Files
pyannote-audio/tests/test_train.py
T
Hervé BREDIN 7121a73f08 feat: add support for label scope and missing classes (#1296)
- setup: switch to pyannote.database 5.0
- feat(task): add support for label scope in speaker diarization task (from pyannote.database 5.0)
- feat(task): add support for missing classes in multi-label segmentation task (from pyannote.database 5.0)
- improve(task): load metadata as tensors/arrays rather than pyannote.core instances
- BREAKING(task): rename `Segmentation` task to `SpeakerDiarization`
- BREAKING(task): remove support for variable chunk duration
2023-04-13 21:15:57 +02:00

145 lines
4.4 KiB
Python

import pytest
from pyannote.database import FileFinder, get_protocol
from pytorch_lightning import Trainer
from pyannote.audio.models.segmentation.debug import SimpleSegmentationModel
from pyannote.audio.tasks import (
OverlappedSpeechDetection,
SpeakerDiarization,
VoiceActivityDetection,
)
@pytest.fixture()
def protocol():
return get_protocol(
"Debug.SpeakerDiarization.Debug", preprocessors={"audio": FileFinder()}
)
def test_train_segmentation(protocol):
segmentation = SpeakerDiarization(protocol)
model = SimpleSegmentationModel(task=segmentation)
trainer = Trainer(fast_dev_run=True)
trainer.fit(model)
def test_train_voice_activity_detection(protocol):
voice_activity_detection = VoiceActivityDetection(protocol)
model = SimpleSegmentationModel(task=voice_activity_detection)
trainer = Trainer(fast_dev_run=True)
trainer.fit(model)
def test_train_overlapped_speech_detection(protocol):
overlapped_speech_detection = OverlappedSpeechDetection(protocol)
model = SimpleSegmentationModel(task=overlapped_speech_detection)
trainer = Trainer(fast_dev_run=True)
trainer.fit(model)
def test_finetune_with_task_that_does_not_need_setup_for_specs(protocol):
voice_activity_detection = VoiceActivityDetection(protocol)
model = SimpleSegmentationModel(task=voice_activity_detection)
trainer = Trainer(fast_dev_run=True)
trainer.fit(model)
voice_activity_detection = VoiceActivityDetection(protocol)
model.task = voice_activity_detection
trainer = Trainer(fast_dev_run=True)
trainer.fit(model)
def test_finetune_with_task_that_needs_setup_for_specs(protocol):
segmentation = SpeakerDiarization(protocol)
model = SimpleSegmentationModel(task=segmentation)
trainer = Trainer(fast_dev_run=True)
trainer.fit(model)
segmentation = SpeakerDiarization(protocol)
model.task = segmentation
trainer = Trainer(fast_dev_run=True)
trainer.fit(model)
def test_transfer_with_task_that_does_not_need_setup_for_specs(protocol):
segmentation = SpeakerDiarization(protocol)
model = SimpleSegmentationModel(task=segmentation)
trainer = Trainer(fast_dev_run=True)
trainer.fit(model)
voice_activity_detection = VoiceActivityDetection(protocol)
model.task = voice_activity_detection
trainer = Trainer(fast_dev_run=True)
trainer.fit(model)
def test_transfer_with_task_that_needs_setup_for_specs(protocol):
voice_activity_detection = VoiceActivityDetection(protocol)
model = SimpleSegmentationModel(task=voice_activity_detection)
trainer = Trainer(fast_dev_run=True)
trainer.fit(model)
segmentation = SpeakerDiarization(protocol)
model.task = segmentation
trainer = Trainer(fast_dev_run=True)
trainer.fit(model)
def test_finetune_freeze_with_task_that_needs_setup_for_specs(protocol):
segmentation = SpeakerDiarization(protocol)
model = SimpleSegmentationModel(task=segmentation)
trainer = Trainer(fast_dev_run=True)
trainer.fit(model)
segmentation = SpeakerDiarization(protocol)
model.task = segmentation
model.freeze_up_to("mfcc")
trainer = Trainer(fast_dev_run=True)
trainer.fit(model)
def test_finetune_freeze_with_task_that_does_not_need_setup_for_specs(protocol):
vad = VoiceActivityDetection(protocol)
model = SimpleSegmentationModel(task=vad)
trainer = Trainer(fast_dev_run=True)
trainer.fit(model)
vad = VoiceActivityDetection(protocol)
model.task = vad
model.freeze_up_to("mfcc")
trainer = Trainer(fast_dev_run=True)
trainer.fit(model)
def test_transfer_freeze_with_task_that_does_not_need_setup_for_specs(protocol):
segmentation = SpeakerDiarization(protocol)
model = SimpleSegmentationModel(task=segmentation)
trainer = Trainer(fast_dev_run=True)
trainer.fit(model)
voice_activity_detection = VoiceActivityDetection(protocol)
model.task = voice_activity_detection
model.freeze_up_to("mfcc")
trainer = Trainer(fast_dev_run=True)
trainer.fit(model)
def test_transfer_freeze_with_task_that_needs_setup_for_specs(protocol):
voice_activity_detection = VoiceActivityDetection(protocol)
model = SimpleSegmentationModel(task=voice_activity_detection)
trainer = Trainer(fast_dev_run=True)
trainer.fit(model)
segmentation = SpeakerDiarization(protocol)
model.task = segmentation
model.freeze_up_to("mfcc")
trainer = Trainer(fast_dev_run=True)
trainer.fit(model)