def pad(cut_manifest: Pathlike, output_cut_manifest: Pathlike,
duration: Optional[float]):
"""
Create a new CutSet by padding the cuts in CUT_MANIFEST. The cuts will be right-padded, i.e. the padding
is placed after the signal ends.
"""
cut_set = CutSet.from_file(cut_manifest)
padded_cut_set = cut_set.pad(desired_duration=duration)
padded_cut_set.to_file(output_cut_manifest)
def append(
cut_manifests: List[Pathlike],
output_cut_manifest: Pathlike,
):
"""
Create a new CutSet by appending the cuts in CUT_MANIFESTS. CUT_MANIFESTS are iterated position-wise (the
cuts on i'th position in each manfiest are appended to each other).
The cuts are appended in the order in which they appear in the
input argument list.
If CUT_MANIFESTS have different lengths, the script stops once the shortest CutSet is depleted.
"""
cut_sets = [CutSet.from_file(path) for path in cut_manifests]
appended_cut_set = CutSet.from_cuts(append_cuts(cuts) for cuts in zip(*cut_sets))
appended_cut_set.to_file(output_cut_manifest)
def truncate(
cut_manifest: Pathlike,
output_cut_manifest: Pathlike,
preserve_id: bool,
max_duration: float,
offset_type: str,
keep_overflowing_supervisions: bool,
):
"""
Truncate the cuts in the CUT_MANIFEST and write them to OUTPUT_CUT_MANIFEST.
Cuts shorter than MAX_DURATION will not be modified.
"""
cut_set = CutSet.from_file(cut_manifest)
truncated_cut_set = cut_set.truncate(
max_duration=max_duration,
offset_type=offset_type,
keep_excessive_supervisions=keep_overflowing_supervisions,
preserve_id=preserve_id,
)
truncated_cut_set.to_file(output_cut_manifest)
def cuts():
cuts = CutSet.from_file("test/fixtures/libri/cuts.json")
# Concatenate 100 cut sets together, starting with an empty CutSet()
return sum((cuts.modify_ids(lambda cid: cid + str(i)) for i in range(100)),
CutSet())
