o ei7@sdZddlZddlZddlZddlmZddlmZddl m Z ddl m Z m Z ddlmZd d lmZe eZe Gd d d eZd gZdS) z Processor class for Bark N) BatchFeature)ProcessorMixin) BatchEncoding)auto_docstringlogging) cached_file) AutoTokenizercseZdZddddZdfdd Ze d dd Z  d!d effd d Zdde dBfddZ dde dBfddZ e defddZd"defddZe      d#defddZZS)$ BarkProcessorr semantic_prompt coarse_prompt fine_promptNcst|||_dS)a* 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`. N)super__init__speaker_embeddings)self tokenizerr __class__f/home/ubuntu/transcripts/venv/lib/python3.10/site-packages/transformers/models/bark/processing_bark.pyr*s zBarkProcessor.__init__speaker_embeddings_path.jsonc Ks|d}|dur`t|||dd|dd|dd|dd|dd||d ddddd }|durFtd tj||d d}nt| }t |}Wdn1sZwYnd}|durnd |vrn||d <t j |fi|}|||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. - 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`]. tokenN subfolder cache_dirforce_downloadFproxieslocal_files_onlyrevision rrrrr rr! _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`. repo_or_path)rr) getrpoploggerwarningospathjoinopenjsonloadr from_pretrained) cls!pretrained_processor_name_or_pathspeaker_embeddings_dict_pathkwargsrspeaker_embeddings_pathrspeaker_embeddings_jsonrrrrr27s>          zBarkProcessor.from_pretrainedrF push_to_hubc s|jdurwtjtj||dddi}||d<|jD];}||}i} |j|D](} tjtj|d||d| || ddtj||d| d | | <q)| ||<qt tj||d } t || Wdn1srwYt j ||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 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_okr'_F) allow_picklez.npyw)rr,makedirsr-r.available_voice_presets_load_voice_presetnpsaver/r0dumprsave_pretrained) rsave_directoryr5speaker_embeddings_directoryr9r6embeddings_dict prompt_key voice_presettmp_dictkeyfprrrrEqs*     zBarkProcessor.save_pretrainedrJcKs|j|}i}|d}dD]b}||vrtd|d|dt|jdd|||dd|d d|d d |d d|d d ||ddd d d d }|duritdtj|jdd||d|dt |||<q|S)Nrr #Voice preset unrecognized, missing z% as a key in self.speaker_embeddings[z].r'/rrrFrr r!r"r&z{` does not exists , no preloaded voice preset will be used - Make sure to provide correct paths to the z embeddings.) rr( ValueErrorrr)r,r-r.rBr1)rrJr6voice_preset_pathsvoice_preset_dictrrLr-rrrrAs<          z BarkProcessor._load_voice_presetcCsdD]@}||vrtd|dt||tjs't|dt|j|dt||j|j|krBt|dt|j|dqdS)Nr rNz as a key.z voice preset must be a z D ndarray.) rP isinstancerBndarray TypeErrorstr preset_shapelenshape)rrJrLrrr_validate_voice_preset_dictsz)BarkProcessor._validate_voice_preset_dictreturncCs2|jdurgSt|j}d|vr|d|S)z Returns a list of available voice presets. Returns: `list[str]`: A list of voice preset names. Nr')rlistkeysremove)r voice_presetsrrrr@s  z%BarkProcessor.available_voice_presetsTremove_unavailablec Csg}|jdurC|jD]}z||}Wnty!||Yq w||q |r8tdt|d|d|rE|D] }|j|=q  <8$  r )__doc__r0r,numpyrBfeature_extraction_utilsrprocessing_utilsrtokenization_utils_baserutilsrr utils.hubrautor get_loggerrtr*r __all__rrrrs