Hugging Face's logo

Transformers documentation

PE Audio (Perception Encoder Audio)

You are viewing main version, which requires installation from source. If you'd like regular pip install, checkout the latest stable version (v5.3.0).
Hugging Face's logo
Join the Hugging Face community

and get access to the augmented documentation experience

to get started

This model was released on {release_date} and added to Hugging Face Transformers on 2025-12-16.

PE Audio (Perception Encoder Audio)

Overview

PE Audio (Perception Encoder Audio) is a state-of-the-art multimodal model that embeds audio and text into a shared (joint) embedding space. The model enables cross-modal retrieval and understanding between audio and text.

Text input

  • Produces a single embedding representing the full text.

Audio input

  • PeAudioFrameLevelModel
    • Produces a sequence of embeddings, one every 40 ms of audio.
    • Suitable for audio event localization and fine-grained temporal analysis.
  • PeAudioModel
    • Produces a single embedding for the entire audio clip.
    • Suitable for global audio-text retrieval tasks.

The resulting embeddings can be used for:

  • Audio event localization
  • Cross-modal (audio–text) retrieval and matching

Usage

Basic usage

TODO

PeAudioFeatureExtractor

class transformers.PeAudioFeatureExtractor

< >

( feature_size: int = 1 sampling_rate: int = 48000 padding_value: float = 0.0 hop_length: int = 1920 **kwargs )

Parameters

  • feature_size (int, optional, defaults to 1) — The feature dimension of the extracted features. Use 1 for mono, 2 for stereo.
  • sampling_rate (int, optional, defaults to 48000) — The sampling rate at which the audio waveform should be digitalized, expressed in hertz (Hz).
  • padding_value (float, optional, defaults to 0.0) — The value that is used for padding.
  • hop_length (int, optional, defaults to 1920) — Overlap length between successive windows.

Constructs a PeAudioFeatureExtractor feature extractor.

This feature extractor inherits from SequenceFeatureExtractor which contains most of the main methods. Users should refer to this superclass for more information regarding those methods.

__call__

< >

( raw_audio: numpy.ndarray | list[float] | list[numpy.ndarray] | list[list[float]] | str | list[str] padding: bool | str | transformers.utils.generic.PaddingStrategy | None = None truncation: bool | None = False max_length: int | None = None return_tensors: str | transformers.utils.generic.TensorType | None = None sampling_rate: int | None = None )

PeAudioProcessor

class transformers.PeAudioProcessor

< >

( *args **kwargs )

__call__

< >

( images: typing.Union[ForwardRef('PIL.Image.Image'), numpy.ndarray, ForwardRef('torch.Tensor'), list['PIL.Image.Image'], list[numpy.ndarray], list['torch.Tensor'], NoneType] = None text: str | list[str] | list[list[str]] | None = None videos: typing.Union[list['PIL.Image.Image'], numpy.ndarray, ForwardRef('torch.Tensor'), list[numpy.ndarray], list['torch.Tensor'], list[list['PIL.Image.Image']], list[list[numpy.ndarray]], list[list['torch.Tensor']], transformers.video_utils.URL, list[transformers.video_utils.URL], list[list[transformers.video_utils.URL]], transformers.video_utils.Path, list[transformers.video_utils.Path], list[list[transformers.video_utils.Path]], NoneType] = None audio: typing.Union[numpy.ndarray, ForwardRef('torch.Tensor'), collections.abc.Sequence[numpy.ndarray], collections.abc.Sequence['torch.Tensor'], NoneType] = None **kwargs: typing_extensions.Unpack[transformers.processing_utils.ProcessingKwargs] ) → BatchFeature

Parameters

  • images (PIL.Image.Image, np.ndarray, torch.Tensor, list[PIL.Image.Image], list[np.ndarray], list[torch.Tensor]) — The image or batch of images to be prepared. Each image can be a PIL image, NumPy array or PyTorch tensor. Both channels-first and channels-last formats are supported.
  • text (TextInput, PreTokenizedInput, list[TextInput], list[PreTokenizedInput], optional) — The sequence or batch of sequences to be encoded. Each sequence can be a string or a list of strings (pretokenized string). If the sequences are provided as list of strings (pretokenized), you must set is_split_into_words=True (to lift the ambiguity with a batch of sequences).
  • videos (np.ndarray, torch.Tensor, List[np.ndarray], List[torch.Tensor]) — The video or batch of videos to be prepared. Each video can be a 4D NumPy array or PyTorch tensor, or a nested list of 3D frames. Both channels-first and channels-last formats are supported.
  • audio (np.ndarray, torch.Tensor, list[np.ndarray], list[torch.Tensor]) — The audio or batch of audio to be prepared. Each audio can be a NumPy array or PyTorch tensor.
  • return_tensors (str or TensorType, optional) — If set, will return tensors of a particular framework. Acceptable values are:

    • 'pt': Return PyTorch torch.Tensor objects.
    • 'np': Return NumPy np.ndarray objects.

Returns

BatchFeature

A BatchFeature object with processed inputs in a dict format.

Main method to prepare for model inputs. This method forwards the each modality argument to its own processor along with kwargs. Please refer to the docstring of the each processor attributes for more information.

PeAudioConfig

class transformers.PeAudioConfig

< >

( output_hidden_states: bool | None = False return_dict: bool | None = True dtype: typing.Union[str, ForwardRef('torch.dtype'), NoneType] = None chunk_size_feed_forward: int = 0 is_encoder_decoder: bool = False id2label: dict[int, str] | dict[str, str] | None = None label2id: dict[str, int] | dict[str, str] | None = None problem_type: typing.Optional[typing.Literal['regression', 'single_label_classification', 'multi_label_classification']] = None tokenizer_class: str | None = None text_config: dict | transformers.configuration_utils.PreTrainedConfig | None = None audio_config: dict | transformers.configuration_utils.PreTrainedConfig | None = None )

Parameters

  • output_hidden_states (bool, optional, defaults to False) — Whether or not the model should return all hidden-states.
  • return_dict (bool, optional, defaults to True) — Whether to return a ModelOutput (dataclass) instead of a plain tuple.
  • dtype (Union[str, torch.dtype], optional) — The chunk size of all feed forward layers in the residual attention blocks. A chunk size of 0 means that the feed forward layer is not chunked. A chunk size of n means that the feed forward layer processes n < sequence_length embeddings at a time. For more information on feed forward chunking, see How does Feed Forward Chunking work?.
  • chunk_size_feed_forward (int, optional, defaults to 0) — The dtype of the weights. This attribute can be used to initialize the model to a non-default dtype (which is normally float32) and thus allow for optimal storage allocation. For example, if the saved model is float16, ideally we want to load it back using the minimal amount of memory needed to load float16 weights.
  • is_encoder_decoder (bool, optional, defaults to False) — Whether the model is used as an encoder/decoder or not.
  • id2label (Union[dict[int, str], dict[str, str]], optional) — A map from index (for instance prediction index, or target index) to label.
  • label2id (Union[dict[str, int], dict[str, str]], optional) — A map from label to index for the model.
  • problem_type (Literal[regression, single_label_classification, multi_label_classification], optional) — Problem type for XxxForSequenceClassification models. Can be one of "regression", "single_label_classification" or "multi_label_classification".
  • tokenizer_class (str, optional) — The class name of model’s tokenizer.
  • text_config (Union[dict, ~configuration_utils.PreTrainedConfig], optional) — The config object or dictionary of the text backbone.
  • audio_config (Union[dict, ~configuration_utils.PreTrainedConfig], optional) — The config object or dictionary of the audio backbone.

This is the configuration class to store the configuration of a PeAudioModel. It is used to instantiate a Pe Audio model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the facebook/pe-av-large

Configuration objects inherit from PreTrainedConfig and can be used to control the model outputs. Read the documentation from PreTrainedConfig for more information.

Example:

>>> from transformers import PeAudioModel, PeAudioConfig

>>> # Initializing a PeAudioModel style configuration
>>> configuration = PeAudioConfig()

>>> # Initializing a model from the pe-av-large style configuration
>>> model = PeAudioModel(configuration)

>>> # Accessing the model configuration
>>> configuration = model.config

PeAudioEncoderConfig

class transformers.PeAudioEncoderConfig

< >

( output_hidden_states: bool | None = False return_dict: bool | None = True dtype: typing.Union[str, ForwardRef('torch.dtype'), NoneType] = None chunk_size_feed_forward: int = 0 is_encoder_decoder: bool = False id2label: dict[int, str] | dict[str, str] | None = None label2id: dict[str, int] | dict[str, str] | None = None problem_type: typing.Optional[typing.Literal['regression', 'single_label_classification', 'multi_label_classification']] = None tokenizer_class: str | None = None dac_config: dict | transformers.configuration_utils.PreTrainedConfig | None = None hidden_size: int = 1792 intermediate_size: int = 4800 num_hidden_layers: int = 6 num_attention_heads: int = 14 num_key_value_heads: int | None = None head_dim: int = 128 hidden_act: str = 'silu' max_position_embeddings: int = 10000 initializer_range: float = 0.02 rms_norm_eps: float = 1e-05 rope_parameters: transformers.modeling_rope_utils.RopeParameters | dict | None = None attention_bias: bool = False attention_dropout: float | int = 0.0 )

Parameters

  • output_hidden_states (bool, optional, defaults to False) — Whether or not the model should return all hidden-states.
  • return_dict (bool, optional, defaults to True) — Whether to return a ModelOutput (dataclass) instead of a plain tuple.
  • dtype (Union[str, torch.dtype], optional) — The chunk size of all feed forward layers in the residual attention blocks. A chunk size of 0 means that the feed forward layer is not chunked. A chunk size of n means that the feed forward layer processes n < sequence_length embeddings at a time. For more information on feed forward chunking, see How does Feed Forward Chunking work?.
  • chunk_size_feed_forward (int, optional, defaults to 0) — The dtype of the weights. This attribute can be used to initialize the model to a non-default dtype (which is normally float32) and thus allow for optimal storage allocation. For example, if the saved model is float16, ideally we want to load it back using the minimal amount of memory needed to load float16 weights.
  • is_encoder_decoder (bool, optional, defaults to False) — Whether the model is used as an encoder/decoder or not.
  • id2label (Union[dict[int, str], dict[str, str]], optional) — A map from index (for instance prediction index, or target index) to label.
  • label2id (Union[dict[str, int], dict[str, str]], optional) — A map from label to index for the model.
  • problem_type (Literal[regression, single_label_classification, multi_label_classification], optional) — Problem type for XxxForSequenceClassification models. Can be one of "regression", "single_label_classification" or "multi_label_classification".
  • tokenizer_class (str, optional) — The class name of model’s tokenizer.
  • dac_config (Union[PreTrainedConfig, dict], optional) — Configuration for the DAC audio encoder used to tokenize the raw audio inputs. If a dictionary is passed, it will be used to instantiate a DacConfig with default DAC hyperparameters.
  • ```python —

    from transformers import PeAudioEncoder, PeAudioEncoderConfig

This is the configuration class to store the configuration of a PeAudioModel. It is used to instantiate a Pe Audio model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the facebook/pe-av-large

Configuration objects inherit from PreTrainedConfig and can be used to control the model outputs. Read the documentation from PreTrainedConfig for more information.

PeAudioEncoder

class transformers.PeAudioEncoder

< >

( config: PeAudioEncoderConfig )

Parameters

  • config (PeAudioEncoderConfig) — Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the from_pretrained() method to load the model weights.

The PeAudio Encoder model.

This model inherits from PreTrainedModel. Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.)

This model is also a PyTorch torch.nn.Module subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.

forward

< >

( input_values: Tensor padding_mask: torch.Tensor | None = None **kwargs )

PeAudioFrameLevelModel

class transformers.PeAudioFrameLevelModel

< >

( config: PeAudioConfig )

forward

< >

( input_ids: Tensor input_values: Tensor attention_mask: torch.Tensor | None = None padding_mask: torch.Tensor | None = None return_loss: bool | None = None **kwargs )

PeAudioModel

class transformers.PeAudioModel

< >

( config: PeAudioConfig )

forward

< >

( input_ids: Tensor input_values: Tensor attention_mask: torch.Tensor | None = None padding_mask: torch.Tensor | None = None return_loss: bool | None = None **kwargs )

Update on GitHub

←Parakeet Pop2Piano→