crowsetta.formats.seq.audseq.AudSeq

crowsetta.formats.seq.audseq.AudSeq#

class crowsetta.formats.seq.audseq.AudSeq(start_times: ndarray, end_times: ndarray, labels: ndarray, annot_path: Path, notated_path=None)[source]#

Bases: object

Class meant to represent Audacity Labeltrack annotations exported to txt files in the standard format [1]_.

The txt file will have 3 tab-separated columns that represent the start time, end time, and labels of annotated regions.

name#

Shorthand name for annotation format: 'aud-seq'.

Type:

str

ext#

Extension of files in annotation format, '.txt'.

Type:

str

start_times#

Vector of integer sample numbers corresponding to beginning of segments, i.e. onsets.

Type:

numpy.ndarray

end_times#

Vector of integer sample numbers corresponding to ends of segments, i.e. offsets.

Type:

numpy.ndarray

labels#

Vector of string labels for segments; each element is either a single word, or a single phonetic transcription code.

Type:

numpy.ndarray

annot_path#

Path to file from which annotations were loaded.

Type:

str, pathlib.Path

notated_path#

Path to file that annot_path annotates. E.g., an audio file, or an array file that contains a spectrogram generated from audio. Optional, default is None.

Type:

str, pathlib.Path

Examples

>>> audseq = crowsetta.example('marron1')
>>> print(audseq)
AudSeq(start_times=array([ 0.        ,  0.76981817,  1.13127401,  2.21840074,  2.55502374,
        3.09030949,  3.69457537,  3.81322118,  4.05603121,  4.86171904,
        4.87551507,  5.52392822,  6.55587085,  6.59449972,  7.0883974 ,
        7.18772877,  7.23463526,  7.94375092,  9.01984083,  9.06950652,
        9.18263392, 10.06282028, 10.07661631, 10.9705987 , 10.98715393,
    11.80663778, 11.86458109, 12.19016727, 13.24142433, 13.277294  ,
    14.49686257, 14.60723076, 15.22805186, 15.31082801, 16.22136563,
    17.25606747, 18.16660509, 18.20247475, 19.65381653, 19.75590711,
    20.71059201, 20.78509054, 20.96719806, 21.02514137, 21.35624596,
    21.45005892, 21.66527691, 21.67355452, 22.73860761, 22.82966137,
    23.63534921, 24.59831172, 24.60383013, 24.67281025, 24.77214163,
    25.68267925, 25.70751209, 26.65943778, 27.7410461 , 27.76036054,
    28.34531198]), end_times=array([ 0.76981817,  1.13127401,  2.21840074,  2.55502374,  3.09030949,
        3.69457537,  3.81322118,  4.05603121,  4.86171904,  4.87551507,
        5.53496504,  6.55587085,  6.59449972,  7.0883974 ,  7.18772877,
        7.23463526,  7.94375092,  9.01984083,  9.06950652,  9.18263392,
    10.06282028, 10.07661631, 10.9705987 , 10.98715393, 11.80663778,
    11.86458109, 12.20396329, 13.24142433, 13.277294  , 14.49686257,
    14.60723076, 15.22805186, 15.31082801, 16.22136563, 17.25606747,
    18.16660509, 18.20247475, 19.65381653, 19.75590711, 20.71059201,
    20.78509054, 20.96719806, 21.02514137, 21.35624596, 21.45005892,
    21.66527691, 21.67355452, 22.73860761, 22.82966137, 23.63534921,
    24.59831172, 24.60383013, 24.67281025, 24.77214163, 25.68267925,
    25.70751209, 26.65943778, 27.7410461 , 27.76036054, 28.359108  ,
    29.10133412]), labels=<StringArray>
[ 'SIL', 'call',  'SIL', 'call',  'SIL',    'Z',  'SIL',   'Ci',    'C',
'SIL',    'H',    'E',  'SIL',    'R',  'SIL',   'J1',   'J1',   'J2',
'J2',  'SIL',   'B1',  'SIL',   'B2',  'SIL',    'Q',  'SIL',    'H',
    'E',  'SIL',    'R',  'SIL',    'O',  'SIL',   'J1',   'J2',    'L',
'SIL',    'N',  'SIL',    'A',  'SIL',    'O',  'SIL',    'P',  'SIL',
    'K',  'SIL',    'V',  'SIL',   'J1',   'J2',  'SIL',   'J2',  'SIL',
'B1',  'SIL',   'B2',    'Q',  'SIL',    'H',    'E']
Length: 61, dtype: string, annot_path=PosixPath('/Users/davidnicholson/Documents/repos/vocalpy/crowsetta/src/crowsetta/examples/405_marron1_June_14_2016_69640887.audacity.txt'), notated_path=None)  # noqa: E501

References

__init__(start_times: ndarray, end_times: ndarray, labels: ndarray, annot_path: Path, notated_path=None) → None#

Method generated by attrs for class AudSeq.

Methods

__init__(start_times, end_times, labels, ...)

Method generated by attrs for class AudSeq.

from_file(annot_path[, notated_path])

Load annotations from a file.

to_annot([round_times, decimals])

Convert this annotation to a crowsetta.Annotation.

to_file(annot_path)

Save this 'aud-seq' annotation to a txt file in the standard/default Audacity LabelTrack format.

to_seq([round_times, decimals])

Convert this annotation to a crowsetta.Sequence.

Attributes

start_times

end_times

labels

annot_path

notated_path

ext

name

classmethod from_file(annot_path: str | bytes | PathLike | Path, notated_path: str | bytes | PathLike | Path | None = None) → Self[source]#

Load annotations from a file.

Parameters:

  • annot_path (str, pathlib.Path) – Path to an annotation file, with ‘.txt’ extension.

  • notated_path (str, pathlib.Path) – Path to file that annot_path annotates. E.g., an audio file, or an array file that contains a spectrogram generated from audio. Optional, default is None.

Examples

>>> path = crowsetta.example('marron1', return_path=True)
>>> audseq = crowsetta.formats.seq.AudSeq.from_file(path)
>>> print(audseq)
AudSeq(start_times=array([ 0.        ,  0.76981817,  1.13127401,  2.21840074,  2.55502374,
        3.09030949,  3.69457537,  3.81322118,  4.05603121,  4.86171904,
        4.87551507,  5.52392822,  6.55587085,  6.59449972,  7.0883974 ,
        7.18772877,  7.23463526,  7.94375092,  9.01984083,  9.06950652,
        9.18263392, 10.06282028, 10.07661631, 10.9705987 , 10.98715393,
    11.80663778, 11.86458109, 12.19016727, 13.24142433, 13.277294  ,
    14.49686257, 14.60723076, 15.22805186, 15.31082801, 16.22136563,
    17.25606747, 18.16660509, 18.20247475, 19.65381653, 19.75590711,
    20.71059201, 20.78509054, 20.96719806, 21.02514137, 21.35624596,
    21.45005892, 21.66527691, 21.67355452, 22.73860761, 22.82966137,
    23.63534921, 24.59831172, 24.60383013, 24.67281025, 24.77214163,
    25.68267925, 25.70751209, 26.65943778, 27.7410461 , 27.76036054,
    28.34531198]), end_times=array([ 0.76981817,  1.13127401,  2.21840074,  2.55502374,  3.09030949,
        3.69457537,  3.81322118,  4.05603121,  4.86171904,  4.87551507,
        5.53496504,  6.55587085,  6.59449972,  7.0883974 ,  7.18772877,
        7.23463526,  7.94375092,  9.01984083,  9.06950652,  9.18263392,
    10.06282028, 10.07661631, 10.9705987 , 10.98715393, 11.80663778,
    11.86458109, 12.20396329, 13.24142433, 13.277294  , 14.49686257,
    14.60723076, 15.22805186, 15.31082801, 16.22136563, 17.25606747,
    18.16660509, 18.20247475, 19.65381653, 19.75590711, 20.71059201,
    20.78509054, 20.96719806, 21.02514137, 21.35624596, 21.45005892,
    21.66527691, 21.67355452, 22.73860761, 22.82966137, 23.63534921,
    24.59831172, 24.60383013, 24.67281025, 24.77214163, 25.68267925,
    25.70751209, 26.65943778, 27.7410461 , 27.76036054, 28.359108  ,
    29.10133412]), labels=<StringArray>
[ 'SIL', 'call',  'SIL', 'call',  'SIL',    'Z',  'SIL',   'Ci',    'C',
'SIL',    'H',    'E',  'SIL',    'R',  'SIL',   'J1',   'J1',   'J2',
'J2',  'SIL',   'B1',  'SIL',   'B2',  'SIL',    'Q',  'SIL',    'H',
    'E',  'SIL',    'R',  'SIL',    'O',  'SIL',   'J1',   'J2',    'L',
'SIL',    'N',  'SIL',    'A',  'SIL',    'O',  'SIL',    'P',  'SIL',
    'K',  'SIL',    'V',  'SIL',   'J1',   'J2',  'SIL',   'J2',  'SIL',
'B1',  'SIL',   'B2',    'Q',  'SIL',    'H',    'E']
Length: 61, dtype: string, annot_path=PosixPath('/Users/davidnicholson/Documents/repos/vocalpy/crowsetta/src/crowsetta/examples/405_marron1_June_14_2016_69640887.audacity.txt'), notated_path=None)  # noqa: E501
to_annot(round_times: bool = True, decimals: int = 3) → Annotation[source]#

Convert this annotation to a crowsetta.Annotation.

Parameters:

  • round_times (bool) – If True, round onsets_s and offsets_s. Default is True.

  • decimals (int) – Number of decimals places to round floating point numbers to. Only meaningful if round_times is True. Default is 3, so that times are rounded to milliseconds.

Returns:

annot

Return type:

crowsetta.Annotation

Examples

>>> path = crowsetta.example('marron1')
>>> audseq = crowsetta.formats.seq.AudSeq.from_file(path)
>>> annot = audseq.to_annot()

Notes

The round_times and decimals arguments are provided to reduce differences across platforms due to floating point error, e.g. when loading annotation files and then sending them to a csv file, the result should be the same on Windows and Linux.

to_file(annot_path: str | bytes | PathLike | Path) → None[source]#

Save this ‘aud-seq’ annotation to a txt file in the standard/default Audacity LabelTrack format.

Parameters:

annot_path (str, pathlib.Path) – Path with filename of txt file that should be saved.

to_seq(round_times: bool = True, decimals: int = 3) → Sequence[source]#

Convert this annotation to a crowsetta.Sequence.

Parameters:

  • round_times (bool) – If True, round onsets_s and offsets_s. Default is True.

  • decimals (int) – Number of decimals places to round floating point numbers to. Only meaningful if round_times is True. Default is 3, so that times are rounded to milliseconds.

Returns:

seq

Return type:

crowsetta.Sequence

Examples

>>> path = crowsetta.example('marron1')
>>> audseq = crowsetta.formats.seq.AudSeq.from_file(path)
>>> seq = audseq.to_seq()

Notes

The round_times and decimals arguments are provided to reduce differences across platforms due to floating point error, e.g. when loading annotation files and then sending them to a csv file, the result should be the same on Windows and Linux.

Contents