Ig#2dZddlZddlmZmZmZddlmZddlm Z m Z ddl m Z e jeZd ZGd d eZe ej%d d dGdd eZe ej%dddGddeZe ej%dddGddeZGddeZy)zBARK model configurationN)DictOptionalUnion)PretrainedConfig)add_start_docstringslogging)CONFIG_MAPPINGa 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). ceZdZdZdgZdddddZ dfd Ze dd ee e jfd e ee e jfd e d e d e ee e fde ddfdZxZS)BarkSubModelConfig bark_modulepast_key_values num_heads num_layersinput_vocab_size block_size)num_attention_headsnum_hidden_layers vocab_size window_sizec  ||_||_||_||_||_||_||_||_| |_| |_ t |,di| y)N) rroutput_vocab_sizerr hidden_sizedropoutbias use_cacheinitializer_rangesuper__init__) selfrrrrrrrrrrkwargs __class__s h/var/www/html/answerous/venv/lib/python3.12/site-packages/transformers/models/bark/configuration_bark.pyr!zBarkSubModelConfig.__init__Ms_% 0!2$"&  "!2 "6"pretrained_model_name_or_path cache_dirforce_downloadlocal_files_onlytokenrevisionreturnrc ||d<||d<||d<||d<|j|||j|fi|\}}|jddk(r||jd}d|vrGt |dr;|d|jk7r)t j d|dd |jd |j|fi|S) Nr(r)r*r, model_typebark_configzYou are using a model of type z to instantiate a model of type zN. This is not supported for all configurations of models and can yield errors.)_set_token_in_kwargsget_config_dictgetr/hasattrloggerwarning from_dict) clsr'r(r)r*r+r,r# config_dicts r%from_pretrainedz"BarkSubModelConfig.from_pretrainedhs({#1 %5!"%z   /1c112OZSYZ V ??< (F 2%(8&@AK ; &73 +E+VbJcgjguguJu NN0\1J0KKk>>""pr  s}}[3F33r&) i@'r< r=igT{Gz?T)NFFNmain)__name__ __module__ __qualname__r/keys_to_ignore_at_inference attribute_mapr! classmethodrstrosPathLikerboolr; __classcell__r$s@r%r r BsJ#4"5 +)(# M  #68<$!&,04',S"++-='>4E#r{{"2344 4  4 c4i() 44 44r&r BarkSemanticConfigBarkSemanticModel)configmodela Example: ```python >>> from transformers import BarkSemanticConfig, BarkSemanticModel >>> # Initializing a Bark sub-module style configuration >>> configuration = BarkSemanticConfig() >>> # Initializing a model (with random weights) from the suno/bark style configuration >>> model = BarkSemanticModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```ceZdZdZy)rLsemanticNr@rArBr/rr&r%rLrLs &Jr&BarkCoarseConfigBarkCoarseModela Example: ```python >>> from transformers import BarkCoarseConfig, BarkCoarseModel >>> # Initializing a Bark sub-module style configuration >>> configuration = BarkCoarseConfig() >>> # Initializing a model (with random weights) from the suno/bark style configuration >>> model = BarkCoarseModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```ceZdZdZy)rScoarse_acousticsNrRrr&r%rSrSs &$Jr&BarkFineConfig 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 ```c$eZdZdZdfd ZxZS)rWfine_acousticsc D||_||_t| dd|i|y)Ntie_word_embeddingsr) n_codes_total n_codes_givenr r!)r"r\r]r^r#r$s r%r!zBarkFineConfig.__init__s)** K-@KFKr&)T)r@rArBr/r!rJrKs@r%rWrWs0"JLLr&c feZdZdZdZ d dedededeffd Zedede de de fdZ xZ S) 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 ``` r0semantic_configcoarse_acoustics_configfine_acoustics_config codec_configc |i}tjd|i}tjd|i}tjd|i}tjdtdi||_t di||_t di||_d|vr|dnd}t|di||_ ||_ t|0di|y)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/encodecr) r6inforLrcrSrdrWrer rfrr r!) r"rcrdrerfrr#codec_model_typer$s r%r!zBarkConfig.__init__ s  " O KKg h " *&( # KKm n ($& ! KKi j  L KKa b1DOD'7'R:Q'R$%3%L6K%L"9E9U< 5[d*+;<L|L!2 "6"r&c |d|j|j|j|jd|S)z Instantiate a [`BarkConfig`] (or a derived class) from bark sub-models configuration. Returns: [`BarkConfig`]: An instance of a configuration object )rcrdrerfr)to_dict)r9rcrdrerfr#s r%from_sub_model_configsz!BarkConfig.from_sub_model_configs0sP +335$;$C$C$E"7"?"?"A%--/     r&)NNNNr>)r@rArB__doc__r/rr!rErLrSrWrrmrJrKs@r%rbrbs2hJ!%(,&*! !#!#"&!# $ !#  !#F + "2  .  '   r&rb)rnrGtypingrrrconfiguration_utilsrutilsrr autor get_loggerr@r6#BARK_SUBMODELCONFIG_START_DOCSTRINGr formatrLrSrWrbrr&r%rvs  ((32!   H %#'#LD4)D4N'..6JRe.f $+%$'..6HPa.b $$)$%$$'..6Fo.^ .L'L/.Lo !o r&