g3dZddlZddlZddlmZddlZddlmZddl m Z ddl m Z ddl mZd d lmZe jeZGd d e ZdS) z Processor class for Bark N)Optional) BatchFeature)ProcessorMixin)logging)get_file_from_repo) AutoTokenizerceZdZdZdZdgZddddZdfd Ze dd Z dd e ffd Z dde fdZ ddeefdZ ddZxZS) BarkProcessora  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_promptNcXt|||_dSN)super__init__speaker_embeddings)selfr r __class__s d/var/www/html/ai-engine/env/lib/python3.11/site-packages/transformers/models/bark/processing_bark.pyrzBarkProcessor.__init__<s) ###"4speaker_embeddings_path.jsonc |6t|||dd|dd|dd|dd|dd|dd|d d|d d }|?td tj||d d}n>t|5}tj |}dddn #1swxYwYnd}tj |fi|}|||S)a 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 dictionnary 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_tokenrevisionrrr r!r"r#tokenr%`z` does not exists , no preloaded speaker embeddings will be used - Make sure to provide a correct path to the json dictionnary if wanted, otherwise set `speaker_embeddings_dict_path=None`.)r r) rpoploggerwarningospathjoinopenjsonloadr from_pretrained)cls!pretrained_processor_name_or_pathspeaker_embeddings_dict_pathkwargsspeaker_embeddings_pathrspeaker_embeddings_jsonr s rr2zBarkProcessor.from_pretrainedAs. ( 3&81, **[$77 **[$77%zz*:EBB 9d33 & +!F!Fjj!1488J55 ' ' ' #'.a"',,'HIeffaaa &*""122L6M)-3J)K)K&LLLLLLLLLLLLLLL"& !12S^^W]^^ sY;MNNNNs D..D25D2rF push_to_hubc |jCtjtj||ddi}||d<|jD]}|dkr||}i} |j|D]r} t jtj|d||d| || dtj||d| d | | <s| ||<ttj||d 5} tj || dddn #1swxYwYtj ||fi|dS) a} Saves the attributes of this processor (tokenizer...) in the specified directory so that it can be reloaded using the [`~BarkProcessor.from_pretrained`] method. Args: save_directory (`str` or `os.PathLike`): Directory where the tokenizer files and the speaker embeddings will be saved (directory will be created if it does not exist). speaker_embeddings_dict_path (`str`, *optional*, defaults to `"speaker_embeddings_path.json"`): The name of the `.json` file that will contains the speaker_embeddings nested path dictionnary, if it exists, and that will be located in `pretrained_model_name_or_path/speaker_embeddings_directory`. speaker_embeddings_directory (`str`, *optional*, defaults to `"speaker_embeddings/"`): The name of the folder in which the speaker_embeddings arrays will be saved. push_to_hub (`bool`, *optional*, defaults to `False`): Whether or not to push your model to the Hugging Face model hub after saving it. You can specify the repository you want to push to with `repo_id` (will default to the name of `save_directory` in your namespace). kwargs: Additional key word arguments passed along to the [`~utils.PushToHubMixin.push_to_hub`] method. Nv2T)exist_ok repo_or_path_F) allow_picklez.npyw) rr,makedirsr-r._load_voice_presetnpsaver/r0dumprsave_pretrained) rsave_directoryr5speaker_embeddings_directoryr9r6embeddings_dict prompt_key voice_presettmp_dictkeyfprs rrFzBarkProcessor.save_pretrainedvs8  " . K ^5QSWXXcg h h h h O.3OPPRUVV /Z\ /2... / / / / / / / / / / / / / / /  FFvFFFFFs EE ErKc |j|}i}dD]a}||vrtd|d|dt|jdd|||dd|dd|d d |d d|d d|d d |dd|dd }|Stdt j|jdd||d|dtj |||<c|S)Nr#Voice preset unrecognized, missing z% as a key in self.speaker_embeddings[z].r=/rrr Fr!r"r#r$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)r,r-r.rCr1)rrKr6voice_preset_pathsvoice_preset_dictrMr-s rrBz BarkProcessor._load_voice_presets!4\BF 3 3C,,, t#ttdpttt&'++NC@@"3' **[$77 **[$77%zz*:EBB 9d33 & +!F!Fjj!1488J55   D| #"',,t'>'B'B>SV'W'WXjknXopp##jv### &(WT]] c " "  rc dD]}||vrtd|dt||tjs-t |dt |j|dt||j|j|kr-t|dt |j|ddS)NrrPz as a key.z voice preset must be a z D ndarray.) rR isinstancerCndarray TypeErrorstr preset_shapelenshape)rrKrMs r_validate_voice_preset_dictz)BarkProcessor._validate_voice_preset_dictsF j jC,&& !Vs!V!V!VWWWl3/<< i3 g gDDUVYDZ@[@[ g g ghhh<$*++t/@/EEE C!h!hTEVWZE[A\A\!h!h!hiiiF j jrptTc |t|ts~t|tr&|j||jvr||}nCt|tr|ds|dz}t j|}||j|fi|t||}|j |f|d||||d|} ||| d<| S)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 dictionnary 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. Nz.npz)data tensor_type max_length)return_tensorspaddingrdreturn_attention_maskreturn_token_type_idsadd_special_tokenshistory_prompt) rWdictrZrrBendswithrCr1r^rr ) rtextrKrerdrirgrhr6 encoded_texts r__call__zBarkProcessor.__call__s"H  #J|T,J,J #<-- 5+7 D$;;;#66|DD lC0099N9Nv9V9V9#/L!w|44  # ,D ,\ D DV D D D'\~VVVL%t~   ) !"7"71        #-9L) *rr)r)rrF)NNr_r`FTF)__name__ __module__ __qualname____doc__tokenizer_class attributesr[r classmethodr2boolrFrZrBrrkr^ro __classcell__)rs@rr r #sT  &OJL 555555 Mk2O2O2O[2On&D%9! 7G7G  7G7G7G7G7G7Gr!!s!!!!B j j j j j j "#DDDDDDDDrr )rsr0r,typingrnumpyrCfeature_extraction_utilsrprocessing_utilsrutilsr utils.hubrautor get_loggerrpr*r rrrs 444444......++++++   H % %|||||N|||||r