# PE Audio Video (Perception Encoder Audio-Video) ## Overview TODO ## Usage ### Basic usage ```py TODO ``` ## PeAudioVideoProcessor[[transformers.PeAudioVideoProcessor]] #### transformers.PeAudioVideoProcessor[[transformers.PeAudioVideoProcessor]] [Source](https://github.com/huggingface/transformers/blob/main/src/transformers/models/pe_audio_video/processing_pe_audio_video.py#L17) __call__transformers.PeAudioVideoProcessor.__call__https://github.com/huggingface/transformers/blob/main/src/transformers/processing_utils.py#L641[{"name": "images", "val": ": typing.Union[ForwardRef('PIL.Image.Image'), numpy.ndarray, ForwardRef('torch.Tensor'), list['PIL.Image.Image'], list[numpy.ndarray], list['torch.Tensor'], NoneType] = None"}, {"name": "text", "val": ": str | list[str] | list[list[str]] | None = None"}, {"name": "videos", "val": ": 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"}, {"name": "audio", "val": ": typing.Union[numpy.ndarray, ForwardRef('torch.Tensor'), collections.abc.Sequence[numpy.ndarray], collections.abc.Sequence['torch.Tensor'], NoneType] = None"}, {"name": "**kwargs", "val": ": typing_extensions.Unpack[transformers.processing_utils.ProcessingKwargs]"}]- **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](/docs/transformers/main/en/internal/file_utils#transformers.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.0[BatchFeature](/docs/transformers/main/en/main_classes/feature_extractor#transformers.BatchFeature)A [BatchFeature](/docs/transformers/main/en/main_classes/feature_extractor#transformers.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. **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](/docs/transformers/main/en/internal/file_utils#transformers.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](/docs/transformers/main/en/main_classes/feature_extractor#transformers.BatchFeature)` A [BatchFeature](/docs/transformers/main/en/main_classes/feature_extractor#transformers.BatchFeature) object with processed inputs in a dict format. ## PeAudioVideoConfig[[transformers.PeAudioVideoConfig]] #### transformers.PeAudioVideoConfig[[transformers.PeAudioVideoConfig]] [Source](https://github.com/huggingface/transformers/blob/main/src/transformers/models/pe_audio_video/configuration_pe_audio_video.py#L89) This is the configuration class to store the configuration of a PeAudioVideoModel. It is used to instantiate a Pe Audio Video 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](https://huggingface.co/facebook/pe-av-large) Configuration objects inherit from [PreTrainedConfig](/docs/transformers/main/en/main_classes/configuration#transformers.PreTrainedConfig) and can be used to control the model outputs. Read the documentation from [PreTrainedConfig](/docs/transformers/main/en/main_classes/configuration#transformers.PreTrainedConfig) for more information. ```python >>> from transformers import PeAudioVideoModel, PeAudioVideoConfig >>> # Initializing a PeAudioVideoModel style configuration >>> configuration = PeAudioVideoConfig() >>> # Initializing a model from the pe-av-large style configuration >>> model = PeAudioModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ``` **Parameters:** text_config (`Union[dict, ~configuration_utils.PreTrainedConfig]`, *optional*) : The config object or dictionary of the text backbone. audio_video_config (`dict` or `PreTrainedConfig`, *optional*) : Configuration for the audio-video encoder component. tie_word_embeddings (`bool`, *optional*, defaults to `True`) : Whether to tie weight embeddings according to model's `tied_weights_keys` mapping. ## PeAudioVideoEncoderConfig[[transformers.PeAudioVideoEncoderConfig]] #### transformers.PeAudioVideoEncoderConfig[[transformers.PeAudioVideoEncoderConfig]] [Source](https://github.com/huggingface/transformers/blob/main/src/transformers/models/pe_audio_video/configuration_pe_audio_video.py#L26) This is the configuration class to store the configuration of a PeAudioVideoModel. It is used to instantiate a Pe Audio Video 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](https://huggingface.co/facebook/pe-av-large) Configuration objects inherit from [PreTrainedConfig](/docs/transformers/main/en/main_classes/configuration#transformers.PreTrainedConfig) and can be used to control the model outputs. Read the documentation from [PreTrainedConfig](/docs/transformers/main/en/main_classes/configuration#transformers.PreTrainedConfig) for more information. ```python >>> from transformers import PeAudioVideoEncoder, PeAudioVideoEncoderConfig >>> # Initializing a PeAudioVideoEncoder style configuration >>> configuration = PeAudioVideoEncoderConfig() >>> # Initializing a model from the pe-av-large style configuration >>> model = PeAudioVideoEncoder(configuration) >>> # Accessing the model configuration >>> configuration = model.config ``` **Parameters:** audio_config (`Union[dict, ~configuration_utils.PreTrainedConfig]`, *optional*) : The config object or dictionary of the audio backbone. video_config (`Union[PreTrainedConfig, dict]`, *optional*) : Configuration for the video encoder. If a dictionary is provided, it is used to instantiate [PeVideoEncoderConfig](/docs/transformers/main/en/model_doc/pe_video#transformers.PeVideoEncoderConfig). hidden_size (`int`, *optional*, defaults to `1792`) : Dimension of the hidden representations. intermediate_size (`int`, *optional*, defaults to `4800`) : Dimension of the MLP representations. num_hidden_layers (`int`, *optional*, defaults to `6`) : Number of hidden layers in the Transformer decoder. num_attention_heads (`int`, *optional*, defaults to `14`) : Number of attention heads for each attention layer in the Transformer decoder. num_key_value_heads (`int`, *optional*) : This is the number of key_value heads that should be used to implement Grouped Query Attention. If `num_key_value_heads=num_attention_heads`, the model will use Multi Head Attention (MHA), if `num_key_value_heads=1` the model will use Multi Query Attention (MQA) otherwise GQA is used. When converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed by meanpooling all the original heads within that group. For more details, check out [this paper](https://huggingface.co/papers/2305.13245). If it is not specified, will default to `num_attention_heads`. head_dim (`int`, *optional*, defaults to `128`) : The attention head dimension. If None, it will default to hidden_size // num_attention_heads hidden_act (`str`, *optional*, defaults to `silu`) : The non-linear activation function (function or string) in the decoder. For example, `"gelu"`, `"relu"`, `"silu"`, etc. max_position_embeddings (`int`, *optional*, defaults to `10000`) : The maximum sequence length that this model might ever be used with. initializer_range (`float`, *optional*, defaults to `0.02`) : The standard deviation of the truncated_normal_initializer for initializing all weight matrices. rms_norm_eps (`float`, *optional*, defaults to `1e-05`) : The epsilon used by the rms normalization layers. rope_parameters (`Union[~modeling_rope_utils.RopeParameters, dict]`, *optional*) : Dictionary containing the configuration parameters for the RoPE embeddings. The dictionary should contain a value for `rope_theta` and optionally parameters used for scaling in case you want to use RoPE with longer `max_position_embeddings`. attention_bias (`bool`, *optional*, defaults to `False`) : Whether to use a bias in the query, key, value and output projection layers during self-attention. attention_dropout (`Union[float, int]`, *optional*, defaults to `0.0`) : The dropout ratio for the attention probabilities. ## PeAudioVideoModel[[transformers.PeAudioVideoModel]] #### transformers.PeAudioVideoModel[[transformers.PeAudioVideoModel]] [Source](https://github.com/huggingface/transformers/blob/main/src/transformers/models/pe_audio_video/modeling_pe_audio_video.py#L745) forwardtransformers.PeAudioVideoModel.forwardhttps://github.com/huggingface/transformers/blob/main/src/transformers/models/pe_audio_video/modeling_pe_audio_video.py#L883[{"name": "input_ids", "val": ": torch.Tensor | None = None"}, {"name": "pixel_values_videos", "val": ": torch.Tensor | None = None"}, {"name": "input_values", "val": ": torch.Tensor | None = None"}, {"name": "attention_mask", "val": ": torch.Tensor | None = None"}, {"name": "padding_mask_videos", "val": ": torch.Tensor | None = None"}, {"name": "padding_mask", "val": ": torch.Tensor | None = None"}, {"name": "return_loss", "val": " = False"}, {"name": "**kwargs", "val": ""}] ## PeAudioVideoEncoder[[transformers.PeAudioVideoEncoder]] #### transformers.PeAudioVideoEncoder[[transformers.PeAudioVideoEncoder]] [Source](https://github.com/huggingface/transformers/blob/main/src/transformers/models/pe_audio_video/modeling_pe_audio_video.py#L573) The PeAudioVideo Encoder model. This model inherits from [PreTrainedModel](/docs/transformers/main/en/main_classes/model#transformers.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](https://pytorch.org/docs/stable/nn.html#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. forwardtransformers.PeAudioVideoEncoder.forwardhttps://github.com/huggingface/transformers/blob/main/src/transformers/models/pe_audio_video/modeling_pe_audio_video.py#L592[{"name": "input_values", "val": ": torch.Tensor | None = None"}, {"name": "pixel_values_videos", "val": ": torch.Tensor | None = None"}, {"name": "padding_mask", "val": ": torch.Tensor | None = None"}, {"name": "padding_mask_videos", "val": ": torch.Tensor | None = None"}, {"name": "**kwargs", "val": ""}] **Parameters:** config ([PeAudioVideoEncoderConfig](/docs/transformers/main/en/model_doc/pe_audio_video#transformers.PeAudioVideoEncoderConfig)) : 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()](/docs/transformers/main/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights.