sg3dZddlZddlZddlmZddlZddlmZddl m Z ddl m Z ddl mZd d lmZe j"eZGd d e Zy) z Processor class for Bark N)Optional) BatchFeature)ProcessorMixin)logging)get_file_from_repo) AutoTokenizerceZdZdZdZdgZddddZdfd Ze ddZ dd e ffd Z dd e fd Z dd eefd Z 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_promptc2t||||_yN)super__init__speaker_embeddings)selfr r __class__s [/var/www/html/venv/lib/python3.12/site-packages/transformers/models/bark/processing_bark.pyrzBarkProcessor.__init__<s #"4c X|t|||jdd|jdd|jdd|jdd|jdd|jdd|jd d|jd d }|:tjd tj j ||d d}n,t|5}tj|}dddnd}tj|fi|}||S#1swY)xYw)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_tokenrevisionrrrr 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 rr1zBarkProcessor.from_pretrainedAs9. ( 3&81, **[$7 **[$7%zz*:EB 9d3 & +!Fjj!148J5 ' #'."'',,'HIefgh^a &*"12L6M)-3J)K&LL"& !112S^W]^ Y;MNNLLs D  D) push_to_hubc |j4tjtjj ||ddi}||d<|jD]}|dk7s |j |}i} |j|D]m} t jtjj |d||d| || dtjj ||d| d | | <o| ||<ttjj ||d 5} tj|| dddt |0||fi|y#1swYxYw) 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.r/dumprsave_pretrained) rsave_directoryr4speaker_embeddings_directoryr8r5embeddings_dict prompt_key voice_presettmp_dictkeyfprs rrEzBarkProcessor.save_pretrainedvsi8  " " . KK ^5QSWXcg h O.3OPRUV /Z\ /2. /  FvF / /s $EErJc |j|}i}dD]2}||vrtd|d|dt|jjdd|||j dd|j dd|j d d |j d d|j d d|j d d |j dd|j dd }|Mtdt j j|jjdd||d|dtj|||<5|S)Nr#Voice preset unrecognized, missing z% as a key in self.speaker_embeddings[z].r</rrrFr r!r"r#r$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-rBr0)rrJr5voice_preset_pathsvoice_preset_dictrLr,s rrAz BarkProcessor._load_voice_presetsm!44\BF 3C,, 9#>cdpcqqst&''++NC@"3' **[$7 **[$7%zz*:EB 9d3 & +!Fjj!148J5 D| "'',,t'>'>'B'B>SV'WXjknXopqrjjviwx # &(WWT] c "3 36! rc ^dD]}||vrtd|dt||tjs't |dt |j |dt||j|j |k7st|dt |j |dy)NrrOz as a key.z voice preset must be a z D ndarray.) rQ isinstancerBndarray TypeErrorstr preset_shapelenshape)rrJrLs r_validate_voice_preset_dictz)BarkProcessor._validate_voice_preset_dictsF jC,& #Fse:!VWWl3/<3%'?DDUDUVYDZ@[?\\f ghh<$**+t/@/@/EE C5(@TEVEVWZE[A\@]]g!hii jrc |t|tswt|tr,|j ||jvr|j |}n;t|tr|j 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. z.npz)data tensor_type max_length)return_tensorspaddingrareturn_attention_maskreturn_token_type_idsadd_special_tokenshistory_prompt) rVdictrYrrAendswithrBr0r]rr ) rtextrJrbrarfrdrer5 encoded_texts r__call__zBarkProcessor.__call__sH  #J|T,J<-++7 D$;$;;#66|D lC09N9Nv9V#/L!ww|4  # ,D , ,\ DV D'\~VL%t~~   ) !"7"71      #-9L) *rr)speaker_embeddings_path.json)rmrF)NNptFTF)__name__ __module__ __qualname____doc__tokenizer_class attributesrZr classmethodr1boolrErYrArrhr]rl __classcell__)rs@rr r #s &OJL 5 Mk2O2On&D%9! 7G  7Gr!s!B j j "#Drr )rsr/r+typingrnumpyrBfeature_extraction_utilsrprocessing_utilsrutilsr utils.hubrautor get_loggerrpr)r rrrsI 4.+    H %|N|r