o Zh.@sdZddlmZmZddlmZddlmZmZddl m Z m Z e e ZdZGd d d eZeejd d d dGdd d eZeejddd dGdddeZeejddd dGdddeZGdddeZgdZdS)zBARK model configuration)DictOptional)PretrainedConfig)add_start_docstringslogging)CONFIG_MAPPING AutoConfiga This is the configuration class to store the configuration of a [`{model}`]. It is used to instantiate the 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 Bark [suno/bark](https://huggingface.co/suno/bark) architecture. Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PretrainedConfig`] for more information. Args: block_size (`int`, *optional*, defaults to 1024): 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). input_vocab_size (`int`, *optional*, defaults to 10_048): Vocabulary size of a Bark sub-model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`{model}`]. Defaults to 10_048 but should be carefully thought with regards to the chosen sub-model. output_vocab_size (`int`, *optional*, defaults to 10_048): Output vocabulary size of a Bark sub-model. Defines the number of different tokens that can be represented by the: `output_ids` when passing forward a [`{model}`]. Defaults to 10_048 but should be carefully thought with regards to the chosen sub-model. num_layers (`int`, *optional*, defaults to 12): Number of hidden layers in the given sub-model. num_heads (`int`, *optional*, defaults to 12): Number of attention heads for each attention layer in the Transformer architecture. hidden_size (`int`, *optional*, defaults to 768): Dimensionality of the "intermediate" (often named feed-forward) layer in the architecture. dropout (`float`, *optional*, defaults to 0.0): The dropout probability for all fully connected layers in the embeddings, encoder, and pooler. bias (`bool`, *optional*, defaults to `True`): Whether or not to use bias in the linear layers and layer norm layers. initializer_range (`float`, *optional*, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. use_cache (`bool`, *optional*, defaults to `True`): Whether or not the model should return the last key/values attentions (not used by all models). csFeZdZdgZdddddZ    dfdd ZZS)BarkSubModelConfigZpast_key_values num_heads num_layersinput_vocab_size block_size)Znum_attention_headsZnum_hidden_layersZ vocab_sizeZ window_size@' T{Gz?c  sR||_||_||_||_||_||_||_||_| |_| |_ t j di| dS)N) rroutput_vocab_sizer r hidden_sizedropoutbias use_cacheinitializer_rangesuper__init__) selfrrrr r rrrrrkwargs __class__rZ/var/www/auris/lib/python3.10/site-packages/transformers/models/bark/configuration_bark.pyrKszBarkSubModelConfig.__init__) rrrrrrrTrT)__name__ __module__ __qualname__Zkeys_to_ignore_at_inferenceZ attribute_mapr __classcell__rrr!r#r As$ r BarkSemanticConfigZBarkSemanticModel)configmodela Example: ```python >>> from transformers import BarkSemanticConfig, BarkSemanticModel >>> # Initializing a Bark sub-module style configuration >>> configuration = BarkSemanticConfig() >>> # Initializing a model (with random weights) from the suno/bark style configuration >>> model = BarkSemanticModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```c@eZdZdZdZdS)r(Zsemanticsemantic_configNr$r%r& model_typebase_config_keyrrrr#r(gBarkCoarseConfigZBarkCoarseModela Example: ```python >>> from transformers import BarkCoarseConfig, BarkCoarseModel >>> # Initializing a Bark sub-module style configuration >>> configuration = BarkCoarseConfig() >>> # Initializing a model (with random weights) from the suno/bark style configuration >>> model = BarkCoarseModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```c@r+)r1Zcoarse_acousticscoarse_acoustics_configNr-rrrr#r1~r0BarkFineConfigZ BarkFineModela n_codes_total (`int`, *optional*, defaults to 8): The total number of audio codebooks predicted. Used in the fine acoustics sub-model. n_codes_given (`int`, *optional*, defaults to 1): The number of audio codebooks predicted in the coarse acoustics sub-model. Used in the acoustics sub-models. Example: ```python >>> from transformers import BarkFineConfig, BarkFineModel >>> # Initializing a Bark sub-module style configuration >>> configuration = BarkFineConfig() >>> # Initializing a model (with random weights) from the suno/bark style configuration >>> model = BarkFineModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```cs&eZdZdZdZdfdd ZZS) r3Zfine_acousticsfine_acoustics_configTc s&||_||_tjdd|i|dS)Ntie_word_embeddingsr) n_codes_total n_codes_givenrr)rr7r8r9r r!rr#rszBarkFineConfig.__init__)Tr5r6)r$r%r&r.r/rr'rrr!r#r3sc s~eZdZdZdZeeeedZ     dde e de e de e d e e ffd d Z e dededed efd d ZZS) BarkConfiga This is the configuration class to store the configuration of a [`BarkModel`]. It is used to instantiate a Bark model according to the specified sub-models configurations, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the Bark [suno/bark](https://huggingface.co/suno/bark) architecture. Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PretrainedConfig`] for more information. Args: semantic_config ([`BarkSemanticConfig`], *optional*): Configuration of the underlying semantic sub-model. coarse_acoustics_config ([`BarkCoarseConfig`], *optional*): Configuration of the underlying coarse acoustics sub-model. fine_acoustics_config ([`BarkFineConfig`], *optional*): Configuration of the underlying fine acoustics sub-model. codec_config ([`AutoConfig`], *optional*): Configuration of the underlying codec sub-model. Example: ```python >>> from transformers import ( ... BarkSemanticConfig, ... BarkCoarseConfig, ... BarkFineConfig, ... BarkModel, ... BarkConfig, ... AutoConfig, ... ) >>> # Initializing Bark sub-modules configurations. >>> semantic_config = BarkSemanticConfig() >>> coarse_acoustics_config = BarkCoarseConfig() >>> fine_acoustics_config = BarkFineConfig() >>> codec_config = AutoConfig.from_pretrained("facebook/encodec_24khz") >>> # Initializing a Bark module style configuration >>> configuration = BarkConfig.from_sub_model_configs( ... semantic_config, coarse_acoustics_config, fine_acoustics_config, codec_config ... ) >>> # Initializing a model (with random weights) >>> model = BarkModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ``` Zbarkr,r2r4 codec_configNrr,r2r4r<c s|dur i}td|duri}td|dur!i}td|dur,i}tdtdi||_tdi||_tdi||_d|vrL|dnd}t|di||_ ||_ t j di|dS)NzMsemantic_config is None. initializing the semantic model with default values.zScoarse_acoustics_config is None. initializing the coarse model with default values.zOfine_acoustics_config is None. initializing the fine model with default values.zGcodec_config is None. initializing the codec model with default values.r.Zencodecr) loggerinfor(r,r1r2r3r4r r<rrr)rr,r2r4r<rr Zcodec_model_typer!rr#rs&     zBarkConfig.__init__cKs(|d||||d|S)z Instantiate a [`BarkConfig`] (or a derived class) from bark sub-models configuration. Returns: [`BarkConfig`]: An instance of a configuration object r;Nr)to_dict)clsr,r2r4r<r rrr#from_sub_model_configssz!BarkConfig.from_sub_model_configs)NNNNr)r$r%r&__doc__r.r(r1r3r Z sub_configsrrr classmethodrrAr'rrr!r#r:s@4 #r:)r1r:r3r(N)rBtypingrrZconfiguration_utilsrutilsrrautor r Z get_loggerr$r=Z#BARK_SUBMODELCONFIG_START_DOCSTRINGr formatr(r1r3r:__all__rrrr#s2  &&    x