ertk.preprocessing.fairseq.FairseqExtractorConfig

class ertk.preprocessing.fairseq.FairseqExtractorConfig(checkpoint: str = '???', layer: str = 'context', aggregate: Agg = Agg.MEAN, device: str = 'cuda', vq_path: str | None = None, vq_ids: bool = False, vq_ids_as_string: bool = True, max_input_len: int = 1500000)

Bases: ERTKConfig

Fairseq feature extractor configuration.

__init__(checkpoint: str = '???', layer: str = 'context', aggregate: Agg = Agg.MEAN, device: str = 'cuda', vq_path: str | None = None, vq_ids: bool = False, vq_ids_as_string: bool = True, max_input_len: int = 1500000) → None

Methods

__init__([checkpoint, layer, aggregate, ...])

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	Aggregation method.
checkpoint	Path to model checkpoint.
device	Device to run model on.
layer	Layer to extract features from.
max_input_len	Maximum input length.
vq_ids	Whether to return VQ cluster ids.
vq_ids_as_string	Whether to return VQ cluster ids as a single string of integers separated by spaces.
vq_path	Path to vector quantiser.

aggregate: Agg = 'mean'

Aggregation method.

checkpoint: str = '???'

Path to model checkpoint.

device: str = 'cuda'

Device to run model on.

layer: str = 'context'

Layer to extract features from.

max_input_len: int = 1500000

Maximum input length.

vq_ids: bool = False

Whether to return VQ cluster ids.

vq_ids_as_string: bool = True

Whether to return VQ cluster ids as a single string of integers separated by spaces.

vq_path: str | None = None

Path to vector quantiser.