mirror of
https://github.com/jamiepine/voicebox.git
synced 2026-09-16 21:30:39 -07:00
James PineandClaude Opus 4.6
2076114972
Four distinct bundling-specific crashes blocked Kokoro and Qwen CustomVoice
from loading in the frozen binary:
1. torch._dynamo import triggered via class-body decorators
(@torch._dynamo.allow_in_graph on PreTrainedModel,
@torch.compiler.disable in flex_attention) pulls in torch._numpy._ufuncs
which crashes on module load with NameError: name 'name' is not defined.
2. AlbertModel (Kokoro) triggers @auto_docstring -> modeling_auto ->
GenerationMixin -> candidate_generator -> sklearn -> scipy, which hits
the same class of bug in scipy.stats._distn_infrastructure (NameError:
name 'obj' is not defined).
3. AutoModel (Qwen) pulls the same sklearn -> scipy chain directly.
4. librosa (required by most TTS engines) -> scipy.signal -> scipy.stats
hits the _distn_infrastructure crash regardless of the transformers
stubs above.
The root cause of (1) and (4) is that PyInstaller's frozen importer runs
module-level `for X in [<list-comp using dir()>]:` loops with an empty
iterable, leaving the loop variable unbound. Trailing `del obj` / unrelated
references then crash.
Fix: a single runtime hook (pyi_rth_torch_compiler_disable.py) installs:
- sys.modules stubs for torch._dynamo and torch._dynamo.config, plus a
meta-path finder for torch._dynamo.* submodules — voicebox never uses
torch.compile/dynamo for inference, so a permissive no-op stub (callable
as decorator, falsey as predicate, context-manager-safe for
TransformGetItemToIndex) is drop-in safe.
- meta-path finder stubs for transformers.utils.auto_docstring and
transformers.generation.candidate_generator — both import-chain
short-circuits; docstrings and speculative decoding aren't used for TTS.
- meta-path finder for scipy.stats._distn_infrastructure that reads the
real .py source via the wrapped loader's get_source(), replaces the
bundling-broken `del obj` with `globals().pop('obj', None)`, and
compile+exec's the patched source. This keeps the real scipy module
intact so librosa and everything downstream works normally.
Supporting changes:
- backend/pyi_hooks/hook-scipy.stats._distn_infrastructure.py sets
module_collection_mode = "pyz+py" so the .py source is actually in the
bundle for the runtime patcher to read.
- build_binary.py and voicebox-server.spec register the runtime hook and
the new hooks dir.
Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>
88 lines
4.8 KiB
RPMSpec
88 lines
4.8 KiB
RPMSpec
# -*- mode: python ; coding: utf-8 -*-
|
|
from PyInstaller.utils.hooks import collect_submodules
|
|
from PyInstaller.utils.hooks import collect_all
|
|
from PyInstaller.utils.hooks import copy_metadata
|
|
|
|
datas = []
|
|
binaries = []
|
|
hiddenimports = ['backend', 'backend.main', 'backend.config', 'backend.database', 'backend.models', 'backend.services.profiles', 'backend.services.history', 'backend.services.tts', 'backend.services.transcribe', 'backend.utils.platform_detect', 'backend.backends', 'backend.backends.pytorch_backend', 'backend.backends.qwen_custom_voice_backend', 'backend.utils.audio', 'backend.utils.cache', 'backend.utils.progress', 'backend.utils.hf_progress', 'backend.services.cuda', 'backend.services.effects', 'backend.utils.effects', 'backend.services.versions', 'pedalboard', 'chatterbox', 'chatterbox.tts_turbo', 'chatterbox.mtl_tts', 'backend.backends.chatterbox_backend', 'backend.backends.chatterbox_turbo_backend', 'backend.backends.luxtts_backend', 'zipvoice', 'zipvoice.luxvoice', 'torch', 'transformers', 'fastapi', 'uvicorn', 'sqlalchemy', 'soundfile', 'qwen_tts', 'qwen_tts.inference', 'qwen_tts.inference.qwen3_tts_model', 'qwen_tts.inference.qwen3_tts_tokenizer', 'qwen_tts.core', 'qwen_tts.cli', 'requests', 'pkg_resources.extern', 'backend.backends.hume_backend', 'tada', 'tada.modules', 'tada.modules.tada', 'tada.modules.encoder', 'tada.modules.decoder', 'tada.modules.aligner', 'tada.modules.acoustic_spkr_verf', 'tada.nn', 'tada.nn.vibevoice', 'tada.utils', 'tada.utils.gray_code', 'tada.utils.text', 'backend.utils.dac_shim', 'torchaudio', 'backend.backends.kokoro_backend', 'en_core_web_sm', 'loguru', 'backend.backends.mlx_backend', 'mlx', 'mlx.core', 'mlx.nn', 'mlx_audio', 'mlx_audio.tts', 'mlx_audio.stt']
|
|
datas += copy_metadata('qwen-tts')
|
|
datas += copy_metadata('requests')
|
|
datas += copy_metadata('transformers')
|
|
datas += copy_metadata('huggingface-hub')
|
|
datas += copy_metadata('tokenizers')
|
|
datas += copy_metadata('safetensors')
|
|
datas += copy_metadata('tqdm')
|
|
datas += copy_metadata('en_core_web_sm')
|
|
hiddenimports += collect_submodules('jaraco')
|
|
hiddenimports += collect_submodules('tada')
|
|
hiddenimports += collect_submodules('mlx')
|
|
hiddenimports += collect_submodules('mlx_audio')
|
|
tmp_ret = collect_all('zipvoice')
|
|
datas += tmp_ret[0]; binaries += tmp_ret[1]; hiddenimports += tmp_ret[2]
|
|
tmp_ret = collect_all('linacodec')
|
|
datas += tmp_ret[0]; binaries += tmp_ret[1]; hiddenimports += tmp_ret[2]
|
|
tmp_ret = collect_all('lazy_loader')
|
|
datas += tmp_ret[0]; binaries += tmp_ret[1]; hiddenimports += tmp_ret[2]
|
|
tmp_ret = collect_all('librosa')
|
|
datas += tmp_ret[0]; binaries += tmp_ret[1]; hiddenimports += tmp_ret[2]
|
|
tmp_ret = collect_all('qwen_tts')
|
|
datas += tmp_ret[0]; binaries += tmp_ret[1]; hiddenimports += tmp_ret[2]
|
|
tmp_ret = collect_all('inflect')
|
|
datas += tmp_ret[0]; binaries += tmp_ret[1]; hiddenimports += tmp_ret[2]
|
|
tmp_ret = collect_all('perth')
|
|
datas += tmp_ret[0]; binaries += tmp_ret[1]; hiddenimports += tmp_ret[2]
|
|
tmp_ret = collect_all('piper_phonemize')
|
|
datas += tmp_ret[0]; binaries += tmp_ret[1]; hiddenimports += tmp_ret[2]
|
|
tmp_ret = collect_all('kokoro')
|
|
datas += tmp_ret[0]; binaries += tmp_ret[1]; hiddenimports += tmp_ret[2]
|
|
tmp_ret = collect_all('misaki')
|
|
datas += tmp_ret[0]; binaries += tmp_ret[1]; hiddenimports += tmp_ret[2]
|
|
tmp_ret = collect_all('language_tags')
|
|
datas += tmp_ret[0]; binaries += tmp_ret[1]; hiddenimports += tmp_ret[2]
|
|
tmp_ret = collect_all('espeakng_loader')
|
|
datas += tmp_ret[0]; binaries += tmp_ret[1]; hiddenimports += tmp_ret[2]
|
|
tmp_ret = collect_all('en_core_web_sm')
|
|
datas += tmp_ret[0]; binaries += tmp_ret[1]; hiddenimports += tmp_ret[2]
|
|
tmp_ret = collect_all('mlx')
|
|
datas += tmp_ret[0]; binaries += tmp_ret[1]; hiddenimports += tmp_ret[2]
|
|
tmp_ret = collect_all('mlx_audio')
|
|
datas += tmp_ret[0]; binaries += tmp_ret[1]; hiddenimports += tmp_ret[2]
|
|
|
|
|
|
a = Analysis(
|
|
['server.py'],
|
|
pathex=[],
|
|
binaries=binaries,
|
|
datas=datas,
|
|
hiddenimports=hiddenimports,
|
|
hookspath=['/Users/jamie/Projects/spacedriveapp/voicebox/backend/pyi_hooks'],
|
|
hooksconfig={},
|
|
runtime_hooks=['/Users/jamie/Projects/spacedriveapp/voicebox/backend/pyi_rth_numpy_compat.py', '/Users/jamie/Projects/spacedriveapp/voicebox/backend/pyi_rth_torch_compiler_disable.py'],
|
|
excludes=['nvidia', 'nvidia.cublas', 'nvidia.cuda_cupti', 'nvidia.cuda_nvrtc', 'nvidia.cuda_runtime', 'nvidia.cudnn', 'nvidia.cufft', 'nvidia.curand', 'nvidia.cusolver', 'nvidia.cusparse', 'nvidia.nccl', 'nvidia.nvjitlink', 'nvidia.nvtx'],
|
|
noarchive=False,
|
|
optimize=0,
|
|
)
|
|
pyz = PYZ(a.pure)
|
|
|
|
exe = EXE(
|
|
pyz,
|
|
a.scripts,
|
|
a.binaries,
|
|
a.datas,
|
|
[],
|
|
name='voicebox-server',
|
|
debug=False,
|
|
bootloader_ignore_signals=False,
|
|
strip=False,
|
|
upx=True,
|
|
upx_exclude=[],
|
|
runtime_tmpdir=None,
|
|
console=True,
|
|
disable_windowed_traceback=False,
|
|
argv_emulation=False,
|
|
target_arch=None,
|
|
codesign_identity=None,
|
|
entitlements_file=None,
|
|
)
|