ertk.preprocessing.encodec.EncodecExtractorConfig

class ertk.preprocessing.encodec.EncodecExtractorConfig(model: Model = Model.ENCODEC_48kHz, aggregate: Agg = Agg.MEAN, device: str = 'cuda', vq_ids: bool = False, vq_ids_as_string: bool = True, max_input_len: int = 1500000)

Bases: ERTKConfig

Configuration for the Encodec feature extractor.

__init__(model: Model = Model.ENCODEC_48kHz, aggregate: Agg = Agg.MEAN, device: str = 'cuda', vq_ids: bool = False, vq_ids_as_string: bool = True, max_input_len: int = 1500000) → None

Methods

__init__([model, aggregate, device, vq_ids, ...])

Inherited Methods

default()	Create default config.
from_config(config)	Create config object from any compatible config.
from_file(path)	Create config from YAML file and optionlly override some values.
merge_with_args(args)	Merge config with command-line arguments.
merge_with_config(config)	Merge other config into this config.
to_dictconfig()	Convert config to DictConfig.
to_file(path)	Write config to YAML file.
to_string()	Generate YAML string representation of config.

Attributes

aggregate	The aggregation method to use.
device	The device to use for inference.
max_input_len	The maximum input length for the model.
model	The Encodec model to use.
vq_ids	Whether to return the VQ-VAE IDs.
vq_ids_as_string	Whether to return the VQ-VAE IDs as a string.

aggregate: Agg = 'mean'

The aggregation method to use.

device: str = 'cuda'

The device to use for inference.

max_input_len: int = 1500000

The maximum input length for the model.

model: Model = '48kHz'

The Encodec model to use.

vq_ids: bool = False

Whether to return the VQ-VAE IDs.

vq_ids_as_string: bool = True

Whether to return the VQ-VAE IDs as a string.