bi S SK Jr S SKJr S SKJr S SKrS SKrS SKJ r J
r
\ " S S5 5 r \ " S\" \ S S
9S S 9r S
\ l
\ " S\" \
/ SQS9SS 9rS\l
\ " S\" \
/ SQS9SS 9rS\l
g) ) dataclass)partial)CallableN)conv_tasnet_base hdemucs_highc \ rS rSr% Sr\\S' \/ \R R 4 \S' \ \S' \ S\ 4S j5 r
S\R R 4S jrS rg
) SourceSeparationBundle uI Dataclass that bundles components for performing source separation.
Example
>>> import torchaudio
>>> from torchaudio.pipelines import CONVTASNET_BASE_LIBRI2MIX
>>> import torch
>>>
>>> # Build the separation model.
>>> model = CONVTASNET_BASE_LIBRI2MIX.get_model()
>>> 100%|███████████████████████████████|19.1M/19.1M [00:04<00:00, 4.93MB/s]
>>>
>>> # Instantiate the test set of Libri2Mix dataset.
>>> dataset = torchaudio.datasets.LibriMix("/home/datasets/", subset="test")
>>>
>>> # Apply source separation on mixture audio.
>>> for i, data in enumerate(dataset):
>>> sample_rate, mixture, clean_sources = data
>>> # Make sure the shape of input suits the model requirement.
>>> mixture = mixture.reshape(1, 1, -1)
>>> estimated_sources = model(mixture)
>>> score = si_snr_pit(estimated_sources, clean_sources) # for demonstration
>>> print(f"Si-SNR score is : {score}.)
>>> break
>>> Si-SNR score is : 16.24.
>>>
_model_path_model_factory_func _sample_ratereturnc U R $ )zCSample rate of the audio that the model is trained on.
:type: int
)r
)selfs j/home/james-whalen/.local/lib/python3.13/site-packages/torchaudio/pipelines/_source_separation_pipeline.py sample_rate"SourceSeparationBundle.sample_rate, s c U R 5 n[ R R U R 5 n[
R " U5 nUR U5 UR 5 U$ )z3Construct the model and load the pretrained weight.) r
torchaudioutils_download_assetr torchloadload_state_dicteval)r modelpath
state_dicts r get_model SourceSeparationBundle.get_model4 sV ((* //0@0@AZZ%
j)
r N)__name__
__module__ __qualname____firstlineno____doc__str__annotations__r r nnModuleintpropertyr r __static_attributes__r" r r r r sZ 6 !"ehhoo"566
!S ! !588?? r r z$models/conv_tasnet_base_libri2mix.pt ) num_sourcesi@ )r r r
a Pre-trained Source Separation pipeline with *ConvTasNet*
:cite:`Luo_2019` trained on *Libri2Mix dataset* :cite:`cosentino2020librimix`.
The source separation model is constructed by :func:`~torchaudio.models.conv_tasnet_base`
and is trained using the training script ``lightning_train.py``
`here `__
with default arguments.
Please refer to :class:`SourceSeparationBundle` for usage instructions.
z models/hdemucs_high_trained.pt)drumsbassothervocals)sourcesiD a Pre-trained music source separation pipeline with
*Hybrid Demucs* :cite:`defossez2021hybrid` trained on both training and test sets of
MUSDB-HQ :cite:`MUSDB18HQ` and an additional 150 extra songs from an internal database
that was specifically produced for Meta.
The model is constructed by :func:`~torchaudio.models.hdemucs_high`.
Training was performed in the original HDemucs repository `here `__.
Please refer to :class:`SourceSeparationBundle` for usage instructions.
z#models/hdemucs_high_musdbhq_only.pta Pre-trained music source separation pipeline with
*Hybrid Demucs* :cite:`defossez2021hybrid` trained on the training set of MUSDB-HQ :cite:`MUSDB18HQ`.
The model is constructed by :func:`~torchaudio.models.hdemucs_high`.
Training was performed in the original HDemucs repository `here `__.
Please refer to :class:`SourceSeparationBundle` for usage instructions.
) dataclassesr functoolsr typingr r r torchaudio.modelsr r r CONVTASNET_BASE_LIBRI2MIXr' HDEMUCS_HIGH_MUSDB_PLUSHDEMUCS_HIGH_MUSDBr" r r r= s ! < / / /d 36 0a@
% ! 10 6Z[
# ,5 6Z[
r