^jp;dZddlZddlZddlmZddlmZddlmZedeGd d eZ edeGd d eZ d d gZ y) zSpeechT5 model configurationN)strict)PreTrainedConfig)auto_docstringzmicrosoft/speecht5_asr) checkpointceZdZUdZdZdddZdZeed<dZ eed <d Z eed<d Z eed<d Z eed <d Z eezed<dZeed<d Zeed<d Zeed<d Zeezed<dZeed<d Zeezed<d Zeezed<d Zeezed<d Zeezed<dZeed<dZeed<dZeed<d Zeed!<d"Zeezed#<dZeed$<d%Z e!ee"ed&fzed'<d(Z#e!ee"ed&fzed)<d*Z$e!ee"ed&fzed+<dZ%eed,<d-Z&eed.<d/Z'eed0<d1Z(eed2<d3Z)eezed4<d5Z*eed6<d7Z+eed8<d"Z,eezed9<d5Z-eed:<d;Z.eed<<d=Z/ed>zed?<d;Z0ed>zed@<d7Z1ee!ezd>zedA<d7Z2ed>zedB<dCZ3eedD<d7Z4eedE<dFZ5eedG<dHZ6eezedI<dJZ7eedK<dLZ8eedM<dFZ9eedN<dLZ:eedO<dHZ;eezedP<d7ZeedU<dVZ?eedW<d1Z@eedX<d7ZAeedY<dZZBeed[<d\ZCeed]<d1ZDeed^<d1ZEeed_<d1ZFeed`<fdaZGdbZHdcZIxZJS)dSpeechT5Configat positional_dropout (`float`, *optional*, defaults to 0.1): The dropout probability for the text position encoding layers. feat_extract_norm (`str`, *optional*, defaults to `"group"`): The norm to be applied to 1D convolutional layers in the speech encoder pre-net. One of `"group"` for group normalization of only the first 1D convolutional layer or `"layer"` for layer normalization of all 1D convolutional layers. feat_proj_dropout (`float`, *optional*, defaults to 0.0): The dropout probability for output of the speech encoder pre-net. feat_extract_activation (`str, `optional`, defaults to `"gelu"`): The non-linear activation function (function or string) in the 1D convolutional layers of the feature extractor. If string, `"gelu"`, `"relu"`, `"selu"` and `"gelu_new"` are supported. conv_dim (`tuple[int]` or `list[int]`, *optional*, defaults to `(512, 512, 512, 512, 512, 512, 512)`): A tuple of integers defining the number of input and output channels of each 1D convolutional layer in the speech encoder pre-net. The length of *conv_dim* defines the number of 1D convolutional layers. conv_stride (`tuple[int]` or `list[int]`, *optional*, defaults to `(5, 2, 2, 2, 2, 2, 2)`): A tuple of integers defining the stride of each 1D convolutional layer in the speech encoder pre-net. The length of *conv_stride* defines the number of convolutional layers and has to match the length of *conv_dim*. conv_kernel (`tuple[int]` or `list[int]`, *optional*, defaults to `(10, 3, 3, 3, 3, 3, 3)`): A tuple of integers defining the kernel size of each 1D convolutional layer in the speech encoder pre-net. The length of *conv_kernel* defines the number of convolutional layers and has to match the length of *conv_dim*. conv_bias (`bool`, *optional*, defaults to `False`): Whether the 1D convolutional layers have a bias. num_conv_pos_embeddings (`int`, *optional*, defaults to 128): Number of convolutional positional embeddings. Defines the kernel size of 1D convolutional positional embeddings layer. num_conv_pos_embedding_groups (`int`, *optional*, defaults to 16): Number of groups of 1D convolutional positional embeddings layer. apply_spec_augment (`bool`, *optional*, defaults to `True`): Whether to apply *SpecAugment* data augmentation to the outputs of the speech encoder pre-net. For reference see [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://huggingface.co/papers/1904.08779). mask_time_prob (`float`, *optional*, defaults to 0.05): Percentage (between 0 and 1) of all feature vectors along the time axis which will be masked. The masking procedure generates ''mask_time_prob*len(time_axis)/mask_time_length'' independent masks over the axis. If reasoning from the probability of each feature vector to be chosen as the start of the vector span to be masked, *mask_time_prob* should be `prob_vector_start*mask_time_length`. Note that overlap may decrease the actual percentage of masked vectors. This is only relevant if `apply_spec_augment is True`. mask_time_length (`int`, *optional*, defaults to 10): Length of vector span along the time axis. mask_time_min_masks (`int`, *optional*, defaults to 2),: The minimum number of masks of length `mask_feature_length` generated along the time axis, each time step, irrespectively of `mask_feature_prob`. Only relevant if ''mask_time_prob*len(time_axis)/mask_time_length < mask_time_min_masks'' mask_feature_prob (`float`, *optional*, defaults to 0.0): Percentage (between 0 and 1) of all feature vectors along the feature axis which will be masked. The masking procedure generates ''mask_feature_prob*len(feature_axis)/mask_time_length'' independent masks over the axis. If reasoning from the probability of each feature vector to be chosen as the start of the vector span to be masked, *mask_feature_prob* should be `prob_vector_start*mask_feature_length`. Note that overlap may decrease the actual percentage of masked vectors. This is only relevant if `apply_spec_augment is True`. mask_feature_length (`int`, *optional*, defaults to 10): Length of vector span along the feature axis. mask_feature_min_masks (`int`, *optional*, defaults to 0),: The minimum number of masks of length `mask_feature_length` generated along the feature axis, each time step, irrespectively of `mask_feature_prob`. Only relevant if ''mask_feature_prob*len(feature_axis)/mask_feature_length < mask_feature_min_masks'' num_mel_bins (`int`, *optional*, defaults to 80): Number of mel features used per input features. Used by the speech decoder pre-net. Should correspond to the value used in the [`SpeechT5Processor`] class. speech_decoder_prenet_layers (`int`, *optional*, defaults to 2): Number of layers in the speech decoder pre-net. speech_decoder_prenet_units (`int`, *optional*, defaults to 256): Dimensionality of the layers in the speech decoder pre-net. speech_decoder_prenet_dropout (`float`, *optional*, defaults to 0.5): The dropout probability for the speech decoder pre-net layers. speaker_embedding_dim (`int`, *optional*, defaults to 512): Dimensionality of the *XVector* embedding vectors. speech_decoder_postnet_layers (`int`, *optional*, defaults to 5): Number of layers in the speech decoder post-net. speech_decoder_postnet_units (`int`, *optional*, defaults to 256): Dimensionality of the layers in the speech decoder post-net. speech_decoder_postnet_kernel (`int`, *optional*, defaults to 5): Number of convolutional filter channels in the speech decoder post-net. speech_decoder_postnet_dropout (`float`, *optional*, defaults to 0.5): The dropout probability for the speech decoder post-net layers. reduction_factor (`int`, *optional*, defaults to 2): Spectrogram length reduction factor for the speech decoder inputs. max_speech_positions (`int`, *optional*, defaults to 4000): The maximum sequence length of speech features that this model might ever be used with. max_text_positions (`int`, *optional*, defaults to 450): The maximum sequence length of text features that this model might ever be used with. encoder_max_relative_position (`int`, *optional*, defaults to 160): Maximum distance for relative position embedding in the encoder. use_guided_attention_loss (`bool`, *optional*, defaults to `True`): Whether to apply guided attention loss while training the TTS model. guided_attention_loss_num_heads (`int`, *optional*, defaults to 2): Number of attention heads the guided attention loss will be applied to. Use -1 to apply this loss to all attention heads. guided_attention_loss_sigma (`float`, *optional*, defaults to 0.4): Standard deviation for guided attention loss. guided_attention_loss_scale (`float`, *optional*, defaults to 10.0): Scaling coefficient for guided attention loss (also known as lambda). Example: ```python >>> from transformers import SpeechT5Model, SpeechT5Config >>> # Initializing a "microsoft/speecht5_asr" style configuration >>> configuration = SpeechT5Config() >>> # Initializing a model (with random weights) from the "microsoft/speecht5_asr" style configuration >>> model = SpeechT5Model(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```speecht5encoder_attention_headsencoder_layers)num_attention_headsnum_hidden_layersQ vocab_sizei hidden_size i encoder_ffn_dim皙?encoder_layerdropdecoder_layersdecoder_ffn_dimdecoder_attention_headsdecoder_layerdropgelu hidden_actpositional_dropouthidden_dropoutattention_dropoutactivation_dropoutg{Gz?initializer_rangegh㈵>layer_norm_epsFscale_embeddinggroupfeat_extract_normgfeat_proj_dropoutfeat_extract_activation)r(r(r(r(r(r(.conv_dim)r+r+r+r+r+ conv_stride) rrrrr+r+ conv_kernel conv_biasnum_conv_pos_embeddingsnum_conv_pos_embedding_groupsTapply_spec_augmentg?mask_time_probr-mask_time_lengthr+mask_time_min_masksmask_feature_probmask_feature_lengthrmask_feature_min_masksN pad_token_id bos_token_id eos_token_iddecoder_start_token_idP num_mel_binsspeech_decoder_prenet_layersspeech_decoder_prenet_unitsg?speech_decoder_prenet_dropoutr(speaker_embedding_dimr*speech_decoder_postnet_layersspeech_decoder_postnet_unitsspeech_decoder_postnet_kernelspeech_decoder_postnet_dropoutreduction_factorimax_speech_positionsimax_text_positionsencoder_max_relative_positionuse_guided_attention_lossguided_attention_loss_num_headsg?guided_attention_loss_sigmag$@guided_attention_loss_scale use_cacheis_encoder_decodertie_word_embeddingsc Xt|j|_t|di|y)N)lenr)num_feat_extract_layerssuper __post_init__)selfkwargs __class__s ~/var/www/ramen.bs-engineer-server.com/venv/lib/python3.12/site-packages/transformers/models/speecht5/configuration_speecht5.pyr\zSpeechT5Config.__post_init__s$'*4=='9$ ''c lt|j|jk7sDt|j|jk7s"t|j|jk7rNt dt|jdt|jdt|jdy)zOPart of `@strict`-powered validation. Validates the architecture of the config.zConfiguration for convolutional layers is incorrect. It is required that `len(config.conv_dim)` == `len(config.conv_stride)` == `len(config.conv_kernel)`, but is `len(config.conv_dim) = z`, `len(config.conv_stride) = z`, `len(config.conv_kernel) = z`.N)rYr,rZr.r) ValueErrorr]s r`validate_architecturez$SpeechT5Config.validate_architectures!! "d&B&B BD$$%)E)EEDMM"d&B&BB &''Ec$JZJZF[E\]//243C3C/D.ERI Crac`tjtj|jdS)Nr;) functoolsreduceoperatormulr,rds r`inputs_to_logits_ratioz%SpeechT5Config.inputs_to_logits_ratios! d.>.>BBra)K__name__ __module__ __qualname____doc__ model_type attribute_maprint__annotations__rr r rrfloatrrrrrstrrrrr r!r"r#boolr%r&r'r)listtupler,r.r/r1r3r4r5r6r7r8r9r:r<r=r>r?rArBrDrErFrGrHrIrJrKrLrMrOrPrQrRrSrTrUrVr\rerk __classcell__)r_s@r`r r sm ^J,E\lmMJKNC#%S%OS%(us{(NCOS#%S%%(us{(J&) )"%NECK%%(us{(&) )#u# NE !OT!$s$%(us{(#)S),OHd3i%S/)O/DKcU38_,D/EKcU38_,EIt#&S&)+!3+##"&NECK&c  %(us{(!!"#C# L#*  L#* +,L#S /D(,)*C$J*L#() #)'**14!53;4!$3$)*!3*(+ #+)*!3*25"ECK5c $#$!!),!3,&*t*+,#S,),,)--It## $$( Crar ceZdZUdZdZdZeed<dZeed<dZ eed<d Z e ee ed fzed <d Z e ee ed fzed <dZe ee ed fzed<dZe e zed<dZeed<dZeed<dZeed<y)SpeechT5HifiGanConfiga model_in_dim (`int`, *optional*, defaults to 80): The number of frequency bins in the input log-mel spectrogram. upsample_initial_channel (`int`, *optional*, defaults to 512): The number of input channels into the upsampling network. upsample_rates (`tuple[int]` or `list[int]`, *optional*, defaults to `[4, 4, 4, 4]`): A tuple of integers defining the stride of each 1D convolutional layer in the upsampling network. The length of *upsample_rates* defines the number of convolutional layers and has to match the length of *upsample_kernel_sizes*. upsample_kernel_sizes (`tuple[int]` or `list[int]`, *optional*, defaults to `[8, 8, 8, 8]`): A tuple of integers defining the kernel size of each 1D convolutional layer in the upsampling network. The length of *upsample_kernel_sizes* defines the number of convolutional layers and has to match the length of *upsample_rates*. resblock_kernel_sizes (`tuple[int]` or `list[int]`, *optional*, defaults to `[3, 7, 11]`): A tuple of integers defining the kernel sizes of the 1D convolutional layers in the multi-receptive field fusion (MRF) module. resblock_dilation_sizes (`tuple[tuple[int]]` or `list[list[int]]`, *optional*, defaults to `[[1, 3, 5], [1, 3, 5], [1, 3, 5]]`): A nested tuple of integers defining the dilation rates of the dilated 1D convolutional layers in the multi-receptive field fusion (MRF) module. leaky_relu_slope (`float`, *optional*, defaults to 0.1): The angle of the negative slope used by the leaky ReLU activation. normalize_before (`bool`, *optional*, defaults to `True`): Whether or not to normalize the spectrogram before vocoding using the vocoder's learned mean and variance. Example: ```python >>> from transformers import SpeechT5HifiGan, SpeechT5HifiGanConfig >>> # Initializing a "microsoft/speecht5_hifigan" style configuration >>> configuration = SpeechT5HifiGanConfig() >>> # Initializing a model (with random weights) from the "microsoft/speecht5_hifigan" style configuration >>> model = SpeechT5HifiGan(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```speecht5_hifiganr@ model_in_dimi> sampling_rater(upsample_initial_channel)rrr.upsample_rates)rrrupsample_kernel_sizes)r resblock_kernel_sizes)r;rr*rrresblock_dilation_sizesg{Gz?r!rleaky_relu_slopeTnormalize_beforeN)rlrmrnrorpr}rrrsr~rrrwrxrrrr!rtrrrvrXrar`r{r{s% N$JL#M3$'c'2>NDIc3h/>9E49uS#X6E9C49uS#X6C,MTE\M#u#!e!!d!rar{) rorgrihuggingface_hub.dataclassesrconfiguration_utilsrutilsrr r{__all__rXrar`rs#.3#34AC%AC5ACH343",3"53"l 4 5ra