^j< zdZddlmZddlmZddlmZgdZgdZed eGd d eZ d gZ y ) zWhisper model configuration)strict)PreTrainedConfig)auto_docstring)X :;<=>?Z[\]ieiniiiiiii"iiiii?iaioiciiSiri9 i i iisiiiiii#i%i&iC)i"*i,i-i.ik3i5i5i9i;i@iAiHFiKi6LiPi!WiYiiiuiviii[i-ieiiQi)Vrrr r r r r rrrrrrrrrrrrrrrrigii iiii}iiiiiFi=ii iC i i i i iiyiWi;iiiiie#i$i(i*i.i/i+0i1i5iM7i+9i;i=i@i@iGi JikNiTiWifi1fiCgiwnisi{i.~i~iioiAiiNiRrr izopenai/whisper-tiny) checkpointceZdZUdZdZdgZdddddZdZee d <d Z ee d <d Z ee d<d Z ee d<d Z ee d<d Zee d<dZee d<dZee d<dZeeze d<dZeeze d<dZee d<dZee d<dZee d<dZee d<dZee d<dZeeze d<dZeeze d<dZeeze d <d!Zee d"<d#Zee d$<d%Z ee d&<d'Z!ee d(<d)Z"ed*ze d+<d)Z#ed*ze d,<d)Z$ee%ezd*ze d-<d*Z&e%d*ze d.<d/Z'e%ee(ed0fzd*ze d1<d#Z)ee d2<d3Z*ee d4<d#Z+ee d5<d6Z,eeze d7<d8Z-ee d9<d:Z.ee d;<dZ/eeze d<<d8Z0ee d=<d>Z1ee d?<d@Z2ee dA<dZ3ee dB<y*)C WhisperConfiga 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). 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 ```whisperpast_key_valuesencoder_attention_headsd_modelencoder_layers)num_key_value_headsnum_attention_heads hidden_sizenum_hidden_layersi vocab_sizeP num_mel_binsdecoder_layersdecoder_attention_headsidecoder_ffn_dimencoder_ffn_dimgencoder_layerdropdecoder_layerdroprdecoder_start_token_idT use_cacheis_encoder_decodergeluactivation_functionidropoutattention_dropoutactivation_dropoutg{Gz?init_stdFscale_embeddingimax_source_positionsimax_target_positionsPN pad_token_id bos_token_id eos_token_idsuppress_tokens)rD.begin_suppress_tokensuse_weighted_layer_sumclassifier_proj_sizeapply_spec_augmentg?mask_time_probr mask_time_lengthrmask_time_min_masksmask_feature_probmask_feature_lengthrmask_feature_min_masksr median_filter_widthtie_word_embeddings)4__name__ __module__ __qualname____doc__ model_typekeys_to_ignore_at_inference attribute_mapr-int__annotations__r/r(r&r2r3r4r5r6floatr7r8r9boolr:r<strr'r=r>r?r@rArBrCrErFrGlistrHrJtuplerKrMrNrOrPrQrRrSrTrUrV|/var/www/ramen.bs-engineer-server.com/venv/lib/python3.12/site-packages/transformers/models/whisper/configuration_whisper.pyr#r#0s A FJ#4"588 - MJL#NC#$S$NC#$S$OSOS%(us{(%(us{("'C'It##%%GSGUS[%(us{(&) )He!OT! $#$ ###$L#*$$L#*$+0L#S /D(0#'OTD['@L49uS#X6=L#(D( ###$$"&NECK&c  %(us{(!!"#C#  $$rfr#N) rZhuggingface_hub.dataclassesrconfiguration_utilsrutilsrNON_SPEECH_TOKENSNON_SPEECH_TOKENS_MULTIr#__all__rerfrgrns[".3#  01r%$r%2r%j  rf