aac_metrics.classes.clap_sim module

class CLAPSim(

return_all_scores: bool = True,

*,

clap_method: Literal['audio', 'text'] = 'text',

clap_model: str | CLAPWrapper = 'MS-CLAP-2023',

device: str | device | None = 'cuda_if_available',

batch_size: int | None = 32,

reset_state: bool = True,

seed: int | None = 42,

verbose: int = 0,

)

Bases: AACMetric[tuple[CLAPScores, CLAPScores] | Tensor]

Cosine-similarity of the Contrastive Language-Audio Pretraining (CLAP) embeddings.

The implementation is based on the msclap pypi package. Note: Instances of this class are not pickable.

• Paper: https://arxiv.org/pdf/2411.00321

• msclap package: https://pypi.org/project/msclap/

For more information, see clap_sim().

compute() → tuple[CLAPScores, CLAPScores] | Tensor

extra_repr() → str

Return the extra representation of the module.

To print customized extra information, you should re-implement this method in your own modules. Both single-line and multi-line strings are acceptable.

full_state_update: ClassVar[bool | None] = False

get_output_names() → tuple[str, ...]

higher_is_better: ClassVar[bool | None] = True

is_differentiable: ClassVar[bool | None] = False

max_value: ClassVar[float] = 1.0

min_value: ClassVar[float] = -1.0

reset() → None

training: bool

update(

candidates: list[str],

mult_references_or_audio_paths: list[list[str]] | list[str],

) → None