in whisper/timing.py [0:0]
def median_filter(x: torch.Tensor, filter_width: int):
"""Apply a median filter of width `filter_width` along the last dimension of `x`"""
pad_width = filter_width // 2
if x.shape[-1] <= pad_width:
# F.pad requires the padding width to be smaller than the input dimension
return x
if (ndim := x.ndim) <= 2:
# `F.pad` does not support 1D or 2D inputs for reflect padding but supports 3D and 4D
x = x[None, None, :]
assert (
filter_width > 0 and filter_width % 2 == 1
), "`filter_width` should be an odd number"
result = None
x = F.pad(x, (filter_width // 2, filter_width // 2, 0, 0), mode="reflect")
if x.is_cuda:
try:
from .triton_ops import median_filter_cuda
result = median_filter_cuda(x, filter_width)
except (RuntimeError, subprocess.CalledProcessError):
warnings.warn(
"Failed to launch Triton kernels, likely due to missing CUDA toolkit; "
"falling back to a slower median kernel implementation..."
)
if result is None:
# sort() is faster than torch.median (https://github.com/pytorch/pytorch/issues/51450)
result = x.unfold(-1, filter_width, 1).sort()[0][..., filter_width // 2]
if ndim <= 2:
result = result[0, 0]
return result