fThw5SrSSKrSSKrSSKJr SSKrSSKJr SSK J r SSK J r SSK Jr S S KJr \ R""\5r"S S \ 5rS /rg) z Processor class for Bark N)Optional) BatchFeature)ProcessorMixin)logging) cached_file) AutoTokenizerc^\rSrSrSrSrS/rSSSS.rSU4Sjjr\ SS j5r SS \ 4U4S jjjr SS \ \4S jjrSS \ \4SjjrSSjrSrU=r$) BarkProcessor#a Constructs a Bark processor which wraps a text tokenizer and optional Bark voice presets into a single processor. Args: tokenizer ([`PreTrainedTokenizer`]): An instance of [`PreTrainedTokenizer`]. speaker_embeddings (`Dict[Dict[str]]`, *optional*): Optional nested speaker embeddings dictionary. The first level contains voice preset names (e.g `"en_speaker_4"`). The second level contains `"semantic_prompt"`, `"coarse_prompt"` and `"fine_prompt"` embeddings. The values correspond to the path of the corresponding `np.ndarray`. See [here](https://suno-ai.notion.site/8b8e8749ed514b0cbf3f699013548683?v=bc67cff786b04b50b3ceb756fd05f68c) for a list of `voice_preset_names`. r tokenizerr semantic_prompt coarse_prompt fine_promptc0>[TU]U5 X lgN)super__init__speaker_embeddings)selfrr __class__s `/var/www/auris/envauris/lib/python3.13/site-packages/transformers/models/bark/processing_bark.pyrBarkProcessor.__init__<s #"4c bUb[UUURSS5URSS5URSS5URSS5URSS5URSS5URS S5URS S5SSSS 9 nUc9[RS [R R X5S 35 SnO-[U5n[R"U5nSSS5 OSn[R"U40UD6nU"UWS9$!,(df  N,=f)ac Instantiate a Bark processor associated with a pretrained model. Args: pretrained_model_name_or_path (`str` or `os.PathLike`): This can be either: - a string, the *model id* of a pretrained [`BarkProcessor`] hosted inside a model repo on huggingface.co. - a path to a *directory* containing a processor saved using the [`~BarkProcessor.save_pretrained`] method, e.g., `./my_model_directory/`. speaker_embeddings_dict_path (`str`, *optional*, defaults to `"speaker_embeddings_path.json"`): The name of the `.json` file containing the speaker_embeddings dictionary located in `pretrained_model_name_or_path`. If `None`, no speaker_embeddings is loaded. **kwargs Additional keyword arguments passed along to both [`~tokenization_utils_base.PreTrainedTokenizer.from_pretrained`]. N subfolder cache_dirforce_downloadFproxiesresume_downloadlocal_files_onlyuse_auth_tokenrevision rr r!r"r#r$tokenr& _raise_exceptions_for_gated_repo%_raise_exceptions_for_missing_entries'_raise_exceptions_for_connection_errors`z` does not exists , no preloaded speaker embeddings will be used - Make sure to provide a correct path to the json dictionary if wanted, otherwise set `speaker_embeddings_dict_path=None`.)rr) rpoploggerwarningospathjoinopenjsonloadr from_pretrained)cls!pretrained_processor_name_or_pathspeaker_embeddings_dict_pathkwargsspeaker_embeddings_pathrspeaker_embeddings_jsonrs rr6BarkProcessor.from_pretrainedAs1. ( 3&11, **[$7 **[$7%zz*:EB 9d3 & +!Fjj!148J5166;8=' #'."'',,'Hghi]` &*"126M)-3J)K&32"& !112S^W]^ Y;MNN32s D  D. push_to_hubc >URGb.[R"[RR XS5SS9 0nXS'URHnUS:wdM UR U5n0n URUHhn [ R"[RR USX7SU 35XSS9 [RR X7SU S 35X'Mj XU'M [[RR X5S 5n [R"Xk5 SSS5 [T U]0"X40UD6 g!,(df  N =f) a Saves the attributes of this processor (tokenizer...) in the specified directory so that it can be reloaded using the [`~BarkProcessor.from_pretrained`] method. Args: save_directory (`str` or `os.PathLike`): Directory where the tokenizer files and the speaker embeddings will be saved (directory will be created if it does not exist). speaker_embeddings_dict_path (`str`, *optional*, defaults to `"speaker_embeddings_path.json"`): The name of the `.json` file that will contains the speaker_embeddings nested path dictionary, if it exists, and that will be located in `pretrained_model_name_or_path/speaker_embeddings_directory`. speaker_embeddings_directory (`str`, *optional*, defaults to `"speaker_embeddings/"`): The name of the folder in which the speaker_embeddings arrays will be saved. push_to_hub (`bool`, *optional*, defaults to `False`): Whether or not to push your model to the Hugging Face model hub after saving it. You can specify the repository you want to push to with `repo_id` (will default to the name of `save_directory` in your namespace). kwargs: Additional key word arguments passed along to the [`~utils.PushToHubMixin.push_to_hub`] method. Nv2T)exist_ok repo_or_path_F) allow_picklez.npyw) rr0makedirsr1r2_load_voice_presetnpsaver3r4dumprsave_pretrained) rsave_directoryr9speaker_embeddings_directoryr>r:embeddings_dict prompt_key voice_presettmp_dictkeyfprs rrKBarkProcessor.save_pretrainedysA8  " " . KK ^SWXcg h O.PRUVZ\ /.W FvFWVs E ErPc URUn0nSGH3nXS;a[SUSUS35e[URRSS5X5UR SS5UR SS5UR S S 5UR S S5UR S S5UR S S 5UR SS5UR SS5S S S S9 nUcL[S[ R RURRSS5X55SUS35e[R"U5XE'GM6 U$)Nr#Voice preset unrecognized, missing z% as a key in self.speaker_embeddings[z].rB/rr r!Fr"r#r$r%r&r'r,z{` does not exists , no preloaded voice preset will be used - Make sure to provide correct paths to the z embeddings.) r ValueErrorrgetr-r0r1r2rHr5)rrPr:voice_preset_pathsvoice_preset_dictrRr1s rrG BarkProcessor._load_voice_presetsh!44\BFC, 9#>cdpcqqst''++NC@"' **[$7 **[$7%zz*:EB 9d3 & +!Fjj!148J5166;8=D| "'',,t'>'>'B'B>SV'WYkYpqrsjjviwx # &(WWT]  "9G<! rc lSHnX!;a[SUS35e[X[R5(d'[ US[ UR U5S35e[XR5UR U:wdM[US[ UR U5S35e g)NrrVz as a key.z voice preset must be a z D ndarray.) rX isinstancerHndarray TypeErrorstr preset_shapelenshape)rrPrRs r_validate_voice_preset_dict)BarkProcessor._validate_voice_preset_dictsFC& #Fse:!VWWl/<<3%'?DDUDUVYDZ@[?\\f ghh<$**+t/@/@/EE C5(@TEVEVWZE[A\@]]g!hiiGrc Ub[U[5(d[U[5(a.URb!X R;aUR U5nOF[U[5(aUR S5(dUS-n[ R"U5nUbUR"U40UD6 [X#S9nUR"U4USUUUUS.UD6n UbX)S'U $)a. Main method to prepare for the model one or several sequences(s). This method forwards the `text` and `kwargs` arguments to the AutoTokenizer's [`~AutoTokenizer.__call__`] to encode the text. The method also proposes a voice preset which is a dictionary of arrays that conditions `Bark`'s output. `kwargs` arguments are forwarded to the tokenizer and to `cached_file` method if `voice_preset` is a valid filename. Args: text (`str`, `List[str]`, `List[List[str]]`): The sequence or batch of sequences to be encoded. Each sequence can be a string or a list of strings (pretokenized string). If the sequences are provided as list of strings (pretokenized), you must set `is_split_into_words=True` (to lift the ambiguity with a batch of sequences). voice_preset (`str`, `Dict[np.ndarray]`): The voice preset, i.e the speaker embeddings. It can either be a valid voice_preset name, e.g `"en_speaker_1"`, or directly a dictionary of `np.ndarray` embeddings for each submodel of `Bark`. Or it can be a valid file name of a local `.npz` single voice preset. return_tensors (`str` or [`~utils.TensorType`], *optional*): If set, will return tensors of a particular framework. Acceptable values are: - `'pt'`: Return PyTorch `torch.Tensor` objects. - `'np'`: Return NumPy `np.ndarray` objects. Returns: Tuple([`BatchEncoding`], [`BatchFeature`]): A tuple composed of a [`BatchEncoding`], i.e the output of the `tokenizer` and a [`BatchFeature`], i.e the voice preset with the right tensors type. z.npz)data tensor_type max_length)return_tensorspaddingrjreturn_attention_maskreturn_token_type_idsadd_special_tokenshistory_prompt) r^dictrarrGendswithrHr5rerr) rtextrPrkrjrormrnr: encoded_texts r__call__BarkProcessor.__call__sH  #J|T,J,J<--++7 $;$;;#66|D lC009N9Nv9V9V#/L!ww|4  #  , ,\ DV D'\VL~~   ) !"7"71      #-9) *r)rr)speaker_embeddings_path.json)rwrF)NNptFTF)__name__ __module__ __qualname____firstlineno____doc__tokenizer_class attributesrbr classmethodr6boolrKrrarGrqreru__static_attributes__ __classcell__)rs@rr r #s &OJL 5 Mk5O5Ot&D%9! 7G  7G7Gr"!x}"!H j j "#DDrr )r~r4r0typingrnumpyrHfeature_extraction_utilsrprocessing_utilsrutilsr utils.hubrautor get_loggerrzr.r __all__rrrsR 4.$    H %BNBJ  r