qiEMdZddlZddlmZddlmZej eZGddeZ Gdd eZ Gd d eZ gd Z y) zCLVP model configurationN)PreTrainedConfig)loggingceZdZdZdZddgZ d fd Ze d dee jzdefdZ xZ S) ClvpEncoderConfiga This is the configuration class to store the configuration of a [`ClvpEncoder`]. It is used to instantiate a CLVP text or CLVP speech encoder according to the specified arguments. Instantiating a configuration with the defaults will yield a similar configuration to that of the encoder of the CLVP [susnato/clvp_dev](https://huggingface.co/susnato/clvp_dev) architecture. Configuration objects inherit from [`PreTrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PreTrainedConfig`] for more information. Args: vocab_size (`int`, *optional*, defaults to 256): Vocabulary size of the CLVP Encoder model. hidden_size (`int`, *optional*, defaults to 768): Dimensionality of the encoder layers and the pooler layer. intermediate_size (`int`, *optional*, defaults to 1536): Dimensionality of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder. projection_dim (`int`, *optional*, defaults to 768): Dimensionality of the projection vector. num_hidden_layers (`int`, *optional*, defaults to 20): Number of hidden layers in the Transformer encoder. num_attention_heads (`int`, *optional*, defaults to 12): Number of attention heads for each attention layer in the Transformer encoder. hidden_act (`str` or `function`, *optional*, defaults to `"gelu"`): The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`, `"relu"`, `"selu"` and `"gelu_new"` `"quick_gelu"` are supported. layer_norm_eps (`float`, *optional*, defaults to 1e-05): The epsilon used by the layer normalization layers. attention_dropout (`float`, *optional*, defaults to 0.1): The dropout ratio for the attention probabilities. dropout (`float`, *optional*, defaults to 0.1): The dropout ratio for the feed-forward layers in [`ClvpEncoderMLP`]. use_rotary_embedding (`bool`, *optional*, defaults to `True`): Whether to use rotary_embedding or not. use_attention_bias (`bool`, *optional*, defaults to `False`): Whether to use bias in Query, Key and Value layers during self attention. summary_type (`str`, *optional*, defaults to `"mean"`): What strategy to use to get pooler_output from the last_hidden_state. `"last"`, `"first"`, `"mean"` and `"cls_index"` are supported. initializer_factor (`float`, *optional*, defaults to 1.0): A factor for initializing all weight matrices (should be kept to 1.0, used internally for initialization testing). bos_token_id (`int`, *optional*, defaults to 255): Beginning of sequence token id. eos_token_id (`int`, *optional*, defaults to 0): End of sequence token id. pad_token_id (`int`, *optional*): Padding token id. Example: ```python >>> from transformers import ClvpEncoderConfig, ClvpEncoder >>> # Initializing a ClvpEncoderConfig with susnato/clvp_dev style configuration >>> encoder_configuration = ClvpEncoderConfig() >>> # Initializing a ClvpEncoder (with random weights) from the susnato/clvp_dev style configuration >>> model = ClvpEncoder(encoder_configuration) >>> # Accessing the model configuration >>> configuration = model.config ``` clvp_encoder text_config speech_configc ||_||_||_||_||_||_||_||_||_| |_ | |_ | |_ | |_ | |_ ||_||_||_t#|Hdi|yN) vocab_size hidden_sizeintermediate_sizeprojection_dimnum_hidden_layersnum_attention_headslayer_norm_eps hidden_actinitializer_factorattention_dropoutdropoutuse_rotary_embeddinguse_attention_bias summary_type bos_token_id eos_token_id pad_token_idsuper__init__)selfrrrrrrrrrrrrrrrrrkwargs __class__s ]/opt/pipecat/venv/lib/python3.12/site-packages/transformers/models/clvp/configuration_clvp.pyr zClvpEncoderConfig.__init__\s*%&!2,!2#6 ,$"4!2 $8!"4(((( "6"pretrained_model_name_or_path config_typec T|j|fi|\}}||jvrtd||jddk(r||}d|vrGt |dr;|d|j k7r)t jd|dd|j d|j|fi|S)NzSWe can only load either 'text_config' or 'speech_config' but you are trying to load model_typeclvpzYou are using a model of type z to instantiate a model of type zN. This is not supported for all configurations of models and can yield errors.) get_config_dictbase_config_key ValueErrorgethasattrr)loggerwarning from_dict)clsr&r'r" config_dicts r$from_pretrainedz!ClvpEncoderConfig.from_pretraineds2c112OZSYZ V c11 1efqers  ??< (F 2%k2K ; &73 +E+VbJcgjguguJu NN0\1J0KKk>>""pr  s}}[3F33r%)ir7 geluh㈵>皙?r<TFmean?rN)r ) __name__ __module__ __qualname____doc__r)r,r classmethodstrosPathLiker5 __classcell__r#s@r$rrs= ~ J$o6O! %'#RR_4,/"++,=4LO44r%rcheZdZdZdZdZdddddd d d d d d d ddddd dd dddd dddgddffd ZxZS)ClvpDecoderConfiga& This is the configuration class to store the configuration of a [`ClvpDecoder`]. It is used to instantiate a CLVP Decoder 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 Decoder part of the CLVP [susnato/clvp_dev](https://huggingface.co/susnato/clvp_dev) architecture. Configuration objects inherit from [`PreTrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PreTrainedConfig`] for more information. The architecture is similar to GPT2. Args: vocab_size (`int`, *optional*, defaults to 8194): Vocabulary size of the model. max_position_embeddings (`int`, *optional*, defaults to 608): The maximum sequence length of mel tokens that this model might ever be used with. Similar to `n_positions` in `GPT2Config`. max_text_tokens (`int`, *optional*, defaults to 404): The maximum sequence length of text tokens that this model might ever be used with. Similar to `n_positions` in `GPT2Config`. hidden_size (`int`, *optional*, defaults to 1024): Dimensionality of the embeddings and hidden states. num_hidden_layers (`int`, *optional*, defaults to 30): Number of hidden layers in the Transformer encoder. num_attention_heads (`int`, *optional*, defaults to 16): Number of attention heads for each attention layer in the Transformer encoder. n_inner (`int`, *optional*): Dimensionality of the inner feed-forward layers. `None` will set it to 4 times `hidden_size`. num_mel_attn_blocks (`int`, *optional*, defaults to 6): Denotes the number of self attention layers in [`ClvpConditioningEncoder`]. activation_function (`str`, *optional*, defaults to `"gelu_new"`): Activation function, to be selected in the list `["relu", "silu", "gelu", "tanh", "gelu_new"]`. resid_pdrop (`float`, *optional*, defaults to 0.1): The dropout probability for all fully connected layers in the embeddings, encoder, and pooler. embd_pdrop (`float`, *optional*, defaults to 0.1): The dropout ratio for the embeddings. attention_dropout (`float`, *optional*, defaults to 0.1): The dropout ratio for the attention. layer_norm_epsilon (`float`, *optional*, defaults to 1e-05): The epsilon to use in the layer normalization layers. initializer_range (`float`, *optional*, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. summary_type (`string`, *optional*, defaults to `"cls_index"`): Argument used when doing sequence summary. Has to be one of the following options: - `"last"`: Take the last token hidden state (like XLNet). - `"first"`: Take the first token hidden state (like BERT). - `"mean"`: Take the mean of all tokens hidden states. - `"cls_index"`: Supply a Tensor of classification token position (like GPT/GPT-2). - `"attn"`: Not implemented now, use multi-head attention. summary_use_proj (`bool`, *optional*, defaults to `True`): Whether or not to add a projection after the vector extraction. summary_activation (`str`, *optional*): Pass `"tanh"` for a tanh activation to the output, any other value will result in no activation. summary_proj_to_labels (`bool`, *optional*, defaults to `True`): Whether the projection outputs should have `config.num_labels` or `config.hidden_size` classes. summary_first_dropout (`float`, *optional*, defaults to 0.1): The dropout ratio to be used after the projection and activation. use_cache (`bool`, *optional*, defaults to `True`): Whether or not the model should return the last key/values attentions (not used by all models). bos_token_id (`int`, *optional*, defaults to 8192): Beginning of sequence token id, used at the start of the generation. eos_token_id (`int`, *optional*, defaults to 8193): End of sequence token id, used in the method [`ClvpModelForConditionalGeneration.fix_speech_decoder_output()`] to correct decoder outputs. pad_token_id (`int`, *optional*): Padding token id. feature_size (`int`, *optional*, defaults to 80): The feature dimension of the extracted mel features. This value is used in [`ClvpConditioningEncoder`]. use_attention_bias (`bool`, *optional*, defaults to `True`): Whether to use bias in Query, Key and Value layers during self attention. initializer_factor (`float`, *optional*, defaults to 1.0): A factor for initializing all weight matrices (should be kept to 1.0, used internally for initialization testing). decoder_fixing_codes (`list`, *optional*, defaults to `[83, 45, 45, 248]`): These values are used in the method `fix_speech_decoder_output` to fix decoder generated outputs. add_cross_attention (`bool`, *optional*, defaults to `False`): Whether cross-attention layers should be added to the model. Example: ```python >>> from transformers import ClvpDecoderConfig, ClvpDecoder >>> # Initializing a ClvpDecoderConfig with susnato/clvp_dev style configuration >>> decoder_configuration = ClvpDecoderConfig() >>> # Initializing a ClvpDecoder (with random weights) from the susnato/clvp_dev style configuration >>> model = ClvpDecoder(decoder_configuration) >>> # Accessing the model configuration >>> configuration = model.config ``` clvp_decoderdecoder_configi i`iiNgelu_newr<r;g{Gz? cls_indexTi i Pr>)S-rUFc ||_||_||_||_||_||_||_||_| |_| |_ | |_ | |_ | |_ ||_ ||_||_||_||_||_||_||_||_||_||_||_||_||_||_t9|tdi|yr )rmax_position_embeddingsmax_text_tokensrrrn_innernum_mel_attn_blocksactivation_function resid_pdrop embd_pdroprlayer_norm_epsiloninitializer_rangersummary_use_projsummary_activationsummary_first_dropoutsummary_proj_to_labels use_cache feature_sizerrdecoder_fixing_codesrrradd_cross_attentionrr )r!rrXrYrrrrZr[r\r]r^rr_r`rrarbrdrcrerrrrfrrrgrhr"r#s r$r zClvpDecoderConfig.__init__s@%'>$.&!2#6  #6 #6 &$!2"4!2( 0"4%:"&<#"("4"4$8!(((#6  "6"r%)r@rArBrCr)r,r rHrIs@r$rKrKsv^ @ J&O #& #!.!;>#>#r%rKc@eZdZdZdZeeedZ dfd ZxZ S) ClvpConfiga: [`ClvpConfig`] is the configuration class to store the configuration of a [`ClvpModelForConditionalGeneration`]. It is used to instantiate a CLVP model according to the specified arguments, defining the text model, speech model and decoder model configs. Instantiating a configuration with the defaults will yield a similar configuration to that of the CLVP [susnato/clvp_dev](https://huggingface.co/susnato/clvp_dev) architecture. Configuration objects inherit from [`PreTrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PreTrainedConfig`] for more information. Args: text_config (`dict`, *optional*): Dictionary of configuration options used to initialize the CLVP text encoder. speech_config (`dict`, *optional*): Dictionary of configuration options used to initialize CLVP speech encoder. decoder_config (`dict`, *optional*): Dictionary of configuration options used to initialize [`ClvpDecoderConfig`]. projection_dim (`int`, *optional*, defaults to 768): Dimensionality of text and speech projection layers. logit_scale_init_value (`float`, *optional*, defaults to 2.6592): The initial value of the *logit_scale* parameter. Default is used as per the original CLVP implementation. initializer_factor (`float`, *optional*, defaults to 1.0): A factor for initializing all weight matrices (should be kept to 1.0, used internally for initialization testing). kwargs (*optional*): Dictionary of keyword arguments. Example: ```python >>> from transformers import ClvpConfig, ClvpModelForConditionalGeneration >>> # Initializing a ClvpConfig with susnato/clvp_dev style configuration >>> configuration = ClvpConfig() >>> # Initializing a ClvpModelForConditionalGeneration (with random weights) from the susnato/clvp_dev style configuration >>> model = ClvpModelForConditionalGeneration(configuration) >>> # Accessing the model configuration >>> configuration = model.config >>> # We can also initialize a CLVPConfig from a CLVPTextConfig, CLVPSpeechConfig and a CLVPAutoRegressiveConfig >>> from transformers import ClvpEncoderConfig, ClvpDecoderConfig >>> # Initializing a CLVP text, CLVP speech and CLVP decoder configuration >>> config_text = ClvpEncoderConfig() >>> config_speech = ClvpEncoderConfig() >>> decoder_config = ClvpDecoderConfig() >>> config = ClvpConfig(config_text, config_speech, decoder_config) ```r*)r r rMc | t}tjdnt|tr tdi|}| t}tjdnt|tr tdi|}| t }tjdnt|tr t di|}||_||_||_||_ ||_ ||_ t|4di|y)NzR`text_config` is `None`. initializing the `ClvpEncoderConfig` with default values.zT`speech_config` is `None`. initializing the `ClvpEncoderConfig` with default values.zS`image_config` is `None`. initializing the `ClvpDecoderConfig` with default values.r )rr0info isinstancedictrKr r rMrlogit_scale_init_valuerrr ) r!r r rMrrorr"r#s r$r zClvpConfig.__init__s  +-K KKl m  T *+:k:K  -/M KKn o  t ,-> >M  !.0N KKm n  -.@@N&*,,&<#"4 "6"r%)NNNr7g/L F@r>) r@rArBrCr)rrK sub_configsr rHrIs@r$rjrjDs>1 fJ(*+K%####r%rj)rjrKr) rCrFconfiguration_utilsrutilsr get_loggerr@r0rrKrj__all__r r%r$rus_ 3   H %C4(C4Lb#(b#J^#!^#B Cr%