mirror of
https://github.com/jamiepine/voicebox.git
synced 2026-09-16 13:20:39 -07:00
a383ff6863
torch is compiled against numpy 1.x. numpy 2.x changed the ABI version returned by PyArray_GetNDArrayCVersion() (0x01000009 → 0x02000000), so torch's is_numpy_available() always returns False and torch.from_numpy() raises RuntimeError. This causes TTS generation to fail with: ValueError: Unable to create tensor, you should probably activate padding with 'padding=True' Two fixes: 1. Pin numpy<2.0 in requirements.txt so new builds bundle a compatible numpy version. (The existing comment already flagged this intention but the upper bound was never added.) 2. Add a PyInstaller runtime hook (pyi_rth_numpy_compat.py) that installs a ctypes memmove fallback for torch.from_numpy() at startup. Runtime hooks run after FrozenImporter is registered so frozen torch is importable. The fallback catches RuntimeError from the C-level ABI check and copies the numpy array into a new tensor via raw memory copy, bypassing the check entirely. This is a belt-and-suspenders fix that works regardless of the bundled numpy version. Co-authored-by: aimaaaimaa <[email protected]> Co-authored-by: Claude Sonnet 4.6 <[email protected]>
81 lines
2.6 KiB
Python
81 lines
2.6 KiB
Python
"""
|
|
PyInstaller runtime hook: numpy 2.x / torch ABI mismatch fix.
|
|
|
|
Problem
|
|
-------
|
|
torch is compiled against numpy 1.x headers. numpy 2.x changed the version
|
|
number returned by PyArray_GetNDArrayCVersion() (0x01000009 → 0x02000000),
|
|
so torch's is_numpy_available() returns False and every torch.from_numpy()
|
|
call raises:
|
|
|
|
RuntimeError: Numpy is not available
|
|
|
|
This surfaces as:
|
|
|
|
ValueError: Unable to create tensor, you should probably activate
|
|
padding with 'padding=True'
|
|
|
|
during TTS generation (EncodecFeatureExtractor → BatchFeature.convert_to_tensors).
|
|
|
|
Fix
|
|
---
|
|
Runtime hooks execute after PyInstaller's FrozenImporter is registered, so
|
|
frozen torch/numpy are importable here. We start a background thread that
|
|
waits for torch to finish loading then wraps torch.from_numpy with a ctypes
|
|
memmove fallback that bypasses the C-level numpy ABI check entirely.
|
|
|
|
This approach works with any numpy version and is safer than binary-patching
|
|
libtorch_python.dylib (which risks PyArray_Descr struct layout mismatches).
|
|
"""
|
|
|
|
import sys
|
|
import threading
|
|
|
|
|
|
def _patch_torch_from_numpy():
|
|
import time
|
|
|
|
for _ in range(7200): # poll up to 360 s at 50 ms intervals
|
|
time.sleep(0.05)
|
|
torch = sys.modules.get("torch")
|
|
if torch is None or not hasattr(torch, "from_numpy"):
|
|
continue
|
|
if getattr(torch, "_vb_from_numpy_patched", False):
|
|
return
|
|
try:
|
|
import ctypes
|
|
import numpy as np
|
|
|
|
_orig = torch.from_numpy
|
|
|
|
def _safe_from_numpy(arr, _orig=_orig, _c=ctypes, _np=np, _t=torch):
|
|
try:
|
|
return _orig(arr)
|
|
except RuntimeError:
|
|
a = _np.ascontiguousarray(arr)
|
|
dtype_map = {
|
|
"float32": _t.float32,
|
|
"float64": _t.float64,
|
|
"int32": _t.int32,
|
|
"int64": _t.int64,
|
|
"int16": _t.int16,
|
|
"int8": _t.int8,
|
|
"uint8": _t.uint8,
|
|
"bool": _t.bool,
|
|
}
|
|
out = _t.empty(
|
|
list(a.shape),
|
|
dtype=dtype_map.get(str(a.dtype), _t.float32),
|
|
)
|
|
_c.memmove(out.data_ptr(), a.ctypes.data, a.nbytes)
|
|
return out
|
|
|
|
torch.from_numpy = _safe_from_numpy
|
|
torch._vb_from_numpy_patched = True
|
|
except Exception:
|
|
pass
|
|
return
|
|
|
|
|
|
threading.Thread(target=_patch_torch_from_numpy, daemon=True).start()
|