aac_datasets.datasets.functional.wavcaps module¶

class WavCapsCard[source]¶

Bases: DatasetCard

ANNOTATIONS_CREATORS : Tuple[str, ...] = ('machine-generated',)¶

CAPTIONS_PER_AUDIO : Dict[Literal['audioset', 'bbc', 'freesound', 'soundbible', 'audioset_no_audiocaps_v1', 'freesound_no_clotho_v2'], int] = {'audioset': 1, 'audioset_no_audiocaps_v1': 1, 'bbc': 1, 'freesound': 1, 'freesound_no_clotho_v2': 1, 'soundbible': 1}¶

CITATION : str = '\n @article{mei2023WavCaps,\n title = {Wav{C}aps: A {ChatGPT}-Assisted Weakly-Labelled Audio Captioning Dataset for Audio-Language Multimodal Research},\n author = {Xinhao Mei and Chutong Meng and Haohe Liu and Qiuqiang Kong and Tom Ko and Chengqi Zhao and Mark D. Plumbley and Yuexian Zou and Wenwu Wang},\n year = 2023,\n journal = {arXiv preprint arXiv:2303.17395},\n url = {https://arxiv.org/pdf/2303.17395.pdf}\n }\n '¶

DEFAULT_REVISION : str = '85a0c21e26fa7696a5a74ce54fada99a9b43c6de'¶

DEFAULT_SUBSET : Literal['audioset', 'bbc', 'freesound', 'soundbible', 'audioset_no_audiocaps_v1', 'freesound_no_clotho_v2'] = 'audioset_no_audiocaps_v1'¶

DESCRIPTION : str = 'WavCaps: A ChatGPT-Assisted Weakly-Labelled Audio Captioning Dataset for Audio-Language Multimodal Research.'¶

EXPECTED_SIZES : Dict[Literal['AudioSet_SL', 'BBC_Sound_Effects', 'FreeSound', 'SoundBible'], int] = {'AudioSet_SL': 108317, 'BBC_Sound_Effects': 31201, 'FreeSound': 262300, 'SoundBible': 1320}¶

HOMEPAGE = 'https://huggingface.co/datasets/cvssp/WavCaps'¶

LANGUAGE : Tuple[str, ...] = ('en',)¶

LANGUAGE_DETAILS : Tuple[str, ...] = ('en-US',)¶

NAME : str = 'wavcaps'¶

PRETTY_NAME : str = 'WavCaps'¶

REPO_ID : str = 'cvssp/WavCaps'¶

SAMPLE_RATE : int = 32000¶

SIZE_CATEGORIES : Tuple[str, ...] = ('100K<n<1M',)¶

SOURCES : Tuple[Literal['AudioSet_SL', 'BBC_Sound_Effects', 'FreeSound', 'SoundBible'], ...] = ('AudioSet_SL', 'BBC_Sound_Effects', 'FreeSound', 'SoundBible')¶

SUBSETS : Tuple[Literal['audioset', 'bbc', 'freesound', 'soundbible', 'audioset_no_audiocaps_v1', 'freesound_no_clotho_v2'], ...] = ('audioset', 'bbc', 'freesound', 'soundbible', 'audioset_no_audiocaps_v1', 'freesound_no_clotho_v2')¶

TASK_CATEGORIES : Tuple[str, ...] = ('audio-to-text', 'text-to-audio')¶

download_wavcaps_dataset(

root: str | Path | None = None,

subset: 'audioset' | 'bbc' | 'freesound' | 'soundbible' | 'audioset_no_audiocaps_v1' | 'freesound_no_clotho_v2' = 'audioset_no_audiocaps_v1',

force: bool = False,

verbose: int = 0,

verify_files: bool = False,

*,

clean_archives: bool = False,

hf_cache_dir: str | None = None,

repo_id: str | None = None,

revision: str | None = None,

zip_path: str | Path | None = None,

) → None[source]¶

Prepare WavCaps data.

Parameters:¶

root: str | Path | None = None¶

Dataset root directory. defaults to “.”.

subset: 'audioset' | 'bbc' | 'freesound' | 'soundbible' | 'audioset_no_audiocaps_v1' | 'freesound_no_clotho_v2' = 'audioset_no_audiocaps_v1'¶

The subset of MACS to use. Can be one of SUBSETS. defaults to “audioset_no_audiocaps_v1”.

force: bool = False¶

If True, force to download again all files. defaults to False.

verbose: int = 0¶

Verbose level. defaults to 0.

verify_files: bool = False¶

If True, check all file already downloaded are valid. defaults to False.

clean_archives: bool = False¶

If True, remove the compressed archives from disk to save space. defaults to True.

hf_cache_dir: str | None = None¶

Optional override for HuggingFace cache directory path. defaults to None.

repo_id: str | None = None¶

Repository ID on HuggingFace. defaults to “cvssp/WavCaps”.

revision: str | None = None¶

Optional override for revision commit/name for HuggingFace rapository. defaults to None.

zip_path: str | Path | None = None¶

Path to zip executable path in shell. defaults to “zip”.

download_wavcaps_datasets(

root: str | Path | None = None,

subsets: 'audioset' | 'bbc' | 'freesound' | 'soundbible' | 'audioset_no_audiocaps_v1' | 'freesound_no_clotho_v2' | Iterable['audioset' | 'bbc' | 'freesound' | 'soundbible' | 'audioset_no_audiocaps_v1' | 'freesound_no_clotho_v2'] = 'audioset_no_audiocaps_v1',

force: bool = False,

verbose: int = 0,

*,

clean_archives: bool = False,

hf_cache_dir: str | None = None,

repo_id: str | None = None,

revision: str | None = None,

verify_files: bool = False,

zip_path: str | Path | None = None,

) → None[source]¶

Function helper to download a list of subsets. See download_wavcaps_dataset() for details.

load_wavcaps_dataset(

root: str | Path | None = None,

subset: 'audioset' | 'bbc' | 'freesound' | 'soundbible' | 'audioset_no_audiocaps_v1' | 'freesound_no_clotho_v2' = 'audioset_no_audiocaps_v1',

verbose: int = 0,

*,

hf_cache_dir: str | None = None,

revision: str | None = None,

) → dict[str, list[Any]][source]¶

Load WavCaps metadata.

Parameters:¶

root: str | Path | None = None¶

Dataset root directory. defaults to “.”.

subset: 'audioset' | 'bbc' | 'freesound' | 'soundbible' | 'audioset_no_audiocaps_v1' | 'freesound_no_clotho_v2' = 'audioset_no_audiocaps_v1'¶

The subset of MACS to use. Can be one of SUBSETS. defaults to “audioset_no_audiocaps_v1”.

verbose: int = 0¶

Verbose level. defaults to 0.

hf_cache_dir: str | None = None¶

Optional override for HuggingFace cache directory path. defaults to None.

revision: str | None = None¶

Optional override for revision commit/name for HuggingFace rapository. defaults to None.

Returns:¶

A dictionnary of lists containing each metadata.