o ZhB@sdZddlmZddlmZmZmZmZmZddl m Z ddl m Z m Z ddlmZer>ddlmZdd lmZdd lmZeeZgd Zgd ZGd dde ZGddde ZddgZdS)zWhisper model configuration) OrderedDict) TYPE_CHECKINGAnyMappingOptionalUnion)PretrainedConfig) OnnxConfigOnnxSeq2SeqConfigWithPast)logging)FeatureExtractionMixin)PreTrainedTokenizerBase) TensorType)X :;<=>?Z[\]ieiniiiiiii"iiiii?iaioiciiSiri9 i i iisiiiiii#i%i&iC)i"*i,i-i.ik3i5i5i9i;i@iAiHFiKi6LiPi!WiYiiiuiviii[i-ieiiQi)Vrrrrrrrrrrrrrrrrr r!r"r#r$r%r&igii iiii}iiiiiFi=ii iC i i i i iiyiWi;iiiiie#i$i(i*i.i/i+0i1i5iM7i+9i;i=i@i@iGi JikNiTiWifi1fiCgiwnisi{i.~i~iioiAiiNiRr(r)ic%seZdZdZdZdgZddddZddd d d d d d d d d ddddd d d ddddddddddgddddddd dddf%fdd ZZS) WhisperConfiga# This is the configuration class to store the configuration of a [`WhisperModel`]. It is used to instantiate a Whisper 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 Whisper [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) 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 51865): Vocabulary size of the Whisper model. Defines the number of different tokens that can be represented by the `decoder_input_ids` passed when calling [`WhisperModel`] num_mel_bins (`int`, *optional*, defaults to 80): Number of mel features used per input features. Should correspond to the value used in the `WhisperProcessor` class. encoder_layers (`int`, *optional*, defaults to 4): Number of encoder layers. decoder_layers (`int`, *optional*, defaults to 4): Number of decoder layers. encoder_attention_heads (`int`, *optional*, defaults to 6): Number of attention heads for each attention layer in the Transformer encoder. decoder_attention_heads (`int`, *optional*, defaults to 6): Number of attention heads for each attention layer in the Transformer decoder. encoder_ffn_dim (`int`, *optional*, defaults to 1536): Dimensionality of the "intermediate" (often named feed-forward) layer in encoder. decoder_ffn_dim (`int`, *optional*, defaults to 1536): Dimensionality of the "intermediate" (often named feed-forward) layer in decoder. encoder_layerdrop (`float`, *optional*, defaults to 0.0): The LayerDrop probability for the encoder. See the [LayerDrop paper](see https://arxiv.org/abs/1909.11556) for more details. decoder_layerdrop (`float`, *optional*, defaults to 0.0): The LayerDrop probability for the decoder. See the [LayerDrop paper](see https://arxiv.org/abs/1909.11556) for more details. decoder_start_token_id (`int`, *optional*, defaults to 50257): Corresponds to the "<|startoftranscript|>" token, which is automatically used when no `decoder_input_ids` are provided to the `generate` function. It is used to guide the model`s generation process depending on the task. use_cache (`bool`, *optional*, defaults to `True`): Whether or not the model should return the last key/values attentions (not used by all models). is_encoder_decoder (`bool`, *optional*, defaults to `True`): Whether the model is used as an encoder/decoder or not. activation_function (`str`, *optional*, defaults to `"gelu"`): The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`, `"relu"`, `"silu"` and `"gelu_new"` are supported. d_model (`int`, *optional*, defaults to 384): Dimensionality of the layers. dropout (`float`, *optional*, defaults to 0.1): The dropout probability for all fully connected layers in the embeddings, encoder, and pooler. attention_dropout (`float`, *optional*, defaults to 0.0): The dropout ratio for the attention probabilities. activation_dropout (`float`, *optional*, defaults to 0.0): The dropout ratio for activations inside the fully connected layer. init_std (`float`, *optional*, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. scale_embedding (`bool`, *optional*, defaults to False): Scale embeddings by diving by sqrt(d_model). max_source_positions (`int`, *optional*, defaults to 1500): The maximum sequence length of log-mel filter-bank features that this model might ever be used with. max_target_positions (`int`, *optional*, defaults to 448): 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). pad_token_id (`int`, *optional*, defaults to 50256): Padding token id. bos_token_id (`int`, *optional*, defaults to 50256): Begin of stream token id. eos_token_id (`int`, *optional*, defaults to 50256): End of stream token id. suppress_tokens (`List[int]`, *optional*): A list containing the non-speech tokens that will be used by the logit processor in the `generate` function. NON_SPEECH_TOKENS and NON_SPEECH_TOKENS_MULTI each correspond to the `english-only` and the `multilingual` model. begin_suppress_tokens (`List[int]`, *optional*, defaults to `[220,50256]`): A list containing tokens that will be suppressed at the beginning of the sampling process. Initialized as the token for `" "` (`blank_token_id`) and the `eos_token_id` use_weighted_layer_sum (`bool`, *optional*, defaults to `False`): Whether to use a weighted average of layer outputs with learned weights. Only relevant when using an instance of [`WhisperForAudioClassification`]. classifier_proj_size (`int`, *optional*, defaults to 256): Dimensionality of the projection before token mean-pooling for classification. Only relevant when using an instance of [`WhisperForAudioClassification`]. apply_spec_augment (`bool`, *optional*, defaults to `False`): Whether to apply *SpecAugment* data augmentation to the outputs of the feature encoder. For reference see [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://arxiv.org/abs/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 == 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`. median_filter_width (`int`, *optional*, defaults to 7): Width of the median filter used to smoothen to cross-attention outputs when computing token timestamps. Should be an odd number. Example: ```python >>> from transformers import WhisperConfig, WhisperModel >>> # Initializing a Whisper tiny style configuration >>> configuration = WhisperConfig() >>> # Initializing a model (with random weights) from the tiny style configuration >>> model = WhisperModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```Zwhisperpast_key_valuesencoder_attention_headsd_model)Znum_key_value_headsZnum_attention_headsZ hidden_sizeiPigr'TZgeluig{Gz?FiiiPNg?rrrrc&' s||_||_||_||_||_||_||_||_||_||_ ||_ ||_ ||_ ||_ | |_| |_| |_||_||_||_||_||_||_||_||_| |_|!|_|"|_|#|_|$|_|%|_tj d|||| | ||d|&dS)N) pad_token_id bos_token_id eos_token_idis_encoder_decoderdecoder_start_token_idsuppress_tokensbegin_suppress_tokens)! vocab_size num_mel_binsr-encoder_layersr,decoder_layersdecoder_attention_headsdecoder_ffn_dimencoder_ffn_dimdropoutattention_dropoutactivation_dropoutactivation_functioninit_stdencoder_layerdropdecoder_layerdrop use_cacheZnum_hidden_layersscale_embeddingmax_source_positionsmax_target_positionsclassifier_proj_sizeuse_weighted_layer_sumapply_spec_augmentmask_time_probmask_time_lengthmask_time_min_masksmask_feature_probmask_feature_lengthmask_feature_min_masksmedian_filter_widthsuper__init__)'selfr;r<r=r,r>r?r@rArGrHr7rIr6rEr-rBrCrDrFrJrKrLr3r4r5r8r9rNrMrOrPrQrRrSrTrUrVkwargs __class__r:`/var/www/auris/lib/python3.10/site-packages/transformers/models/whisper/configuration_whisper.pyrXsT) zWhisperConfig.__init__) __name__ __module__ __qualname____doc__Z model_typeZkeys_to_ignore_at_inferenceZ attribute_maprX __classcell__r:r:r[r]r*;s^r*cseZdZedeeeeefffddZ       dd ed d ed ede de ddede dedeee fffdd Z ede fddZZS)WhisperOnnxConfigreturncCsPtdddddfg}|jrddi|d<nddd |d<|jr&|j|d d |S) Ninput_featuresbatchZ feature_sizeZencoder_sequence)rrrrdecoder_input_idsZdecoder_sequence)rrinputs) direction)ruse_pastZfill_with_past_key_values_)rYZ common_inputsr:r:r]rh!szWhisperOnnxConfig.inputsFN"V@r1 preprocessor)rr batch_size seq_lengthis_pair frameworkr sampling_rate time_duration frequencyc st} tj||j|||||d} | djd} |jr| dn|}t|j||||} | d| d<| d| d<d| vrD| d| d<| S)N)rnrorrrsrtrurerrgr+) rr generate_dummy_inputsZfeature_extractorshaperjrWZ tokenizerpop) rYrnrorprqrrrsrtruZ dummy_inputsZencoder_inputsZencoder_sequence_lengthZdecoder_inputsr[r:r]rv2s(   z'WhisperOnnxConfig.generate_dummy_inputscCsdS)NgMbP?r:)rYr:r:r]atol_for_validationVsz%WhisperOnnxConfig.atol_for_validation)rkrkFNrlrmr1)r^r_r`propertyrstrintrhrboolrfloatrrvryrbr:r:r[r]rc s>   $rcN)ra collectionsrtypingrrrrrZconfiguration_utilsr Zonnxr r utilsr Zfeature_extraction_utilsr Ztokenization_utils_baserrZ get_loggerr^loggerZNON_SPEECH_TOKENSZNON_SPEECH_TOKENS_MULTIr*rc__all__r:r:r:r]s"        f ;