mirror of
https://github.com/pyannote/pyannote-audio.git
synced 2026-11-20 13:07:51 +09:00
1.2 MiB
1.2 MiB
In [1]:
from pyannote.database import registry, FileFinder
registry.load_database('../tests/data/database.yml')
protocol = registry.get_protocol('Debug.SpeakerDiarization.Debug',
preprocessors={"audio": FileFinder()})'Debug.SpeakerDiarization.Debug' found in /Users/hbredin/Development/pyannote/pyannote-audio/tests/data/database.yml does not define the 'scope' of speaker labels (file, database, or global). Setting it to 'file'. 'Debug.SpeakerDiarization.Bug1237' found in /Users/hbredin/Development/pyannote/pyannote-audio/tests/data/database.yml does not define the 'scope' of speaker labels (file, database, or global). Setting it to 'file'.
In [2]:
from pyannote.audio.models.segmentation.debug import SimpleSegmentationModel
from pyannote.audio.models.embedding.debug import SimpleEmbeddingModel
import lightning.pytorch as plIn [3]:
from pyannote.audio.utils.preview import listen
listen(next(protocol.train()))Out [3]:
In [4]:
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)GPU available: True (mps), used: False
Protocol Debug.SpeakerDiarization.Debug does not precompute the output of torchaudio.info(): adding a 'torchaudio.info' preprocessor for you to speed up dataloaders. See pyannote.database documentation on how to do that yourself.
TPU available: False, using: 0 TPU cores IPU available: False, using: 0 IPUs HPU available: False, using: 0 HPUs Missing logger folder: /Users/hbredin/Development/pyannote/pyannote-audio/notebook/lightning_logs | Name | Type | Params | In sizes | Out sizes ---------------------------------------------------------------------------------------------------------------------- 0 | mfcc | MFCC | 0 | [32, 1, 32000] | [32, 1, 40, 161] 1 | lstm | LSTM | 18.9 K | [32, 161, 40] | [[32, 161, 64], [[2, 32, 32], [2, 32, 32]]] 2 | classifier | Linear | 65 | [32, 161, 64] | [32, 161, 1] 3 | activation | Sigmoid | 0 | [32, 161, 1] | [32, 161, 1] 4 | validation_metric | MetricCollection | 0 | ? | ? ---------------------------------------------------------------------------------------------------------------------- 19.0 K Trainable params 0 Non-trainable params 19.0 K Total params 0.076 Total estimated model params size (MB)
Sanity Checking: 0it [00:00, ?it/s]
Training: 0it [00:00, ?it/s]
Validation: 0it [00:00, ?it/s]
`Trainer.fit` stopped: `max_epochs=1` reached.
In [5]:
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)GPU available: True (mps), used: False TPU available: False, using: 0 TPU cores IPU available: False, using: 0 IPUs HPU available: False, using: 0 HPUs | Name | Type | Params | In sizes | Out sizes ---------------------------------------------------------------------------------------------------------------------- 0 | mfcc | MFCC | 0 | [32, 1, 32000] | [32, 1, 40, 161] 1 | lstm | LSTM | 18.9 K | [32, 161, 40] | [[32, 161, 64], [[2, 32, 32], [2, 32, 32]]] 2 | classifier | Linear | 65 | [32, 161, 64] | [32, 161, 1] 3 | activation | Sigmoid | 0 | [32, 161, 1] | [32, 161, 1] 4 | validation_metric | MetricCollection | 0 | ? | ? ---------------------------------------------------------------------------------------------------------------------- 19.0 K Trainable params 0 Non-trainable params 19.0 K Total params 0.076 Total estimated model params size (MB)
Sanity Checking: 0it [00:00, ?it/s]
Training: 0it [00:00, ?it/s]
Validation: 0it [00:00, ?it/s]
`Trainer.fit` stopped: `max_epochs=1` reached.
In [6]:
from pyannote.audio.tasks import SpeakerDiarization
seg = SpeakerDiarization(protocol, duration=2., batch_size=32, num_workers=4)
model = SimpleSegmentationModel(task=seg)
trainer = pl.Trainer(max_epochs=1)
_ = trainer.fit(model)GPU available: True (mps), used: False TPU available: False, using: 0 TPU cores IPU available: False, using: 0 IPUs HPU available: False, using: 0 HPUs
Output()
| Name | Type | Params | In sizes | Out sizes ---------------------------------------------------------------------------------------------------------------------- 0 | mfcc | MFCC | 0 | [32, 1, 32000] | [32, 1, 40, 161] 1 | lstm | LSTM | 18.9 K | [32, 161, 40] | [[32, 161, 64], [[2, 32, 32], [2, 32, 32]]] 2 | classifier | Linear | 195 | [32, 161, 64] | [32, 161, 3] 3 | activation | Sigmoid | 0 | [32, 161, 3] | [32, 161, 3] 4 | validation_metric | MetricCollection | 0 | ? | ? ---------------------------------------------------------------------------------------------------------------------- 19.1 K Trainable params 0 Non-trainable params 19.1 K Total params 0.077 Total estimated model params size (MB)
- 27.32% of all chunks contain no speech at all. - 66.79% contain 1 speaker or less - 91.25% contain 2 speakers or less - 98.04% contain 3 speakers or less - 100.00% contain 4 speakers or less Setting `max_speakers_per_chunk` to 3. You can override this value (or avoid this estimation step) by passing `max_speakers_per_chunk=3` to the task constructor.
Sanity Checking: 0it [00:00, ?it/s]
Training: 0it [00:00, ?it/s]
Validation: 0it [00:00, ?it/s]
`Trainer.fit` stopped: `max_epochs=1` reached.
In [7]:
from pyannote.audio.tasks import SpeakerEmbedding
emb = SpeakerEmbedding(protocol, duration=2., num_workers=4)
model = SimpleEmbeddingModel(task=emb)
trainer = pl.Trainer(max_epochs=1)
_ = trainer.fit(model)GPU available: True (mps), used: False TPU available: False, using: 0 TPU cores IPU available: False, using: 0 IPUs HPU available: False, using: 0 HPUs Loading Debug.SpeakerDiarization.Debug training labels: 10file [00:00, 363.55file/s] | Name | Type | Params | In sizes | Out sizes ---------------------------------------------------------------------------------------------------------------------- 0 | mfcc | MFCC | 0 | [32, 1, 32000] | [32, 1, 40, 161] 1 | lstm | LSTM | 18.9 K | [32, 161, 40] | [[32, 161, 64], [[2, 32, 32], [2, 32, 32]]] 2 | loss_func | ArcFaceLoss | 832 | ? | ? 3 | validation_metric | MetricCollection | 0 | ? | ? ---------------------------------------------------------------------------------------------------------------------- 19.8 K Trainable params 0 Non-trainable params 19.8 K Total params 0.079 Total estimated model params size (MB)
Sanity Checking: 0it [00:00, ?it/s]
Training: 0it [00:00, ?it/s]
`Trainer.fit` stopped: `max_epochs=1` reached.