+ jH-Rt^RIHt^RIHt^RIHtHt^RIH t H t ]P!] 4t ]!RR7]!RR]444t]!RR7]!R R ]444t]!RR7]!R R ]444t]!RR7]!R R]444t]!RR7]!RR]444t.ROtR#)zBARK model configuration)strict)PreTrainedConfig)auto_docstringlogging)CONFIG_MAPPING AutoConfigz suno/bark) checkpointcra]tRt^toRtR.tRRRRRRR R /tR tR tR t ^ t ^ t R t Rt RtRtRtV3RltRtVtR#)BarkSubModelConfiga 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. bias (`bool`, *optional*, defaults to `True`): Whether or not to use bias in the linear layers and layer norm layers. past_key_valuesnum_attention_heads num_headsnum_hidden_layers num_layers vocab_sizeinput_vocab_size window_size block_sizeii@'igT{Gz?c<V^8dQh/S[;R&S[;R&S[;R&S[;R&S[;R&S[;R&S[S[,;R&S[;R&S[;R &S[;R &#) rroutput_vocab_sizerr hidden_sizedropoutbiasinitializer_range use_cache)intfloatbool)format __classdict__s"l/home/luca/screen-checking/.venv/lib/python3.14/site-packages/transformers/models/bark/configuration_bark.py __annotate__BarkSubModelConfig.__annotate__s89:";<#=>?@ABCDS[EF GH#IJKN)__name__ __module__ __qualname____firstlineno____doc__keys_to_ignore_at_inference attribute_maprrrrr rrrrr__annotate_func____static_attributes____classdictcell__r!s@r"r r sr $5"5 {\(| MJ"#JIKGD#IKr%r c"]tRt^BtRtRtRtRtR#)BarkSemanticConfigaS 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. bias (`bool`, *optional*, defaults to `True`): Whether or not to use bias in the linear layers and layer norm layers 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 ```semanticsemantic_configr&Nr'r(r)r*r+ model_typebase_config_keyr/r&r%r"r3r3Bs <J'Or%r3c"]tRt^gtRtRtRtRtR#)BarkCoarseConfigaK 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. bias (`bool`, *optional*, defaults to `True`): Whether or not to use bias in the linear layers and layer norm layers 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 ```coarse_acousticscoarse_acoustics_configr&Nr6r&r%r"r:r:gs <$J/Or%r:cDa]tRt^toRtRtRtRt^t^t V3Rlt Rt Vt R#)BarkFineConfigau block_size (`int`, *optional*, defaults to 1024): The maximum sequence length that this model might ever be used with. Typically set this to something large just in case (e.g., 512 or 1024 or 2048). input_vocab_size (`int`, *optional*, defaults to 10_048): Vocabulary size of a Bark sub-model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`{model}`]. Defaults to 10_048 but should be carefully thought with regards to the chosen sub-model. output_vocab_size (`int`, *optional*, defaults to 10_048): Output vocabulary size of a Bark sub-model. Defines the number of different tokens that can be represented by the: `output_ids` when passing forward a [`{model}`]. Defaults to 10_048 but should be carefully thought with regards to the chosen sub-model. bias (`bool`, *optional*, defaults to `True`): Whether or not to use bias in the linear layers and layer norm layers n_codes_total (`int`, *optional*, defaults to 8): The total number of audio codebooks predicted. Used in the fine acoustics sub-model. n_codes_given (`int`, *optional*, defaults to 1): The number of audio codebooks predicted in the coarse acoustics sub-model. Used in the acoustics sub-models. Example: ```python >>> from transformers import BarkFineConfig, BarkFineModel >>> # Initializing a Bark sub-module style configuration >>> configuration = BarkFineConfig() >>> # Initializing a model (with random weights) from the suno/bark style configuration >>> model = BarkFineModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```fine_acousticsfine_acoustics_configTc><V^8dQh/S[;R&S[;R&S[;R&#)rtie_word_embeddings n_codes_total n_codes_given)rr)r r!s"r"r#BarkFineConfig.__annotate__s2R$STUVWr%r&N) r'r(r)r*r+r7r8rBrCrDr.r/r0r1s@r"r>r>s/! F"J-O $MMWr%r>cnaa]tRt^toRtRtR]R]R]R] /t Rt Rt Rt RtRtV3R ltV3R ltR tVtV;t#) BarkConfiga 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( ... 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<r@ codec_configNrc <VPf&\4Vn\PR4M:\ VP\ 4'd\R/VPBVnVP f&\4Vn\PR4M:\ VP \ 4'd\R/VP BVnVPf&\4Vn\PR4M:\ VP\ 4'd\R/VPBVnVPf.\R,!4Vn \PR4M^\ VP\ 4'd?VPPRR4p\V,!R/VPBVn \SV`8!R/VBR#)NzW`semantic_config` is `None`. Initializing the `BarkSemanticConfig` with default values.z]`coarse_acoustics_config` is `None`. Initializing the `BarkCoarseConfig` with default values.zY`fine_acoustics_config` is `None`. Initializing the `BarkFineConfig` with default values.encodeczN`codec_config` is `None`. Initializing the `codec_config` with default values.r7r&)r5r3loggerinfo isinstancedictr<r:r@r>rIrgetsuper __post_init__)selfkwargscodec_model_type __class__s&, r"rRBarkConfig.__post_init__so    '#5#7D KKq r ,,d 3 3#5#M8L8L#MD  ' ' /+;+=D ( KKo 44d ; ;+;+[d>Z>Z+[D (  % % -)7)9D & KKs t 22D 9 9)7)U$:T:T)UD &    $ .y 9 ;D  KKh i ))4 0 0#0044\9M  ./? @ U4CTCT UD  ''r%c<V^8dQh/S[S[,R,;R&S[S[,R,;R&S[S[,R,;R&S[S[,R,;R&S[;R&#)rNr5r<r@rIr)rOrr)r r!s"r"r#BarkConfig.__annotate__s|h,,t3:ij"$44t;Bkl "22T9@mn))D07op#qr%)r<rIr@r5)r'r(r)r*r+r7r3r:r>r sub_configsr5r<r@rIrrRr.r/r0 __classcell__)rVr!s@@r"rGrGsZ(TJ-!#3 K 7;O>B<@37L#(ur%rGN)r:rGr>r3)r+huggingface_hub.dataclassesrconfiguration_utilsrutilsrrautorr get_loggerr'rLr r3r:r>rG__all__r&r%r"rbs.3,-   H %;'#)#(#L;' (+ (( (F;' 0) 0( 0F;')')()X;'T(!T((T(n Ur%