mirror of
https://github.com/pyannote/pyannote-audio.git
synced 2026-11-20 13:07:51 +09:00
* feat(cli): add --subfolder option to benchmark command (#2063) * fix(utils): fix `SpeakerDiarizationMixin.optimal_mapping` when `reference` is a mapping * fix(task): fix `balance` option crashing training with `KeyError: 'metadata'` (#2067) * fix(io): fix `Audio.crop` raising when an in-memory waveform is cropped up to its very end (#2068) * fix(model): make Model.default_activation return identity for unsupported tasks * fix: compute sample duration from preloaded waveform * fix(pipeline): omit unset runtime options from model references (#2080) Co-authored-by: abeeranajam31 <128603901+abeeranajam31@users.noreply.github.com> Co-authored-by: antoinelaurent <antoinelaurent@me.com> Co-authored-by: Kayvan Zahiri <123409429+Kayvan-Zahiri@users.noreply.github.com> Co-authored-by: Mohammad Hijjawi <51020382+MohammadHijjawi97@users.noreply.github.com>
22 lines
620 B
Python
22 lines
620 B
Python
# Copyright (c) 2025- pyannoteAI
|
|
|
|
import pytest
|
|
import torch
|
|
|
|
|
|
def test_separation_masker():
|
|
pytest.importorskip("asteroid")
|
|
pytest.importorskip("transformers")
|
|
from pyannote.audio.models.separation.ToTaToNet import ToTaToNet
|
|
|
|
model = ToTaToNet(
|
|
use_wavlm=False,
|
|
n_sources=2,
|
|
dprnn={"n_repeats": 1, "bn_chan": 8, "hid_size": 8, "chunk_size": 10},
|
|
).eval()
|
|
with torch.inference_mode():
|
|
encoded = model.encoder(torch.randn(1, 1, 1600))
|
|
masks = model.masker(encoded)
|
|
assert masks.shape == (1, 2, *encoded.shape[1:])
|
|
assert torch.isfinite(masks).all()
|