+ j<Rt^RIt^RIt^RIt^RIHt^RIHt^RI H t ^RI H t H t ^RIHt^RIHt] P$!]4t] !RR ]44tR .tR#) z Processor class for Bark N) BatchFeature)ProcessorMixin BatchEncoding)auto_docstringlogging) cached_file) AutoTokenizercaa]tRt^"toR^R^R^/tRV3Rllt]RRl4tRV3RlV3Rlllt] V3RlR l4t RV3R lR llt RV3R lR llt ] V3RlRl4tRV3RlRllt]RV3RlRll4tRtVtV;t#) BarkProcessorsemantic_prompt coarse_prompt fine_promptc 2<\SV`V4W nR#)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__s&&&i/home/luca/screen-checking/.venv/lib/python3.14/site-packages/transformers/models/bark/processing_bark.pyrBarkProcessor.__init__*s #"4c VPR4pVe\VVVPRR4VPRR4VPRR4VPRR4VPRR4VVPR R4RRRR 7 pVf:\P R \ P PW4 R 24RpM5\V4;_uu_4p\P!V4pRRR4MRpXe R V9dWR &\P!V3/VBpV!WR7# +'giL?;i)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`]. tokenN subfolder cache_dirforce_downloadFproxieslocal_files_onlyrevision rrrrrrr _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_jsonrs &&&, rr1BarkProcessor.from_pretrained7s;, 7# ' 3&11, **[$7 **[$7%zz*:EB 9d3!',>!FJ5166;8= ' #'."'',,'Hghi]` &*"1226M)-3J)K&32"&   )!335V>2!112S^W]^ YNN32s D.. D> c <V^8dQhRS[/#) push_to_hubbool)format __classdict__s"r __annotate__BarkProcessor.__annotate__qs3G3G  3Grc D<VPEel\P!\PP WR4RR7/pWR&\PP W4pVP FpVP V4p /p VPV,Fp \PP Wx RV 24p VPW|V4\P!WV ,RR7\PP W8 RV R 24W&K WV&K \\PP W4R 4;_uu_4p \P!Wm4RRR4\SV`8!W3/VBR# +'giL#;i) a Saves the attributes of this processor (tokenizer...) in the specified directory so that it can be reloaded using the [`~BarkProcessor.from_pretrained`] method. Args: save_directory (`str` or `os.PathLike`): Directory where the tokenizer files and the speaker embeddings will be saved (directory will be created if it does not exist). speaker_embeddings_dict_path (`str`, *optional*, defaults to `"speaker_embeddings_path.json"`): The name of the `.json` file that will contains the speaker_embeddings nested path dictionary, if it exists, and that will be located in `pretrained_model_name_or_path/speaker_embeddings_directory`. speaker_embeddings_directory (`str`, *optional*, defaults to `"speaker_embeddings/"`): The name of the folder in which the speaker_embeddings arrays will be saved. push_to_hub (`bool`, *optional*, defaults to `False`): Whether or not to push your model to the Hugging Face model hub after saving it. You can specify the repository you want to push to with `repo_id` (will default to the name of `save_directory` in your namespace). kwargs: Additional key word arguments passed along to the [`~utils.PushToHubMixin.push_to_hub`] method. Nv2T)exist_okr&_F) allow_picklez.npyw)rr+makedirsr,r-available_voice_presets_load_voice_preset_reject_path_traversalnpsaver.r/dumprsave_pretrained)rsave_directoryr4speaker_embeddings_directoryr;r5embeddings_dictembeddings_subdir prompt_key voice_presettmp_dictkeytarget_filepathfprs&&&&&, rrOBarkProcessor.save_pretrainedqsT8  " " . KK ^SWXcg h O.>C&(ggll3D TUVYUZF[&\O//0AT^_GGO#->US$&GGLL1MQ]]^_b^ccgOh$iHM ? /7 +;bggll>PRUVVZ\ /.W FvFWVs F F c,<V^8dQhRS[RS[RS[/#)r:base_dir target_pathoffending_valuestr)r>r?s"rr@rAs(PPP3PQTPrc\PPV4p\PPV4p\PPW4.4V8HpV'g\ RV: 24hR# \dRpL(i;i)FzInvalid voice preset path: N)r+r,abspath commonpath ValueError)r\r]r^basetarget containeds&&& rrK$BarkProcessor._reject_path_traversals|wwx(- **D>:dBI:?:MNO O I s#A<< B  B c.<V^8dQhRS[R,/#r:rUNr_)r>r?s"rr@rAs&!&!sTz&!rc PVPV,p/pVPR4pVPPRR4pREF\pWs9d\RV RV R24hVPV\P P WcV,4W7,4\VPPRR4W7,VPRR4VPRR4VPR R 4VPR R4VPR R 4VVPR R4R R R R7 pVfQ\R\P P VPPRR4W7,4 RV R24h\P!V4WG&EK_ V#)rr&/#Voice preset unrecognized, missing z% as a key in self.speaker_embeddings[z].rNrrFrrr r!r%z{` does not exists , no preloaded voice preset will be used - Make sure to provide correct paths to the z embeddings.r r r) rr'rdrKr+r,r-rr(rLr0) rrUr5voice_preset_pathsvoice_preset_dictrr&rWr,s &&, rrJ BarkProcessor._load_voice_presets!44\B 7#..22>3G FC, 9#>cdpcqqst  ' 'bggll!FJ5166;8= D| "'',,t'>'>'B'B>SV'WYkYpqrsjjviwx # &(WWT]  "=G@! rc.<V^8dQhRS[R,/#rj)dict)r>r?s"rr@rAs j jt jrc RFpW!9d\RV R24h\W,\P4'g,\ V R\ VP V,4 R24h\W,P4VP V,8wgK\V R\ VP V,4 R24h R#)r rmz as a key.z voice preset must be a z D ndarray.Nrn) rd isinstancerLndarray TypeErrorr` preset_shapelenshape)rrUrWs&& r_validate_voice_preset_dict)BarkProcessor._validate_voice_preset_dictsFC& #Fse:!VWWl/<<3%'?DDUDUVYDZ@[?\\f ghh<$**+t/@/@/EE C5(@TEVEVWZE[A\@]]g!hiiGrc <V^8dQhRS[/#r:return)list)r>r?s"rr@rAs   rc VPf.#\VPP44pRV9dVPR4V#)ze Returns a list of available voice presets. Returns: `list[str]`: A list of voice preset names. r&)rrkeysremove)r voice_presetss& rrI%BarkProcessor.available_voice_presetssJ  " " *IT4499;< ] *   0rc <V^8dQhRS[/#)r:remove_unavailabler<)r>r?s"rr@rAs>>T>rcv.pVPeVPF&pVPV4pTP T4K( V'd&\ PR\V4 RV R24V'dVFpVPVK R#R#R# \dTP T4Ki;i)NzThe following z' speaker embeddings are not available: zU If you would like to use them, please check the paths or try downloading them again.) rrIrJrdappendr{r)r*ry)rrunavailable_keysrUrps&& r_verify_speaker_embeddings(BarkProcessor._verify_speaker_embeddingss  " " . $ < < (,(?(? (M% 001BC!= $S)9%:$;;bcsbtukk "$4L// =%5"! /"$++L9sBB87B8c <V^8dQhRS[/#r~r)r>r?s"rr@rAs77 7rc Ve\V\4'g\V\4'd1VPe#W P9dVP V4pML\V\4'd!VP R4'g VR,p\ P!V4pVe VP!V3/VB\W#R7pVP!V3RVRRRVRVRVRV/VBp VeW)R &V #) a 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 containing the keys `"semantic_prompt"`, `"coarse_prompt"` and `"fine_prompt"`. Returns: [`BatchEncoding`]: A [`BatchEncoding`] object containing the output of the `tokenizer`. If a voice preset is provided, the returned object will include a `"history_prompt"` key containing a [`BatchFeature`], i.e the voice preset with the right tensors type. z.npz)data tensor_typereturn_tensorspadding max_lengthreturn_attention_maskreturn_token_type_idsadd_special_tokenshistory_prompt) rursr`rrJendswithrLr0r{rr) rtextrUrrrrrr5 encoded_texts &&&&&&&&, r__call__BarkProcessor.__call__s0  #J|T,J,J<--++7 $;$;;#66|D lC009N9Nv9V9V#/L!ww|4  #  , ,\ DV D'\VL~~   )  !  "  #8  #8   2      #-9) *r)r)N)speaker_embeddings_path.json)rrF)T)NNptFTF)__name__ __module__ __qualname____firstlineno__rxr classmethodr1rO staticmethodrKrJr{propertyrIrrr__static_attributes____classdictcell__ __classcell__)rr?s@@rr r "s 1qL 57O7Or3G3GjPP$&!&!P j j  >>.7777rr )__doc__r/r+numpyrLfeature_extraction_utilsrprocessing_utilsrtokenization_utils_baserutilsrr utils.hubrautor get_loggerrr)r __all__rrrsb 4.4,$    H %hNhhV  r