, internet comes back, generation completes. Chatterbox and LuxTTS don't exhibit this because their engine libs resolve everything through already-cached paths at load time. Fix: wrap each inference-sync body with `force_offline_if_cached(True, ...)`. Since inference only runs after a successful load, weights are known to be on disk, so `is_cached=True` is unconditional. Also adds the load-time guard that was missing from `qwen_custom_voice_backend.py` — CustomVoice previously had no offline protection at all. Paths patched: - PyTorchTTSBackend.create_voice_prompt (create_voice_clone_prompt) - PyTorchTTSBackend.generate (generate_voice_clone) - PyTorchSTTBackend.transcribe (Whisper generate + decoder-prompt-ids) - MLXTTSBackend.generate (mlx_audio generate, all branches) - MLXSTTBackend.transcribe (mlx_audio whisper generate) - QwenCustomVoiceBackend._load_model_sync + generate Does not address the secondary `check_model_inputs() missing 'func'` error reported in the same issue — that's a `transformers` 5.x version-skew bug on the install path, separate concern. Fixes #462. Co-Authored-By: Claude Opus 4.7 (1M context) <[email protected]> * fix(offline): mutate cached HF constants + threadsafe refcount Review feedback on the initial fix surfaced two real issues: 1. ``os.environ`` toggles alone don't flip offline mode. ``huggingface_hub.constants.HF_HUB_OFFLINE`` is read once at import time into a module-level bool; ``transformers.utils.hub._is_offline_mode`` mirrors that bool at its own import time. The hot paths (``_http._default_backend_factory`` in huggingface_hub, ``is_offline_mode`` in transformers) read the cached bools — not the env — so mutating only ``os.environ`` was a no-op. 2. Race condition on concurrent inference. Two threads running inside ``force_offline_if_cached`` via ``asyncio.to_thread`` could have thread A's ``finally`` strip thread B's offline protection mid-run. Rewrite the helper to: - mutate ``huggingface_hub.constants.HF_HUB_OFFLINE`` and ``transformers.utils.hub._is_offline_mode`` directly - refcount concurrent users under a single ``threading.RLock`` so a shared offline window is restored only when the last caller exits - still write ``os.environ`` for anything that reads it dynamically Also addresses the unused-variable ruff flag on the Whisper transcribe path (``audio, sr`` → ``audio, _sr``). New unit tests cover the cached-constant mutation, env propagation, no-op on ``is_cached=False``, nested contexts, and a threaded race where a slow thread must retain offline mode after a peer exits. Co-Authored-By: Claude Opus 4.7 (1M context) <[email protected]> * fix(offline): atomic entry rollback + tidy test assertions Review follow-up: - Wrap the `_offline_refcount == 0` setup in a try/except so any failure during the cached-constant mutation (including unexpected non-ImportError like RuntimeError or AttributeError from a half-initialized module) rolls back *all* partial state before re-raising. Without this, a mid-setup crash could leave `huggingface_hub.constants.HF_HUB_OFFLINE` mutated but the refcount at 0 — a persistent offline flag outliving the process. - Swap ruff-flagged Yoda comparisons in the new test file (SIM300) and add a module-level note warning that these tests mutate global state and are not safe under cross-process parallelism. Co-Authored-By: Claude Opus 4.7 (1M context) <[email protected]> * test(offline): make concurrency test deterministic and bounded Replace the `sleep(0.15)` ordering hack with an explicit `threading.Event` the fast thread sets in `finally`. The slow thread waits on that event (bounded), then observes the flag — so we deterministically verify the slow thread still sees offline mode after the fast thread has exited. Also add timeouts to `barrier.wait()` and assert `not thread.is_alive()` after the joins so the test can't hang on an unexpected failure path. Co-Authored-By: Claude Opus 4.7 (1M context) <[email protected]> --------- Co-authored-by: Claude Opus 4.7 (1M context) <[email protected]>
119 lines
3.7 KiB
Python
119 lines
3.7 KiB
Python
"""
|
|
Unit tests for the ``force_offline_if_cached`` helper.
|
|
|
|
Verifies that the helper mutates the cached module constants in
|
|
``huggingface_hub.constants`` and ``transformers.utils.hub`` — not just
|
|
``os.environ`` — and that concurrent users are refcount-coordinated so
|
|
one thread's exit can't strip another thread's offline protection.
|
|
|
|
NOTE: These tests mutate process-global state in ``huggingface_hub.constants``
|
|
and ``transformers.utils.hub``. They are not safe under cross-process
|
|
parallelism (e.g. ``pytest-xdist`` with ``--dist=loadfile``/``loadscope``);
|
|
run this file serially.
|
|
"""
|
|
|
|
import os
|
|
import sys
|
|
import threading
|
|
from pathlib import Path
|
|
|
|
import pytest
|
|
|
|
sys.path.insert(0, str(Path(__file__).parent.parent))
|
|
|
|
from utils.hf_offline_patch import force_offline_if_cached # noqa: E402
|
|
|
|
|
|
def _hf_const():
|
|
import huggingface_hub.constants as hf_const
|
|
|
|
return hf_const
|
|
|
|
|
|
def _tf_hub():
|
|
import transformers.utils.hub as tf_hub
|
|
|
|
return tf_hub
|
|
|
|
|
|
def test_mutates_cached_huggingface_hub_constant():
|
|
original = _hf_const().HF_HUB_OFFLINE
|
|
with force_offline_if_cached(True, "t"):
|
|
assert _hf_const().HF_HUB_OFFLINE is True
|
|
assert original == _hf_const().HF_HUB_OFFLINE
|
|
|
|
|
|
def test_mutates_cached_transformers_constant():
|
|
original = _tf_hub()._is_offline_mode
|
|
with force_offline_if_cached(True, "t"):
|
|
assert _tf_hub()._is_offline_mode is True
|
|
assert original == _tf_hub()._is_offline_mode
|
|
|
|
|
|
def test_sets_env_variable():
|
|
original = os.environ.get("HF_HUB_OFFLINE")
|
|
with force_offline_if_cached(True, "t"):
|
|
assert "1" == os.environ.get("HF_HUB_OFFLINE")
|
|
assert original == os.environ.get("HF_HUB_OFFLINE")
|
|
|
|
|
|
def test_noop_when_not_cached():
|
|
before = _hf_const().HF_HUB_OFFLINE
|
|
with force_offline_if_cached(False, "t"):
|
|
assert before == _hf_const().HF_HUB_OFFLINE
|
|
|
|
|
|
def test_nested_contexts_respect_refcount():
|
|
original = _hf_const().HF_HUB_OFFLINE
|
|
with force_offline_if_cached(True, "outer"):
|
|
assert _hf_const().HF_HUB_OFFLINE is True
|
|
with force_offline_if_cached(True, "inner"):
|
|
assert _hf_const().HF_HUB_OFFLINE is True
|
|
# inner exit must not restore while outer is still active
|
|
assert _hf_const().HF_HUB_OFFLINE is True
|
|
assert original == _hf_const().HF_HUB_OFFLINE
|
|
|
|
|
|
def test_concurrent_threads_share_offline_window():
|
|
"""A slow thread must keep seeing offline mode even if a peer exits first."""
|
|
original = _hf_const().HF_HUB_OFFLINE
|
|
observations: list[bool] = []
|
|
errors: list[Exception] = []
|
|
barrier = threading.Barrier(2)
|
|
fast_exited = threading.Event()
|
|
|
|
def slow():
|
|
try:
|
|
with force_offline_if_cached(True, "slow"):
|
|
barrier.wait(timeout=5)
|
|
assert fast_exited.wait(timeout=5), "fast thread did not exit"
|
|
observations.append(_hf_const().HF_HUB_OFFLINE)
|
|
except Exception as exc: # noqa: BLE001
|
|
errors.append(exc)
|
|
|
|
def fast():
|
|
try:
|
|
with force_offline_if_cached(True, "fast"):
|
|
barrier.wait(timeout=5)
|
|
except Exception as exc: # noqa: BLE001
|
|
errors.append(exc)
|
|
finally:
|
|
fast_exited.set()
|
|
|
|
t_slow = threading.Thread(target=slow)
|
|
t_fast = threading.Thread(target=fast)
|
|
t_slow.start()
|
|
t_fast.start()
|
|
t_slow.join(timeout=5)
|
|
t_fast.join(timeout=5)
|
|
|
|
assert not t_slow.is_alive(), "slow thread did not finish"
|
|
assert not t_fast.is_alive(), "fast thread did not finish"
|
|
assert not errors, errors
|
|
assert observations == [True], "slow thread lost offline protection"
|
|
assert original == _hf_const().HF_HUB_OFFLINE
|
|
|
|
|
|
if __name__ == "__main__":
|
|
pytest.main([__file__, "-v"])
|