o hP@sxdZddlZddlmZddlmZddlmZee Z ddd Z Gd d d eZ Gd d d eZ GdddeZdS)z CLAP model configurationN)Union)PretrainedConfig)loggingzFhttps://huggingface.co/laion/clap-htsat-fused/resolve/main/config.jsonzHhttps://huggingface.co/laion/clap-htsat-unfused/resolve/main/config.json)zlaion/clap-htsat-fusedzlaion/clap-htsat-unfusedcsleZdZdZdZ             dfdd Zedeee j fddfddZ Z S)ClapTextConfiga This is the configuration class to store the configuration of a [`ClapTextModel`]. It is used to instantiate a CLAP 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 CLAP [calp-hsat-fused](https://huggingface.co/laion/clap-hsat-fused) architecture. Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PretrainedConfig`] for more information. Args: vocab_size (`int`, *optional*, defaults to 30522): Vocabulary size of the CLAP model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`ClapTextModel`]. hidden_size (`int`, *optional*, defaults to 768): Dimensionality of the encoder layers and the pooler layer. num_hidden_layers (`int`, *optional*, defaults to 12): Number of hidden layers in the Transformer encoder. num_attention_heads (`int`, *optional*, defaults to 12): Number of attention heads for each attention layer in the Transformer encoder. intermediate_size (`int`, *optional*, defaults to 3072): Dimensionality of the "intermediate" (often named feed-forward) layer in the Transformer encoder. hidden_act (`str` or `Callable`, *optional*, defaults to `"relu"`): The non-linear activation function (function or string) in the encoder and pooler. If string, `"relu"`, `"relu"`, `"silu"` and `"relu_new"` are supported. hidden_dropout_prob (`float`, *optional*, defaults to 0.1): The dropout probability for all fully connected layers in the embeddings, encoder, and pooler. attention_probs_dropout_prob (`float`, *optional*, defaults to 0.1): The dropout ratio for the attention probabilities. max_position_embeddings (`int`, *optional*, defaults to 512): The maximum sequence length that this model might ever be used with. Typically set this to something large just in case (e.g., 512 or 1024 or 2048). type_vocab_size (`int`, *optional*, defaults to 2): The vocabulary size of the `token_type_ids` passed when calling [`ClapTextModel`]. layer_norm_eps (`float`, *optional*, defaults to 1e-12): The epsilon used by the layer normalization layers. position_embedding_type (`str`, *optional*, defaults to `"absolute"`): Type of position embedding. Choose one of `"absolute"`, `"relative_key"`, `"relative_key_query"`. For positional embeddings use `"absolute"`. For more information on `"relative_key"`, please refer to [Self-Attention with Relative Position Representations (Shaw et al.)](https://arxiv.org/abs/1803.02155). For more information on `"relative_key_query"`, please refer to *Method 4* in [Improve Transformer Models with Better Relative Position Embeddings (Huang et al.)](https://arxiv.org/abs/2009.13658). is_decoder (`bool`, *optional*, defaults to `False`): Whether the model is used as a decoder or not. If `False`, the model is used as an encoder. use_cache (`bool`, *optional*, defaults to `True`): Whether or not the model should return the last key/values attentions (not used by all models). Only relevant if `config.is_decoder=True`. projection_hidden_act (`str`, *optional*, defaults to `"relu"`): The non-linear activation function (function or string) in the projection layer. If string, `"gelu"`, `"relu"`, `"silu"` and `"gelu_new"` are supported. projection_dim (`int`, *optional*, defaults to 512) Dimension of the projection head of the `ClapTextModelWithProjection`. Examples: ```python >>> from transformers import ClapTextConfig, ClapTextModel >>> # Initializing a CLAP text configuration >>> configuration = ClapTextConfig() >>> # Initializing a model (with random weights) from the configuration >>> model = ClapTextModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```clap_text_modelY gelu皙??-q=rabsoluteTreluc s~tjd|||d|||_||_||_||_||_||_||_||_ | |_ | |_ | |_ | |_ ||_||_||_| |_dS)N) pad_token_id bos_token_id eos_token_id)super__init__ vocab_size hidden_sizenum_hidden_layersnum_attention_heads hidden_actintermediate_sizehidden_dropout_probattention_probs_dropout_probmax_position_embeddingstype_vocab_sizeinitializer_factorlayer_norm_epsposition_embedding_type use_cacheprojection_hidden_actprojection_dim)selfrrrrr!r r"r#r$r%r&r'r+rrrr(r)r*kwargs __class__ra/var/www/html/ai/venv/lib/python3.10/site-packages/transformers/models/clap/configuration_clap.pyrgs" zClapTextConfig.__init__pretrained_model_name_or_pathreturnrcK|||j|fi|\}}|ddkr|d}d|vr:t|dr:|d|jkr:td|dd|jd|j|fi|S)N model_typeclap text_configYou are using a model of type to instantiate a model of type N. This is not supported for all configurations of models and can yield errors._set_token_in_kwargsget_config_dictgethasattrr4loggerwarning from_dictclsr1r- config_dictrrr0from_pretrained   zClapTextConfig.from_pretrained)rr r r r r r r rrrrrrrrrTr __name__ __module__ __qualname____doc__r4r classmethodrstrosPathLikerE __classcell__rrr.r0r s2D*&rcseZdZdZdZdddddddgdd d gd gd d dddddddddddddddffdd Zedeee j fddfddZ Z S)ClapAudioConfiga This is the configuration class to store the configuration of a [`ClapAudioModel`]. It is used to instantiate a CLAP audio encoder according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the audio encoder of the CLAP [laion/clap-htsat-fused](https://huggingface.co/laion/clap-htsat-fused) architecture. Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PretrainedConfig`] for more information. Args: window_size (`int`, *optional*, defaults to 8): Image size of the spectrogram num_mel_bins (`int`, *optional*, defaults to 64): Number of mel features used per frames. Should correspond to the value used in the `ClapProcessor` class. spec_size (`int`, *optional*, defaults to 256): Desired input size of the spectrogram that the model supports. It can be different from the output of the `ClapFeatureExtractor`, in which case the input features will be resized. Corresponds to the `image_size` of the audio models. hidden_act (`str`, *optional*, defaults to `"gelu"`): The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`, `"relu"`, `"silu"` and `"gelu_new"` are supported. patch_size (`int`, *optional*, defaults to 4): Patch size for the audio spectrogram patch_stride (`list`, *optional*, defaults to `[4, 4]`): Patch stride for the audio spectrogram num_classes (`int`, *optional*, defaults to 527): Number of classes used for the head training hidden_size (`int`, *optional*, defaults to 768): Hidden size of the output of the audio encoder. Correspond to the dimension of the penultimate layer's output,which is sent to the projection MLP layer. projection_dim (`int`, *optional*, defaults to 512): Hidden size of the projection layer. depths (`list`, *optional*, defaults to `[2, 2, 6, 2]`): Depths used for the Swin Layers of the audio model num_attention_heads (`list`, *optional*, defaults to `[4, 8, 16, 32]`): Number of attention heads used for the Swin Layers of the audio model enable_fusion (`bool`, *optional*, defaults to `False`): Whether or not to enable patch fusion. This is the main contribution of the authors, and should give the best results. hidden_dropout_prob (`float`, *optional*, defaults to 0.1): The dropout probabilitiy for all fully connected layers in the encoder. fusion_type (`[type]`, *optional*): Fusion type used for the patch fusion. patch_embed_input_channels (`int`, *optional*, defaults to 1): Number of channels used for the input spectrogram flatten_patch_embeds (`bool`, *optional*, defaults to `True`): Whether or not to flatten the patch embeddings patch_embeds_hidden_size (`int`, *optional*, defaults to 96): Hidden size of the patch embeddings. It is used as the number of output channels. enable_patch_layer_norm (`bool`, *optional*, defaults to `True`): Whether or not to enable layer normalization for the patch embeddings drop_path_rate (`float`, *optional*, defaults to 0.0): Drop path rate for the patch fusion attention_probs_dropout_prob (`float`, *optional*, defaults to 0.0): The dropout ratio for the attention probabilities. qkv_bias (`bool`, *optional*, defaults to `True`): Whether or not to add a bias to the query, key, value projections. mlp_ratio (`float`, *optional*, defaults to 4.0): Ratio of the mlp hidden dim to embedding dim. aff_block_r (`int`, *optional*, defaults to 4): downsize_ratio used in the AudioFF block num_hidden_layers (`int`, *optional*, defaults to 4): Number of hidden layers in the Transformer encoder. projection_hidden_act (`str`, *optional*, defaults to `"relu"`): The non-linear activation function (function or string) in the projection layer. If string, `"gelu"`, `"relu"`, `"silu"` and `"gelu_new"` are supported. layer_norm_eps (`[type]`, *optional*, defaults to 1e-05): The epsilon used by the layer normalization layers. initializer_factor (`float`, *optional*, defaults to 1.0): A factor for initializing all weight matrices (should be kept to 1, used internally for initialization testing). Example: ```python >>> from transformers import ClapAudioConfig, ClapAudioModel >>> # Initializing a ClapAudioConfig with laion/clap-htsat-fused style configuration >>> configuration = ClapAudioConfig() >>> # Initializing a ClapAudioModel (with random weights) from the laion/clap-htsat-fused style configuration >>> model = ClapAudioModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```clap_audio_model@r ir r)rrr)rVrS Fr NrT`gg@rgh㈵>rc stjdi|||_||_||_||_||_||_||_| |_ ||_ | |_ ||_| |_ ||_ ||_| |_| |_||_||_||_||_||_||_||_||_||_||_||_||_dS)Nr)rr window_size num_mel_bins spec_size patch_size patch_stride num_classesrdepthsrr enable_fusion fusion_typer r"r+flatten_patch_embedspatch_embeds_hidden_sizeenable_patch_layer_normdrop_path_rater#qkv_bias mlp_ratiopatch_embed_input_channels aff_block_rr'r&r*)r,r[r\r]r r^r_r`rr+rarrbr"rcrjrdrerfrgr#rhrirkrr*r'r&r-r.rr0rs: zClapAudioConfig.__init__r1r2rcKr3)Nr4r5 audio_configr7r8r9r:rBrrr0rE;rFzClapAudioConfig.from_pretrainedrGrrr.r0rQsBW=&rQcsHeZdZdZdZ      dfdd Zed ed efd d Z Z S) ClapConfiga( [`ClapConfig`] is the configuration class to store the configuration of a [`ClapModel`]. It is used to instantiate a CLAP model according to the specified arguments, defining the text model and audio model configs. Instantiating a configuration with the defaults will yield a similar configuration to that of the CLAP [laion/clap-htsat-fused](https://huggingface.co/laion/clap-htsat-fused) architecture. Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PretrainedConfig`] for more information. Args: text_config (`dict`, *optional*): Dictionary of configuration options used to initialize [`ClapTextConfig`]. audio_config (`dict`, *optional*): Dictionary of configuration options used to initialize [`ClapAudioConfig`]. logit_scale_init_value (`float`, *optional*, defaults to 14.29): The inital value of the *logit_scale* paramter. Default is used as per the original CLAP implementation. projection_dim (`int`, *optional*, defaults to 512): Dimentionality of text and audio projection layers. projection_hidden_act (`str`, *optional*, defaults to `"relu"`): Activation function for the projection layers. initializer_factor (`float`, *optional*, defaults to 1.0): Factor to scale the initialization of the model weights. kwargs (*optional*): Dictionary of keyword arguments. Example: ```python >>> from transformers import ClapConfig, ClapModel >>> # Initializing a ClapConfig with laion-ai/base style configuration >>> configuration = ClapConfig() >>> # Initializing a ClapModel (with random weights) from the laion-ai/base style configuration >>> model = ClapModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config >>> # We can also initialize a ClapConfig from a ClapTextConfig and a ClapAudioConfig >>> from transformers import ClapTextConfig, ClapAudioConfig >>> # Initializing a ClapText and ClapAudioConfig configuration >>> config_text = ClapTextConfig() >>> config_audio = ClapAudioConfig() >>> config = ClapConfig.from_text_audio_configs(config_text, config_audio) ```r5N$I$I,@rrrc stjdi||duri}td|duri}tdtdi||_tdi||_||j_||j_||j_ ||j_ ||_||_ |jj |_ ||_ ||_ |jj t|jj|_ dS)NzItext_config is None. Initializing the ClapTextConfig with default values.zKaudio_config is None. initializing the ClapAudioConfig with default values.r)rrr?inforr6rQrlr+r*rlogit_scale_init_valuer&rlenra)r,r6rlrpr+r*r&r-r.rr0rs&    zClapConfig.__init__r6rlcKs|d||d|S)z Instantiate a [`ClapConfig`] (or a derived class) from clap text model configuration and clap audio model configuration. Returns: [`ClapConfig`]: An instance of a configuration object )r6rlNr)to_dict)rCr6rlr-rrr0from_text_audio_configss z"ClapConfig.from_text_audio_configs)NNrnrrr) rHrIrJrKr4rrLrrQrsrPrrr.r0rmNs1$rm)rKrNtypingrconfiguration_utilsrutilsr get_loggerrHr?"CLAP_PRETRAINED_MODEL_ARCHIVE_LISTrrQrmrrrr0s    +