Transformers documentation
PP-OCRv6_tiny_rec
This model was contributed to Hugging Face Transformers on 2026-05-19.
PP-OCRv6_tiny_rec
Overview
PP-OCRv6_tiny_rec is the most lightweight recognition model in the PP-OCRv6 series. It uses LCNetV4 as the backbone with a direct reshape projection instead of an encoder neck, and a CTC+NRTR multi-head decoder. The model supports 49 languages and contains 1.1M parameters.
Model Architecture
Usage
Single input inference
The example below demonstrates how to detect text with PP-OCRv6_tiny_rec using the AutoModel.
from io import BytesIO
import httpx
from PIL import Image
from transformers import AutoImageProcessor, AutoModelForTextRecognition
from transformers.image_utils import load_image
model_path = "PaddlePaddle/PP-OCRv6_tiny_rec_safetensors"
model = AutoModelForTextRecognition.from_pretrained(model_path, device_map="auto")
image_processor = AutoImageProcessor.from_pretrained(model_path)
image_url = "https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_ocr_rec_001.png"
image = load_image(image_url)
inputs = image_processor(images=image, return_tensors="pt").to(model.device)
outputs = model(**inputs)
results = image_processor.post_process_text_recognition(outputs)
for result in results:
print(result)Batched inference
Here is how you can do it with PP-OCRv6_tiny_rec using the AutoModel:
from io import BytesIO
import httpx
from PIL import Image
from transformers import AutoImageProcessor, AutoModelForTextRecognition
from transformers.image_utils import load_image
model_path = "PaddlePaddle/PP-OCRv6_tiny_rec_safetensors"
model = AutoModelForTextRecognition.from_pretrained(model_path, device_map="auto")
image_processor = AutoImageProcessor.from_pretrained(model_path)
image_url = "https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_ocr_rec_001.png"
image = load_image(image_url)
inputs = image_processor(images=[image, image], return_tensors="pt").to(model.device)
outputs = model(**inputs)
results = image_processor.post_process_text_recognition(outputs)
for result in results:
print(result)PPOCRV6TinyRecForTextRecognition
class transformers.PPOCRV6TinyRecForTextRecognition
< source >( config: PPOCRV6TinyRecConfig )
Parameters
- config (PPOCRV6TinyRecConfig) — Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the from_pretrained() method to load the model weights.
PPOCR6TinyRec model for text recognition tasks.
This model inherits from PreTrainedModel. Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.)
This model is also a PyTorch torch.nn.Module subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.
forward
< source >( pixel_values: FloatTensor**kwargs: Unpack ) → BaseModelOutputWithNoAttention or tuple(torch.FloatTensor)
Parameters
- pixel_values (
torch.FloatTensorof shape(batch_size, num_channels, image_size, image_size)) — The tensors corresponding to the input images. Pixel values can be obtained using PPOCRV6SmallRecImageProcessor. SeePPOCRV6SmallRecImageProcessor.__call__()for details (processor_classuses PPOCRV6SmallRecImageProcessor for processing images).
Returns
BaseModelOutputWithNoAttention or tuple(torch.FloatTensor)
A BaseModelOutputWithNoAttention or a tuple of
torch.FloatTensor (if return_dict=False is passed or when config.return_dict=False) comprising various
elements depending on the configuration (PPOCRV6TinyRecConfig) and inputs.
The PPOCRV6TinyRecForTextRecognition forward method, overrides the __call__ special method.
Although the recipe for forward pass needs to be defined within this function, one should call the
Moduleinstance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.
last_hidden_state (
torch.FloatTensorof shape(batch_size, num_channels, height, width)) — Sequence of hidden-states at the output of the last layer of the model.hidden_states (
tuple(torch.FloatTensor), optional, returned whenoutput_hidden_states=Trueis passed or whenconfig.output_hidden_states=True) — Tuple oftorch.FloatTensor(one for the output of the embeddings, if the model has an embedding layer, + one for the output of each layer) of shape(batch_size, num_channels, height, width).Hidden-states of the model at the output of each layer plus the optional initial embedding outputs.
PPOCRV6TinyRecConfig
class transformers.PPOCRV6TinyRecConfig
< source >( transformers_version: str | None = Nonearchitectures: list[str] | None = Noneoutput_hidden_states: bool | None = Falsereturn_dict: bool | None = Truedtype: typing.Union[str, ForwardRef('torch.dtype'), NoneType] = Nonechunk_size_feed_forward: int = 0is_encoder_decoder: bool = Falseid2label: dict[int, str] | dict[str, str] | None = Nonelabel2id: dict[str, int] | dict[str, str] | None = Noneproblem_type: typing.Optional[typing.Literal['regression', 'single_label_classification', 'multi_label_classification']] = Nonebackbone_config: dict | transformers.configuration_utils.PreTrainedConfig | None = Nonehidden_size: int = 120head_out_channels: int = 6625 )
Parameters
- backbone_config (
Union[dict, ~configuration_utils.PreTrainedConfig], optional) — The configuration of the backbone model. - hidden_size (
int, optional, defaults to120) — Dimension of the hidden representations. - head_out_channels (
int, optional, defaults to 18714) — The number of output channels from the PPOCRV6TinyRecHead, responsible for final classification.
This is the configuration class to store the configuration of a PPOCRV6TinyRecModel. It is used to instantiate a Pp Ocrv6 Tiny Rec model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the PaddlePaddle/PP-OCRv6_tiny_rec_safetensors
Configuration objects inherit from PreTrainedConfig and can be used to control the model outputs. Read the documentation from PreTrainedConfig for more information.
PPOCRV6TinyRecModel
class transformers.PPOCRV6TinyRecModel
< source >( config: PPOCRV6TinyRecConfig )
Parameters
- config (PPOCRV6TinyRecConfig) — Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the from_pretrained() method to load the model weights.
PPOCRV6TinyRec model, consisting of Backbone and Head networks.
This model inherits from PreTrainedModel. Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.)
This model is also a PyTorch torch.nn.Module subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.
forward
< source >( pixel_values: FloatTensor**kwargs: Unpack ) → BaseModelOutputWithNoAttention or tuple(torch.FloatTensor)
Parameters
- pixel_values (
torch.FloatTensorof shape(batch_size, num_channels, image_size, image_size)) — The tensors corresponding to the input images. Pixel values can be obtained using PPOCRV6SmallRecImageProcessor. SeePPOCRV6SmallRecImageProcessor.__call__()for details (processor_classuses PPOCRV6SmallRecImageProcessor for processing images).
Returns
BaseModelOutputWithNoAttention or tuple(torch.FloatTensor)
A BaseModelOutputWithNoAttention or a tuple of
torch.FloatTensor (if return_dict=False is passed or when config.return_dict=False) comprising various
elements depending on the configuration (PPOCRV6TinyRecConfig) and inputs.
The PPOCRV6TinyRecModel forward method, overrides the __call__ special method.
Although the recipe for forward pass needs to be defined within this function, one should call the
Moduleinstance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.
last_hidden_state (
torch.FloatTensorof shape(batch_size, num_channels, height, width)) — Sequence of hidden-states at the output of the last layer of the model.hidden_states (
tuple(torch.FloatTensor), optional, returned whenoutput_hidden_states=Trueis passed or whenconfig.output_hidden_states=True) — Tuple oftorch.FloatTensor(one for the output of the embeddings, if the model has an embedding layer, + one for the output of each layer) of shape(batch_size, num_channels, height, width).Hidden-states of the model at the output of each layer plus the optional initial embedding outputs.
PPOCRV6SmallRecImageProcessor
class transformers.PPOCRV6SmallRecImageProcessor
< source >( **kwargs: Unpack )
Parameters
- do_convert_rgb (
bool, kwargs, optional, defaults toTrue) — Whether to convert the image to RGB. - do_resize (
bool, kwargs, optional, defaults toTrue) — Whether to resize the image. - size (
Annotated[int | list[int] | tuple[int, ...] | dict[str, int] | None, None], kwargs, defaults to{'height' -- 48, 'width': 320}): Describes the maximum input dimensions to the model. - default_to_square (
bool, kwargs, optional, defaults toTrue) — Whether to default to a square image when resizing, if size is an int. - crop_size (
Annotated[int | list[int] | tuple[int, ...] | dict[str, int] | None, None], kwargs) — Size of the output image after applyingcenter_crop. - resample (
Annotated[Union[int, PILImageResampling, NoneType], None], kwargs, defaults toResampling.BILINEAR) — Resampling filter to use if resizing the image. This can be one of the enumPILImageResampling. Only has an effect ifdo_resizeis set toTrue. - do_rescale (
bool, kwargs, optional, defaults toTrue) — Whether to rescale the image. - rescale_factor (
float, kwargs, optional, defaults to0.00392156862745098) — Rescale factor to rescale the image by ifdo_rescaleis set toTrue. - do_normalize (
bool, kwargs, optional, defaults toTrue) — Whether to normalize the image. - image_mean (
Union[float, list[float], tuple[float, ...]], kwargs, optional, defaults to[0.5, 0.5, 0.5]) — Image mean to use for normalization. Only has an effect ifdo_normalizeis set toTrue. - image_std (
Union[float, list[float], tuple[float, ...]], kwargs, optional, defaults to[0.5, 0.5, 0.5]) — Image standard deviation to use for normalization. Only has an effect ifdo_normalizeis set toTrue. - do_pad (
bool, kwargs, optional, defaults toTrue) — Whether to pad the image. Padding is done either to the largest size in the batch or to a fixed square size per image. The exact padding strategy depends on the model. - pad_size (
Annotated[int | list[int] | tuple[int, ...] | dict[str, int] | None, None], kwargs, defaults to{'height' -- 48, 'width': 320}): The size in{"height": int, "width" int}to pad the images to. Must be larger than any image size provided for preprocessing. Ifpad_sizeis not provided, images will be padded to the largest height and width in the batch. Applied only whendo_pad=True. - do_center_crop (
bool, kwargs, optional) — Whether to center crop the image. - data_format (
Union[str, ~image_utils.ChannelDimension], kwargs, optional) — OnlyChannelDimension.FIRSTis supported. Added for compatibility with slow processors. - input_data_format (
Union[str, ~image_utils.ChannelDimension], kwargs, optional) — The channel dimension format for the input image. If unset, the channel dimension format is inferred from the input image. Can be one of:"channels_first"orChannelDimension.FIRST: image in (num_channels, height, width) format."channels_last"orChannelDimension.LAST: image in (height, width, num_channels) format."none"orChannelDimension.NONE: image in (height, width) format.
- device (
Annotated[Union[str, torch.device, NoneType], None], kwargs) — The device to process the videos on. If unset, the device is inferred from the input videos. - return_tensors (
Annotated[str | ~utils.generic.TensorType | None, None], kwargs) — Returns stacked tensors if set to'pt', otherwise returns a list of tensors. - disable_grouping (
bool, kwargs, optional) — Whether to disable grouping of images by size to process them individually and not in batches. If None, will be set to True if the images are on CPU, and False otherwise. This choice is based on empirical observations, as detailed here: https://github.com/huggingface/transformers/pull/38157 - image_seq_length (
int, kwargs, optional) — The number of image tokens to be used for each image in the input. Added for backward compatibility but this should be set as a processor attribute in future models. Returns stacked tensors if set to'pt', otherwise returns a list of tensors. - disable_grouping (
bool, kwargs, optional) — Whether to disable grouping of images by size to process them individually and not in batches. If None, will be set to True if the images are on CPU, and False otherwise. This choice is based on empirical observations, as detailed here: https://github.com/huggingface/transformers/pull/38157 - image_seq_length (
int, kwargs, optional) — The number of image tokens to be used for each image in the input. Added for backward compatibility but this should be set as a processor attribute in future models. Returns stacked tensors if set to'pt', otherwise returns a list of tensors. - disable_grouping (
bool, kwargs, optional) — Whether to disable grouping of images by size to process them individually and not in batches. If None, will be set to True if the images are on CPU, and False otherwise. This choice is based on empirical observations, as detailed here: https://github.com/huggingface/transformers/pull/38157 - image_seq_length (
int, kwargs, optional) — The number of image tokens to be used for each image in the input. Added for backward compatibility but this should be set as a processor attribute in future models. Returns stacked tensors if set to'pt', otherwise returns a list of tensors. - disable_grouping (
bool, kwargs, optional) — Whether to disable grouping of images by size to process them individually and not in batches. If None, will be set to True if the images are on CPU, and False otherwise. This choice is based on empirical observations, as detailed here: https://github.com/huggingface/transformers/pull/38157 - image_seq_length (
int, kwargs, optional) — The number of image tokens to be used for each image in the input. Added for backward compatibility but this should be set as a processor attribute in future models. Returns stacked tensors if set to'pt', otherwise returns a list of tensors. - disable_grouping (
bool, kwargs, optional) — Whether to disable grouping of images by size to process them individually and not in batches. If None, will be set to True if the images are on CPU, and False otherwise. This choice is based on empirical observations, as detailed here: https://github.com/huggingface/transformers/pull/38157 - image_seq_length (
int, kwargs, optional) — The number of image tokens to be used for each image in the input. Added for backward compatibility but this should be set as a processor attribute in future models. Returns stacked tensors if set to'pt', otherwise returns a list of tensors. - disable_grouping (
bool, kwargs, optional) — Whether to disable grouping of images by size to process them individually and not in batches. If None, will be set to True if the images are on CPU, and False otherwise. This choice is based on empirical observations, as detailed here: https://github.com/huggingface/transformers/pull/38157 - image_seq_length (
int, kwargs, optional) — The number of image tokens to be used for each image in the input. Added for backward compatibility but this should be set as a processor attribute in future models. Returns stacked tensors if set to'pt', otherwise returns a list of tensors. - disable_grouping (
bool, kwargs, optional) — Whether to disable grouping of images by size to process them individually and not in batches. If None, will be set to True if the images are on CPU, and False otherwise. This choice is based on empirical observations, as detailed here: https://github.com/huggingface/transformers/pull/38157 - image_seq_length (
int, kwargs, optional) — The number of image tokens to be used for each image in the input. Added for backward compatibility but this should be set as a processor attribute in future models. Returns stacked tensors if set to'pt', otherwise returns a list of tensors. - disable_grouping (
bool, kwargs, optional) — Whether to disable grouping of images by size to process them individually and not in batches. If None, will be set to True if the images are on CPU, and False otherwise. This choice is based on empirical observations, as detailed here: https://github.com/huggingface/transformers/pull/38157 - image_seq_length (
int, kwargs, optional) — The number of image tokens to be used for each image in the input. Added for backward compatibility but this should be set as a processor attribute in future models. Returns stacked tensors if set to'pt', otherwise returns a list of tensors. - disable_grouping (
bool, kwargs, optional) — Whether to disable grouping of images by size to process them individually and not in batches. If None, will be set to True if the images are on CPU, and False otherwise. This choice is based on empirical observations, as detailed here: https://github.com/huggingface/transformers/pull/38157 - image_seq_length (
int, kwargs, optional) — The number of image tokens to be used for each image in the input. Added for backward compatibility but this should be set as a processor attribute in future models. Returns stacked tensors if set to'pt', otherwise returns a list of tensors. - disable_grouping (
bool, kwargs, optional) — Whether to disable grouping of images by size to process them individually and not in batches. If None, will be set to True if the images are on CPU, and False otherwise. This choice is based on empirical observations, as detailed here: https://github.com/huggingface/transformers/pull/38157 - image_seq_length (
int, kwargs, optional) — The number of image tokens to be used for each image in the input. Added for backward compatibility but this should be set as a processor attribute in future models. Returns stacked tensors if set to'pt', otherwise returns a list of tensors. - disable_grouping (
bool, kwargs, optional) — Whether to disable grouping of images by size to process them individually and not in batches. If None, will be set to True if the images are on CPU, and False otherwise. This choice is based on empirical observations, as detailed here: https://github.com/huggingface/transformers/pull/38157 - image_seq_length (
int, kwargs, optional) — The number of image tokens to be used for each image in the input. Added for backward compatibility but this should be set as a processor attribute in future models. Returns stacked tensors if set to'pt', otherwise returns a list of tensors. - disable_grouping (
bool, kwargs, optional) — Whether to disable grouping of images by size to process them individually and not in batches. If None, will be set to True if the images are on CPU, and False otherwise. This choice is based on empirical observations, as detailed here: https://github.com/huggingface/transformers/pull/38157 - image_seq_length (
int, kwargs, optional) — The number of image tokens to be used for each image in the input. Added for backward compatibility but this should be set as a processor attribute in future models. Returns stacked tensors if set to'pt', otherwise returns a list of tensors. - disable_grouping (
bool, kwargs, optional) — Whether to disable grouping of images by size to process them individually and not in batches. If None, will be set to True if the images are on CPU, and False otherwise. This choice is based on empirical observations, as detailed here: https://github.com/huggingface/transformers/pull/38157 - image_seq_length (
int, kwargs, optional) — The number of image tokens to be used for each image in the input. Added for backward compatibility but this should be set as a processor attribute in future models. Returns stacked tensors if set to'pt', otherwise returns a list of tensors. - disable_grouping (
bool, kwargs, optional) — Whether to disable grouping of images by size to process them individually and not in batches. If None, will be set to True if the images are on CPU, and False otherwise. This choice is based on empirical observations, as detailed here: https://github.com/huggingface/transformers/pull/38157 - image_seq_length (
int, kwargs, optional) — The number of image tokens to be used for each image in the input. Added for backward compatibility but this should be set as a processor attribute in future models. Returns stacked tensors if set to'pt', otherwise returns a list of tensors. - disable_grouping (
bool, kwargs, optional) — Whether to disable grouping of images by size to process them individually and not in batches. If None, will be set to True if the images are on CPU, and False otherwise. This choice is based on empirical observations, as detailed here: https://github.com/huggingface/transformers/pull/38157 - image_seq_length (
int, kwargs, optional) — The number of image tokens to be used for each image in the input. Added for backward compatibility but this should be set as a processor attribute in future models. Returns stacked tensors if set to'pt', otherwise returns a list of tensors. - disable_grouping (
bool, kwargs, optional) — Whether to disable grouping of images by size to process them individually and not in batches. If None, will be set to True if the images are on CPU, and False otherwise. This choice is based on empirical observations, as detailed here: https://github.com/huggingface/transformers/pull/38157 - image_seq_length (
int, kwargs, optional) — The number of image tokens to be used for each image in the input. Added for backward compatibility but this should be set as a processor attribute in future models. Returns stacked tensors if set to'pt', otherwise returns a list of tensors. - disable_grouping (
bool, kwargs, optional) — Whether to disable grouping of images by size to process them individually and not in batches. If None, will be set to True if the images are on CPU, and False otherwise. This choice is based on empirical observations, as detailed here: https://github.com/huggingface/transformers/pull/38157 - image_seq_length (
int, kwargs, optional) — The number of image tokens to be used for each image in the input. Added for backward compatibility but this should be set as a processor attribute in future models. Returns stacked tensors if set to'pt', otherwise returns a list of tensors. - disable_grouping (
bool, kwargs, optional) — Whether to disable grouping of images by size to process them individually and not in batches. If None, will be set to True if the images are on CPU, and False otherwise. This choice is based on empirical observations, as detailed here: https://github.com/huggingface/transformers/pull/38157 - image_seq_length (
int, kwargs, optional) — The number of image tokens to be used for each image in the input. Added for backward compatibility but this should be set as a processor attribute in future models. Returns stacked tensors if set to'pt', otherwise returns a list of tensors. - disable_grouping (
bool, kwargs, optional) — Whether to disable grouping of images by size to process them individually and not in batches. If None, will be set to True if the images are on CPU, and False otherwise. This choice is based on empirical observations, as detailed here: https://github.com/huggingface/transformers/pull/38157 - image_seq_length (
int, kwargs, optional) — The number of image tokens to be used for each image in the input. Added for backward compatibility but this should be set as a processor attribute in future models. Returns stacked tensors if set to'pt', otherwise returns a list of tensors. - disable_grouping (
bool, kwargs, optional) — Whether to disable grouping of images by size to process them individually and not in batches. If None, will be set to True if the images are on CPU, and False otherwise. This choice is based on empirical observations, as detailed here: https://github.com/huggingface/transformers/pull/38157 - image_seq_length (
int, kwargs, optional) — The number of image tokens to be used for each image in the input. Added for backward compatibility but this should be set as a processor attribute in future models. Returns stacked tensors if set to'pt', otherwise returns a list of tensors. - disable_grouping (
bool, kwargs, optional) — Whether to disable grouping of images by size to process them individually and not in batches. If None, will be set to True if the images are on CPU, and False otherwise. This choice is based on empirical observations, as detailed here: https://github.com/huggingface/transformers/pull/38157 - image_seq_length (
int, kwargs, optional) — The number of image tokens to be used for each image in the input. Added for backward compatibility but this should be set as a processor attribute in future models. Returns stacked tensors if set to'pt', otherwise returns a list of tensors. - disable_grouping (
bool, kwargs, optional) — Whether to disable grouping of images by size to process them individually and not in batches. If None, will be set to True if the images are on CPU, and False otherwise. This choice is based on empirical observations, as detailed here: https://github.com/huggingface/transformers/pull/38157 - image_seq_length (
int, kwargs, optional) — The number of image tokens to be used for each image in the input. Added for backward compatibility but this should be set as a processor attribute in future models. Returns stacked tensors if set to'pt', otherwise returns a list of tensors. - disable_grouping (
bool, kwargs, optional) — Whether to disable grouping of images by size to process them individually and not in batches. If None, will be set to True if the images are on CPU, and False otherwise. This choice is based on empirical observations, as detailed here: https://github.com/huggingface/transformers/pull/38157 - image_seq_length (
int, kwargs, optional) — The number of image tokens to be used for each image in the input. Added for backward compatibility but this should be set as a processor attribute in future models. Returns stacked tensors if set to'pt', otherwise returns a list of tensors. - disable_grouping (
bool, kwargs, optional) — Whether to disable grouping of images by size to process them individually and not in batches. If None, will be set to True if the images are on CPU, and False otherwise. This choice is based on empirical observations, as detailed here: https://github.com/huggingface/transformers/pull/38157 - image_seq_length (
int, kwargs, optional) — The number of image tokens to be used for each image in the input. Added for backward compatibility but this should be set as a processor attribute in future models. Returns stacked tensors if set to'pt', otherwise returns a list of tensors. - disable_grouping (
bool, kwargs, optional) — Whether to disable grouping of images by size to process them individually and not in batches. If None, will be set to True if the images are on CPU, and False otherwise. This choice is based on empirical observations, as detailed here: https://github.com/huggingface/transformers/pull/38157 - image_seq_length (
int, kwargs, optional) — The number of image tokens to be used for each image in the input. Added for backward compatibility but this should be set as a processor attribute in future models. - Returns stacked tensors if set to
'pt', otherwise returns a list of tensors. —
Constructs a PPOCRV6SmallRecImageProcessor image processor.
disable_grouping (bool, kwargs, optional):
Whether to disable grouping of images by size to process them individually and not in batches.
If None, will be set to True if the images are on CPU, and False otherwise. This choice is based on
empirical observations, as detailed here: https://github.com/huggingface/transformers/pull/38157 image_seq_length (int, kwargs, optional):
The number of image tokens to be used for each image in the input.
Added for backward compatibility but this should be set as a processor attribute in future models.
Calculate the width and height from the widest image in the batch.
post_process_text_recognition
< source >( predictions )
Post-processes raw model logits to decode the recognized text and its confidence score.