ertk.preprocessing.fairseq.FairseqExtractor

class ertk.preprocessing.fairseq.FairseqExtractor(config: FairseqExtractorConfig)

Fairseq processor.

Methods

`__init__`(config)
`process_file`(path[, sr])	Process individual audio file.
`process_instance`(x, **kwargs)	Process a single audio clip.

Inherited Methods

`finish`()	Perform any cleanup necesasry (e.g.
`friendly_name`()	Get the friendly name for this processor.
`get_config_type`()	Get the configuration type for this processor.
`get_default_config`()	Get the default configuration for this processor.
`get_processor_class`(name)	Get the class for the named processor.
`make_processor`(name, config)	Create an instance of the named processor.
`process_all`(xs, batch_size, **kwargs)	Process all instances in batches.
`process_batch`(batch, **kwargs)	Process a batch of instances.
`process_files`(paths, batch_size[, sr])	Process a set of files.
`valid_processors`()	Get a list of all registered processor names.

Attributes

`dim`	The dimensionality of the extracted features.
`feature_names`	The names of the features produced by this processor.
`is_sequence`	Whether this FeatureExtractor yields sequence features.
`config`	The configuration for this processor.

property feature_names: List[str]: The names of the features produced by this processor.

property is_sequence: bool: Whether this FeatureExtractor yields sequence features.

process_file(path: PathLike | str, sr: float | None = None) → ndarray

Process individual audio file.

Parameters:

path: pathlike or str: The path to an audio file.
sr: float, optional: Target sample rate. If not given, then each audio file is loaded with its native sample rate. Otherwise audio data is resampled to this sample rate.

Returns:

process_instance(x: ndarray, **kwargs) → ndarray

Process a single audio clip.

Parameters:

Returns: