> For the complete documentation index, see [llms.txt](https://boinc-ai.gitbook.io/transformers/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://boinc-ai.gitbook.io/transformers/api/main-classes/auto-classes/autoprocessor.md). # AutoProcessor ### AutoProcessor #### class transformers.AutoProcessor [\](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/auto/processing_auto.py#L118) ( ) This is a generic processor class that will be instantiated as one of the processor classes of the library when created with the [AutoProcessor.from\_pretrained()](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/auto#transformers.AutoProcessor.from_pretrained) class method. This class cannot be instantiated directly using `__init__()` (throws an error). **from\_pretrained** [\](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/auto/processing_auto.py#L132) ( pretrained\_model\_name\_or\_path\*\*kwargs ) Parameters * **pretrained\_model\_name\_or\_path** (`str` or `os.PathLike`) — This can be either: * a string, the *model id* of a pretrained feature\_extractor 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 files saved using the `save_pretrained()` method, e.g., `./my_model_directory/`. * **cache\_dir** (`str` or `os.PathLike`, *optional*) — Path to a directory in which a downloaded pretrained model feature extractor should be cached if the standard cache should not be used. * **force\_download** (`bool`, *optional*, defaults to `False`) — Whether or not to force to (re-)download the feature extractor files and override the cached versions if they exist. * **resume\_download** (`bool`, *optional*, defaults to `False`) — Whether or not to delete incompletely received file. Attempts to resume the download if such a file exists. * **proxies** (`Dict[str, str]`, *optional*) — A dictionary of proxy servers to use by protocol or endpoint, e.g., `{'http': 'foo.bar:3128', 'http://hostname': 'foo.bar:4012'}.` The proxies are used on each request. * **token** (`str` or *bool*, *optional*) — The token to use as HTTP bearer authorization for remote files. If `True`, will use the token generated when running `huggingface-cli login` (stored in `~/.huggingface`). * **revision** (`str`, *optional*, defaults to `"main"`) — The specific model version to use. It can be a branch name, a tag name, or a commit id, since we use a git-based system for storing models and other artifacts on huggingface.co, so `revision` can be any identifier allowed by git. * **return\_unused\_kwargs** (`bool`, *optional*, defaults to `False`) — If `False`, then this function returns just the final feature extractor object. If `True`, then this functions returns a `Tuple(feature_extractor, unused_kwargs)` where *unused\_kwargs* is a dictionary consisting of the key/value pairs whose keys are not feature extractor attributes: i.e., the part of `kwargs` which has not been used to update `feature_extractor` and is otherwise ignored. * **trust\_remote\_code** (`bool`, *optional*, defaults to `False`) — Whether or not to allow for custom models defined on the Hub in their own modeling files. This option should only be set to `True` for repositories you trust and in which you have read the code, as it will execute code present on the Hub on your local machine. * **kwargs** (`Dict[str, Any]`, *optional*) — The values in kwargs of any keys which are feature extractor attributes will be used to override the loaded values. Behavior concerning key/value pairs whose keys are *not* feature extractor attributes is controlled by the `return_unused_kwargs` keyword parameter. Instantiate one of the processor classes of the library from a pretrained model vocabulary. The processor class to instantiate is selected based on the `model_type` property of the config object (either passed as an argument or loaded from `pretrained_model_name_or_path` if possible): * **align** — [AlignProcessor](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/align#transformers.AlignProcessor) (ALIGN model) * **altclip** — [AltCLIPProcessor](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/altclip#transformers.AltCLIPProcessor) (AltCLIP model) * **bark** — [BarkProcessor](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/bark#transformers.BarkProcessor) (Bark model) * **blip** — [BlipProcessor](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/blip#transformers.BlipProcessor) (BLIP model) * **blip-2** — [Blip2Processor](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/blip-2#transformers.Blip2Processor) (BLIP-2 model) * **bridgetower** — [BridgeTowerProcessor](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/bridgetower#transformers.BridgeTowerProcessor) (BridgeTower model) * **chinese\_clip** — [ChineseCLIPProcessor](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/chinese_clip#transformers.ChineseCLIPProcessor) (Chinese-CLIP model) * **clap** — [ClapProcessor](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/clap#transformers.ClapProcessor) (CLAP model) * **clip** — [CLIPProcessor](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/clip#transformers.CLIPProcessor) (CLIP model) * **clipseg** — [CLIPSegProcessor](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/clipseg#transformers.CLIPSegProcessor) (CLIPSeg model) * **flava** — [FlavaProcessor](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/flava#transformers.FlavaProcessor) (FLAVA model) * **git** — [GitProcessor](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/git#transformers.GitProcessor) (GIT model) * **groupvit** — [CLIPProcessor](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/clip#transformers.CLIPProcessor) (GroupViT model) * **hubert** — [Wav2Vec2Processor](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/wav2vec2#transformers.Wav2Vec2Processor) (Hubert model) * **idefics** — [IdeficsProcessor](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/idefics#transformers.IdeficsProcessor) (IDEFICS model) * **instructblip** — [InstructBlipProcessor](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/instructblip#transformers.InstructBlipProcessor) (InstructBLIP model) * **layoutlmv2** — [LayoutLMv2Processor](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/layoutlmv2#transformers.LayoutLMv2Processor) (LayoutLMv2 model) * **layoutlmv3** — [LayoutLMv3Processor](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/layoutlmv3#transformers.LayoutLMv3Processor) (LayoutLMv3 model) * **markuplm** — [MarkupLMProcessor](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/markuplm#transformers.MarkupLMProcessor) (MarkupLM model) * **mctct** — [MCTCTProcessor](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/mctct#transformers.MCTCTProcessor) (M-CTC-T model) * **mgp-str** — [MgpstrProcessor](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/mgp-str#transformers.MgpstrProcessor) (MGP-STR model) * **oneformer** — [OneFormerProcessor](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/oneformer#transformers.OneFormerProcessor) (OneFormer model) * **owlvit** — [OwlViTProcessor](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/owlvit#transformers.OwlViTProcessor) (OWL-ViT model) * **pix2struct** — [Pix2StructProcessor](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/pix2struct#transformers.Pix2StructProcessor) (Pix2Struct model) * **pop2piano** — [Pop2PianoProcessor](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/pop2piano#transformers.Pop2PianoProcessor) (Pop2Piano model) * **sam** — [SamProcessor](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/sam#transformers.SamProcessor) (SAM model) * **sew** — [Wav2Vec2Processor](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/wav2vec2#transformers.Wav2Vec2Processor) (SEW model) * **sew-d** — [Wav2Vec2Processor](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/wav2vec2#transformers.Wav2Vec2Processor) (SEW-D model) * **speech\_to\_text** — [Speech2TextProcessor](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/speech_to_text#transformers.Speech2TextProcessor) (Speech2Text model) * **speech\_to\_text\_2** — [Speech2Text2Processor](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/speech_to_text_2#transformers.Speech2Text2Processor) (Speech2Text2 model) * **speecht5** — [SpeechT5Processor](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/speecht5#transformers.SpeechT5Processor) (SpeechT5 model) * **trocr** — [TrOCRProcessor](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/trocr#transformers.TrOCRProcessor) (TrOCR model) * **tvlt** — [TvltProcessor](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/tvlt#transformers.TvltProcessor) (TVLT model) * **unispeech** — [Wav2Vec2Processor](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/wav2vec2#transformers.Wav2Vec2Processor) (UniSpeech model) * **unispeech-sat** — [Wav2Vec2Processor](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/wav2vec2#transformers.Wav2Vec2Processor) (UniSpeechSat model) * **vilt** — [ViltProcessor](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/vilt#transformers.ViltProcessor) (ViLT model) * **vision-text-dual-encoder** — [VisionTextDualEncoderProcessor](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/vision-text-dual-encoder#transformers.VisionTextDualEncoderProcessor) (VisionTextDualEncoder model) * **wav2vec2** — [Wav2Vec2Processor](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/wav2vec2#transformers.Wav2Vec2Processor) (Wav2Vec2 model) * **wav2vec2-conformer** — [Wav2Vec2Processor](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/wav2vec2#transformers.Wav2Vec2Processor) (Wav2Vec2-Conformer model) * **wavlm** — [Wav2Vec2Processor](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/wav2vec2#transformers.Wav2Vec2Processor) (WavLM model) * **whisper** — [WhisperProcessor](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/whisper#transformers.WhisperProcessor) (Whisper model) * **xclip** — [XCLIPProcessor](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/xclip#transformers.XCLIPProcessor) (X-CLIP model) Passing `token=True` is required when you want to use a private model. Examples: Copied ``` >>> from transformers import AutoProcessor >>> # Download processor from huggingface.co and cache. >>> processor = AutoProcessor.from_pretrained("facebook/wav2vec2-base-960h") >>> # If processor files are in a directory (e.g. processor was saved using *save_pretrained('./test/saved_model/')*) >>> # processor = AutoProcessor.from_pretrained("./test/saved_model/") ``` **register** [\](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/auto/processing_auto.py#L321) ( config\_classprocessor\_classexist\_ok = False ) Parameters * **config\_class** ([PretrainedConfig](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/configuration#transformers.PretrainedConfig)) — The configuration corresponding to the model to register. * **processor\_class** (`FeatureExtractorMixin`) — The processor to register. Register a new processor for this class.