sg .dZddlmZddlmZddlmZmZddlm Z m Z eje Z dZGd d eZeej!d d dGdd eZeej!dd dGddeZeej!dd dGddeZGddeZy)zBARK model configuration)Dict)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). cHeZdZdgZdddddZ dfd ZxZS) BarkSubModelConfigpast_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 ^/var/www/html/venv/lib/python3.12/site-packages/transformers/models/bark/configuration_bark.pyrzBarkSubModelConfig.__init__Ks_% 0!2$"&  "!2 "6") i@'r% r&igT{Gz?T)__name__ __module__ __qualname__keys_to_ignore_at_inference attribute_mapr __classcell__r"s@r#r r AsK#4"5 +)(# M  ##r$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 ```ceZdZdZdZy)r/semanticsemantic_configNr(r)r* model_typebase_config_keyrr$r#r/r/gs&J'Or$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 ```ceZdZdZdZy)r9coarse_acousticscoarse_acoustics_configNr6rr$r#r9r9~s&$J/Or$BarkFineConfig BarkFineModela n_codes_total (`int`, *optional*, defaults to 8): The total number of audio codebooks predicted. Used in the fine acoustics sub-model. n_codes_given (`int`, *optional*, defaults to 1): The number of audio codebooks predicted in the coarse acoustics sub-model. Used in the acoustics sub-models. Example: ```python >>> from transformers import BarkFineConfig, BarkFineModel >>> # Initializing a Bark sub-module style configuration >>> configuration = BarkFineConfig() >>> # Initializing a model (with random weights) from the suno/bark style configuration >>> model = BarkFineModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```c(eZdZdZdZdfd ZxZS)r>fine_acousticsfine_acoustics_configc D||_||_t| dd|i|y)Ntie_word_embeddingsr) n_codes_total n_codes_givenrr)r rDrErFr!r"s r#rzBarkFineConfig.__init__s)** K-@KFKr$)T)r(r)r*r7r8rr-r.s@r#r>r>s0"J-OLLr$c teZdZdZdZeeeedZ d de de de de ffd Z e dededede fd ZxZS) 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 ``` barkr5r=rB codec_configr5r=rBrMc |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.r7encodecr) loggerinfor/r5r9r=r>rBr rMrrr) r r5r=rBrMrr!codec_model_typer"s r#rzBarkConfig.__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 rLr)to_dict)clsr5r=rBrMr!s r#from_sub_model_configsz!BarkConfig.from_sub_model_configssP +335$;$C$C$E"7"?"?"A%--/     r$)NNNNr')r(r)r*__doc__r7r/r9r>r sub_configsrr classmethodrrVr-r.s@r#rJrJs2hJ-#3!/" K!%(,&*! !#!#"&!# $ !#  !#F + "2  .  '   r$rJN)rWtypingrconfiguration_utilsrutilsrrautor r get_loggerr(rP#BARK_SUBMODELCONFIG_START_DOCSTRINGr formatr/r9r>rJrr$r#ras32-   H %#'#L##)##L'..6JRe.f $(+(%$( '..6HPa.b $0)0%$0 '..6Fo.^ .L'L/.Lu !u r$