o ¾e¦im9ã@sPdZddlmZddlmZe e¡Zgd¢Zgd¢Z Gdd„deƒZ dgZ dS) zWhisper model configurationé)ÚPreTrainedConfig)Úlogging)Xééééé é éééééééé:é;é<é=é>é?éZé[é\é]ieini¶ii­iÁii¢i"iÄióiÿii?iaioiciöiSiri9 i¸ i‹ i¨isiøiÈi³ißi¹i#i‰%iç&iC)i"*iœ,i½-iƒ.ik3i5i„5iØ9iÊ;i@i—AiHFiKi6LiôPi!Wi—YiiiuiÔvi‚i…ˆi[i-žieži²¸iú¿éQÄi·Äé¸Äé¹Ä)Vrrrrrr r r r r rrrrrrrrrrrrrigi÷i iiii}i†i–iši£iFi=i¾iœ iC i® iµ iÄ iÐ iiyiWi;i¹i÷iiie#i§$i¼(i±*i¢.i/i+0i1iá5iM7i+9i¡;i=i©@iÜ@iºGi JikNi«TiøWifi1fiCgiwnisi¢{i.~iÖ~iio§iA¹iÎÂiNÄiRÄrriºÄc&sˆeZdZdZdZdgZddddœZddd d d d d d d d d ddddd d d ddddddddddgddddddd ddddf&‡fdd„ Z‡ZS) Ú 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://huggingface.co/papers/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://huggingface.co/papers/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://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 == 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 ```ÚwhisperÚpast_key_valuesÚencoder_attention_headsÚd_model)Únum_key_value_headsÚnum_attention_headsÚ hidden_sizei™ÊéPééigrTÚgelui€g{®Gáz”?FiÜiÀiPÄNéÜégš™™™™™©?r rérc'( sö||_||_||_||_||_||_||_||_||_||_ ||_ ||_ ||_ ||_ | |_| |_| |_||_||_||_||_||_||_||_||_| |_|!|_|"|_|#|_|$|_|%|_||_||_ ||_!| |_"|&|_#t$ƒj%d| ||dœ|'¤ŽdS)N)Úis_encoder_decoderÚsuppress_tokensÚbegin_suppress_tokens©)&Ú vocab_sizeÚ num_mel_binsr"Úencoder_layersr!Údecoder_layersÚdecoder_attention_headsÚdecoder_ffn_dimÚencoder_ffn_dimÚdropoutÚattention_dropoutÚactivation_dropoutÚactivation_functionÚinit_stdÚencoder_layerdropÚdecoder_layerdropÚ use_cacheÚnum_hidden_layersÚscale_embeddingÚmax_source_positionsÚmax_target_positionsÚclassifier_proj_sizeÚuse_weighted_layer_sumÚapply_spec_augmentÚmask_time_probÚmask_time_lengthÚmask_time_min_masksÚmask_feature_probÚmask_feature_lengthÚmask_feature_min_masksÚmedian_filter_widthÚ pad_token_idÚ bos_token_idÚ eos_token_idÚdecoder_start_token_idÚtie_word_embeddingsÚsuperÚ__init__)(Úselfr1r2r3r!r4r5r6r7r=r>rQr?r-r;r"r8r9r:r<rArBrCrNrOrPr.r/rErDrFrGrHrIrJrKrLrMrRÚkwargs©Ú __class__r0úo/home/ubuntu/transcripts/venv/lib/python3.10/site-packages/transformers/models/whisper/configuration_whisper.pyrT¼sV*ý üzWhisperConfig.__init__) Ú__name__Ú __module__Ú __qualname__Ú__doc__Ú model_typeÚkeys_to_ignore_at_inferenceÚ attribute_maprTÚ __classcell__r0r0rWrYr1s`ýÙrN) r]Úconfiguration_utilsrÚutilsrÚ get_loggerrZÚloggerÚNON_SPEECH_TOKENSÚNON_SPEECH_TOKENS_MULTIrÚ__all__r0r0r0rYÚs     h