mirror of
https://github.com/pyannote/pyannote-audio.git
synced 2026-11-20 13:07:51 +09:00
* closes #476 (CLI) * closes #514 (support for AutoLR) * closes #485 (hyper-parameter optimization with Hydra’s Ax sweeper) * closes #412 (log graph to Tensorboard)
4.3 KiB
4.3 KiB
In [ ]:
from pyannote.database import get_protocol, FileFinder
protocol = get_protocol('Debug.SpeakerDiarization.Debug',
preprocessors={"audio": FileFinder()})In [ ]:
from pyannote.audio.models.debug import SimpleSegmentationModel
from pyannote.audio.models.debug import MultiTaskSegmentationModel
from pyannote.audio.models.debug import SimpleEmbeddingModel
import pytorch_lightning as plIn [ ]:
from pyannote.audio.utils.preview import listen
listen(next(protocol.train()))In [ ]:
from pyannote.audio.tasks import VoiceActivityDetection
vad = VoiceActivityDetection(protocol, duration=2., batch_size=32, num_workers=4)
model = SimpleSegmentationModel(task=vad)
trainer = pl.Trainer(max_epochs=1)
_ = trainer.fit(model, vad)In [ ]:
from pyannote.audio.tasks import SpeakerChangeDetection
scd = SpeakerChangeDetection(protocol, duration=2., batch_size=32, num_workers=4)
model = SimpleSegmentationModel(task=scd)
trainer = pl.Trainer(max_epochs=1)
_ = trainer.fit(model, scd)In [ ]:
from pyannote.audio.tasks import OverlappedSpeechDetection
ovl = OverlappedSpeechDetection(protocol, duration=2., batch_size=32, num_workers=4)
model = SimpleSegmentationModel(task=ovl)
trainer = pl.Trainer(max_epochs=1)
_ = trainer.fit(model, ovl)In [ ]:
from pyannote.audio.tasks import MultiTaskSegmentation
seg = MultiTaskSegmentation(protocol, vad=True, scd=True, osd=True, duration=2., batch_size=32, num_workers=4)
model = MultiTaskSegmentationModel(task=seg)
trainer = pl.Trainer(max_epochs=1)
_ = trainer.fit(model, seg)In [ ]:
from pyannote.audio.tasks import SpeakerTracking
spk = SpeakerTracking(protocol, duration=2., batch_size=32, num_workers=4)
model = SimpleSegmentationModel(task=spk)
trainer = pl.Trainer(max_epochs=1)
_ = trainer.fit(model, spk)In [ ]:
from pyannote.audio.tasks.speaker_verification.task import SpeakerEmbeddingArcFace
emb = SpeakerEmbeddingArcFace(protocol, duration=2., num_workers=4)
model = SimpleEmbeddingModel(task=emb)
trainer = pl.Trainer(max_epochs=1)
_ = trainer.fit(model, emb)