U ,-e4@sdZddlZddlZddlmZddlZddlmZddl m Z ddl m Z ddl mZd d lmZe eZGd d d e ZdS) z Processor class for Bark N)Optional) BatchFeature)ProcessorMixin)logging)get_file_from_repo) AutoTokenizercseZdZdZdZdgZddddZdfdd Zedd d Z de dfdd Z de dddZ d eedddZd!ddZZS)" 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*, defaults to `None`): 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 tokenizerrZsemantic_promptZ coarse_promptZ fine_promptNcst|||_dS)N)super__init__speaker_embeddings)selfr r __class__i/var/www/html/Darija-Ai-Train/env/lib/python3.8/site-packages/transformers/models/bark/processing_bark.pyr:s zBarkProcessor.__init__speaker_embeddings_path.jsoncKs|dk rt|||dd|dd|dd|dd|dd|dd|d d|d dd }|dkrtd tj||d d}qt|}t |}W5QRXnd}t j |f|}|||dS)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. Valid model ids can be located at the root-level, like `bert-base-uncased`, or namespaced under a user or organization name, like `dbmdz/bert-base-german-cased`. - 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_tokenrevisionrrrrrrrr`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)clsZ!pretrained_processor_name_or_pathspeaker_embeddings_dict_pathkwargsZspeaker_embeddings_pathrZspeaker_embeddings_jsonr rrrr*?s.          zBarkProcessor.from_pretrainedrF) push_to_hubc s|jdk rtjtj||dddi}||d<|jD]~}|dkr6||}i} |j|D]P} tjtj|d||d| || ddtj||d| d | | <qZ| ||<q6ttj||d } t || W5QRXt j ||f|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. NZv2T)exist_ok repo_or_path_F)Z allow_picklez.npyw) rr$makedirsr%r&_load_voice_presetnpsaver'r(dumprsave_pretrained) rZsave_directoryr,Zspeaker_embeddings_directoryr.r-Zembeddings_dictZ prompt_key voice_presetZtmp_dictkeyfprrrr8us.      zBarkProcessor.save_pretrained)r9cKs|j|}i}dD]}||kr4td|d|dt|jdd|||dd|dd|d d |d d|d d |d d |dd|ddd }|dkrtdtj|jdd||d|dt |||<q|S)Nr #Voice preset unrecognized, missing z% as a key in self.speaker_embeddings[z].r0/rrrFrrrrrrr z{` does not exists , no preloaded voice preset will be used - Make sure to provide correct paths to the z embeddings.) r ValueErrorrgetr!r$r%r&r5r))rr9r-Zvoice_preset_pathsZvoice_preset_dictr:r%rrrr4s6            z BarkProcessor._load_voice_presetcCsdD]}||kr td|dt||tjsNt|dt|j|dt||j|j|krt|dt|j|dqdS)Nr r<z as a key.z voice preset must be a z D ndarray.)r> isinstancer5Zndarraystr preset_shapelenshape)rr9r:rrr_validate_voice_preset_dictsz)BarkProcessor._validate_voice_preset_dictptTc Ks|dk rbt|tsbt|tr<|jdk r<||jkr<||}n&t|trX|dsX|d}t|}|dk r|j|f|t ||d}|j |f|d||||d|} |dk r|| 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)dataZ tensor_type max_length)return_tensorspaddingrIreturn_attention_maskreturn_token_type_idsadd_special_tokensZhistory_prompt) r@dictrArr4endswithr5r)rErr ) rtextr9rJrIrNrLrMr-Z encoded_textrrr__call__s:$    zBarkProcessor.__call__)N)r)rrF)N)N)NNrFrGFTF)__name__ __module__ __qualname____doc__Ztokenizer_class attributesrBr classmethodr*boolr8rAr4rrOrErR __classcell__rrrrr "s6 89! r )rVr(r$typingrnumpyr5Zfeature_extraction_utilsrZprocessing_utilsrutilsrZ utils.hubrautor Z get_loggerrSr"r rrrrs