o h2@sdZddlZddlmZmZmZddlmZddlm Z m Z ddl m Z e eZd d d Zd ZGd ddeZe ejddddGdddeZe ejddddGdddeZe ejddddGdddeZGdddeZdS)z BARK model configurationN)DictOptionalUnion)PretrainedConfig)add_start_docstringslogging)CONFIG_MAPPINGz?https://huggingface.co/suno/bark-small/resolve/main/config.jsonz9https://huggingface.co/suno/bark/resolve/main/config.json)zsuno/bark-smallz suno/barka 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). cseZdZdZdgZdddddZ   dfdd Ze     ddee e j fde ee e j fde de de ee e fde ddfddZZS) BarkSubModelConfig bark_modulepast_key_values num_heads num_layersinput_vocab_size block_size)num_attention_headsnum_hidden_layers vocab_size window_size@' T{Gz?c  sR||_||_||_||_||_||_||_||_| |_| |_ t j di| dS)N) rroutput_vocab_sizerr hidden_sizedropoutbias use_cacheinitializer_rangesuper__init__) selfrrrrrrrr r"r!kwargs __class__ra/var/www/html/ai/venv/lib/python3.10/site-packages/transformers/models/bark/configuration_bark.pyr$RszBarkSubModelConfig.__init__NFmainpretrained_model_name_or_path cache_dirforce_downloadlocal_files_onlytokenrevisionreturnrc Ks||d<||d<||d<||d<||||j|fi|\}}|ddkr0||jd}d|vrOt|drO|d|jkrOtd|dd |jd |j|fi|S) Nr,r-r.r0 model_typebark_configzYou are using a model of type z to instantiate a model of type zN. This is not supported for all configurations of models and can yield errors.)_set_token_in_kwargsget_config_dictgetr2hasattrloggerwarning from_dict) clsr+r,r-r.r/r0r& config_dictrrr)from_pretrainedms    z"BarkSubModelConfig.from_pretrained) rrrrrrrTrT)NFFNr*)__name__ __module__ __qualname__r2keys_to_ignore_at_inference attribute_mapr$ classmethodrstrosPathLikerboolr> __classcell__rrr'r)r GsP   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 ```c@eZdZdZdS)rJsemanticNr?r@rAr2rrrr)rJBarkCoarseConfigBarkCoarseModela 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@rN)rRcoarse_acousticsNrPrrrr)rRrQBarkFineConfig 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"eZdZdZdfdd ZZS)rUfine_acousticsTc s&||_||_tjdd|i|dS)Ntie_word_embeddingsr) n_codes_total n_codes_givenr#r$)r%rZr[r\r&r'rr)r$szBarkFineConfig.__init__)TrXrY)r?r@rAr2r$rIrrr'r)rUsc s`eZdZdZdZ     d dedededeffd d Zedede de de fd d Z Z 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 ``` r3Nrsemantic_configcoarse_acoustics_configfine_acoustics_config codec_configc 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.r2encodecr) r9inforJr^rRr_rUr`r rar"r#r$)r%r^r_r`rar"r&codec_model_typer'rr)r$s&     zBarkConfig.__init__cKs(|d||||d|S)z Instantiate a [`BarkConfig`] (or a derived class) from bark sub-models configuration. Returns: [`BarkConfig`]: An instance of a configuration object )r^r_r`raNr)to_dict)r<r^r_r`rar&rrr)from_sub_model_configs5sz!BarkConfig.from_sub_model_configs)NNNNr)r?r@rA__doc__r2rr$rDrJrRrUrrfrIrrr'r)r]s64#r])rgrFtypingrrrconfiguration_utilsrutilsrrautor get_loggerr?r9"BARK_PRETRAINED_CONFIG_ARCHIVE_MAP#BARK_SUBMODELCONFIG_START_DOCSTRINGr formatrJrRrUr]rrrr)s8   &G