sgc:dZddlZddlmZddlmZddlmZeje Z GddeZ Gd d eZ Gd d eZ Gd deZy)z#BARK model generation configurationN)Dict)GenerationConfig)loggingcDeZdZdZ dfd ZxZS)BarkSemanticGenerationConfigsemanticc t|d|| |||||||d || |_| |_||_| |_| |_||_||_||_ y)a Class that holds a generation configuration for [`BarkSemanticModel`]. This configuration inherit from [`GenerationConfig`] and can be used to control the model generation. Read the documentation from [`GenerationConfig`] for more information. Args: eos_token_id (`int`, *optional*, defaults to 10_000): The id of the *end-of-sequence* token. renormalize_logits (`bool`, *optional*, defaults to `True`): Whether to renormalize the logits after applying all the logits processors (including the custom ones). It's highly recommended to set this flag to `True` as the search algorithms suppose the score logits are normalized but some logit processors break the normalization. max_new_tokens (`int`, *optional*, defaults to 768): The maximum numbers of tokens to generate, ignoring the number of tokens in the prompt. output_scores (`bool`, *optional*, defaults to `False`): Whether or not to return the prediction scores. See `scores` under returned tensors for more details. return_dict_in_generate (`bool`, *optional*, defaults to `False`): Whether or not to return a [`~utils.ModelOutput`] instead of a plain tuple. output_hidden_states (`bool`, *optional*, defaults to `False`): Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for more details. output_attentions (`bool`, *optional*, defaults to `False`): Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned tensors for more details. temperature (`float`, *optional*, defaults to 1.0): The value used to modulate the next token probabilities. do_sample (`bool`, *optional*, defaults to `False`): Whether or not to use sampling ; use greedy decoding otherwise. text_encoding_offset (`int`, *optional*, defaults to 10_048): Text encoding offset. text_pad_token (`int`, *optional*, defaults to 129_595): Text pad token. semantic_infer_token (`int`, *optional*, defaults to 129_599): Semantic infer token. semantic_vocab_size (`int`, *optional*, defaults to 10_000): Semantic vocab size. max_input_semantic_length (`int`, *optional*, defaults to 256): Max length of semantic input vector. semantic_rate_hz (`float`, *optional*, defaults to 49.9): Semantic rate in Hertz. min_eos_p (`float`, *optional*): Minimum threshold of the probability of the EOS token for it to be sampled. This is an early stopping strategy to mitigate potential unwanted generations at the end of a prompt. The original implementation suggests a default value of 0.2. ) temperature do_sample eos_token_idrenormalize_logitsmax_new_tokens output_scoresreturn_dict_in_generateoutput_hidden_statesoutput_attentionsN) super__init__text_encoding_offsettext_pad_tokensemantic_pad_tokensemantic_infer_tokensemantic_vocab_sizemax_input_semantic_lengthsemantic_rate_hz min_eos_p)selfr rrrrrrr r rrrrrrrkwargs __class__s i/var/www/html/venv/lib/python3.12/site-packages/transformers/models/bark/generation_configuration_bark.pyrz%BarkSemanticGenerationConfig.__init__s~B  #%1)'$;!5/  %9!,".$8!#6 )B& 0")'TiFFFF?Fi@'i;i?r$g33333H@N)__name__ __module__ __qualname__ model_typer __classcell__r!s@r"rrsFJ %"#$""%#U#U#r#rcJeZdZdZ ddedeffd ZxZS)BarkCoarseGenerationConfigcoarse_acousticsmax_coarse_historysliding_window_lenc t|d|||||||d|||_| |_| |_| |_| |_| |_||_y)as Class that holds a generation configuration for [`BarkCoarseModel`]. This configuration inherit from [`GenerationConfig`] and can be used to control the model generation. Read the documentation from [`GenerationConfig`] for more information. Args: renormalize_logits (`bool`, *optional*, defaults to `True`): Whether to renormalize the logits after applying all the logits processors (including the custom ones). It's highly recommended to set this flag to `True` as the search algorithms suppose the score logits are normalized but some logit processors break the normalization. output_scores (`bool`, *optional*, defaults to `False`): Whether or not to return the prediction scores. See `scores` under returned tensors for more details. return_dict_in_generate (`bool`, *optional*, defaults to `False`): Whether or not to return a [`~utils.ModelOutput`] instead of a plain tuple. output_hidden_states (`bool`, *optional*, defaults to `False`): Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for more details. output_attentions (`bool`, *optional*, defaults to `False`): Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned tensors for more details. temperature (`float`, *optional*, defaults to 1.0): The value used to modulate the next token probabilities. do_sample (`bool`, *optional*, defaults to `False`): Whether or not to use sampling ; use greedy decoding otherwise. coarse_semantic_pad_token (`int`, *optional*, defaults to 12_048): Coarse semantic pad token. coarse_rate_hz (`int`, *optional*, defaults to 75): Coarse rate in Hertz. n_coarse_codebooks (`int`, *optional*, defaults to 2): Number of coarse codebooks. coarse_infer_token (`int`, *optional*, defaults to 12_050): Coarse infer token. max_coarse_input_length (`int`, *optional*, defaults to 256): Max length of input coarse vector. max_coarse_history (`int`, *optional*, defaults to 630): Max length of the output of the coarse acoustics model used in the fine generation step. sliding_window_len (`int`, *optional*, defaults to 60): The coarse generation step uses a sliding window to generate raw audio. )r r rrrrrNr) rrcoarse_semantic_pad_tokencoarse_rate_hzn_coarse_codebookscoarse_infer_tokenmax_coarse_input_lengthr0r1)rrrrrrr r r3r4r5r6r7r0r1r r!s r"rz#BarkCoarseGenerationConfig.__init__ysrr  #1'$;!5/  *C&,"4"4'>$"4"4r#)TFFFFr%Fi/Ki/r&iv<)r'r(r)r*intrr+r,s@r"r.r.vsV#J  %""(! #"%"$J5 J5 J5J5r#r.c2eZdZdZ dfd ZdZxZS)BarkFineGenerationConfigfine_acousticsc Pt||||_||_||_y)aClass that holds a generation configuration for [`BarkFineModel`]. [`BarkFineModel`] is an autoencoder model, so should not usually be used for generation. However, under the hood, it uses `temperature` when used by [`BarkModel`] This configuration inherit from [`GenerationConfig`] and can be used to control the model generation. Read the documentation from [`GenerationConfig`] for more information. Args: temperature (`float`, *optional*): The value used to modulate the next token probabilities. max_fine_history_length (`int`, *optional*, defaults to 512): Max length of the fine history vector. max_fine_input_length (`int`, *optional*, defaults to 1024): Max length of fine input vector. n_fine_codebooks (`int`, *optional*, defaults to 8): Number of codebooks used. )r N)rrmax_fine_history_lengthmax_fine_input_lengthn_fine_codebooks)rr r@rArBr r!s r"rz!BarkFineGenerationConfig.__init__s-4 [1'>$%:" 0r#c y)z Overrides GenerationConfig.validate because BarkFineGenerationConfig don't use any parameters outside temperature. Nr)rr s r"validatez!BarkFineGenerationConfig.validates r#)r%i)r'r(r)r*rrDr+r,s@r"r=r=s!!J #" 1@ r#r=cXeZdZdZdZ d dededefdZedede de fdZ d Z y) BarkGenerationConfigbarkTNsemantic_configcoarse_acoustics_configfine_acoustics_configc |i}tjd|i}tjd|i}tjdtdi||_t di||_t di||_||_||_ y)a$Class that holds a generation configuration for [`BarkModel`]. The [`BarkModel`] does not have a `generate` method, but uses this class to generate speeches with a nested [`BarkGenerationConfig`] which uses [`BarkSemanticGenerationConfig`], [`BarkCoarseGenerationConfig`], [`BarkFineGenerationConfig`]. This configuration inherit from [`GenerationConfig`] and can be used to control the model generation. Read the documentation from [`GenerationConfig`] for more information. Args: semantic_config (`Dict`, *optional*): Semantic generation configuration. coarse_acoustics_config (`Dict`, *optional*): Coarse generation configuration. fine_acoustics_config (`Dict`, *optional*): Fine generation configuration. sample_rate (`int`, *optional*, defaults to 24_000): Sample rate. codebook_size (`int`, *optional*, defaults to 1024): Vector length for each codebook. 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.r) loggerinforrJr.rKr=rL sample_rate codebook_size)rrJrKrLrPrQr s r"rzBarkGenerationConfig.__init__s<  " O KKg h " *&( # KKm n ($& ! KKi j;NoN'A'\D['\$%=%V@U%V"&*r#c n|d|j|j|jd|S)z Instantiate a [`BarkGenerationConfig`] (or a derived class) from bark sub-models generation configuration. Returns: [`BarkGenerationConfig`]: An instance of a configuration object )rJrKrLr)to_dict)clsrJrKrLr s r"from_sub_model_configsz+BarkGenerationConfig.from_sub_model_configs(sD +335$;$C$C$E"7"?"?"A    r#c$tj|j}|jj |d<|j j |d<|j j |d<|jj|d<|S)z Serializes this instance to a Python dictionary. Override the default [`~PretrainedConfig.to_dict`]. Returns: `Dict[str, any]`: Dictionary of all the attributes that make up this configuration instance, rJrKrLr*) copydeepcopy__dict__rJrSrKrLr!r*)routputs r"rSzBarkGenerationConfig.to_dict=s}t}}-$($8$8$@$@$B !,0,H,H,P,P,R()*.*D*D*L*L*N&'#~~88| r#)NNNi]rE) r'r(r)r*is_compositionrr classmethodrr.r=rUrSrr#r"rHrHstJN !%(,&* /+/+"&/+ $ /+b 5 "<  8   (r#rH)__doc__rWtypingrgeneration.configuration_utilsrutilsr get_loggerr'rNrr.r=rHrr#r"rbsg* >   H %X##3X#vM5!1M5`( /( VZ+Zr#