Hugging Face's logo

Transformers documentation

PP-OCRv6_small_rec

You are viewing main version, which requires installation from source. If you'd like regular pip install, checkout the latest stable version (v5.8.1).
Hugging Face's logo
Join the Hugging Face community

and get access to the augmented documentation experience

to get started

This model was released on 2026-05-19 and added to Hugging Face Transformers on 2026-05-19.

PP-OCRv6_small_rec

PyTorch

Overview

TODO.

Model Architecture

TODO.

Usage

Single input inference

The example below demonstrates how to detect text with PP-OCRv6_small_rec using the AutoModel.

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_small_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_small_rec using the AutoModel:

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_small_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)

PPOCRV6SmallRecForTextRecognition

class transformers.PPOCRV6SmallRecForTextRecognition

< >

( config: PPOCRV6SmallRecConfig )

Parameters

  • config (PPOCRV6SmallRecConfig) — 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.

PPOCR6SmallRec 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

< >

( pixel_values: FloatTensor **kwargs: typing_extensions.Unpack[transformers.utils.generic.TransformersKwargs] ) → BaseModelOutputWithNoAttention or tuple(torch.FloatTensor)

Parameters

  • pixel_values (torch.FloatTensor of shape (batch_size, num_channels, image_size, image_size)) — The tensors corresponding to the input images. Pixel values can be obtained using PPOCRV6SmallRecImageProcessor. See PPOCRV6SmallRecImageProcessor.__call__() for details (processor_class uses 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 (PPOCRV6SmallRecConfig) and inputs.

The PPOCRV6SmallRecForTextRecognition forward method, overrides the __call__ special method.

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance 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.FloatTensor of 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 when output_hidden_states=True is passed or when config.output_hidden_states=True) — Tuple of torch.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.

PPOCRV6SmallRecConfig

class transformers.PPOCRV6SmallRecConfig

< >

( transformers_version: str | None = None architectures: list[str] | None = None output_hidden_states: bool | None = False return_dict: bool | None = True dtype: typing.Union[str, ForwardRef('torch.dtype'), NoneType] = None chunk_size_feed_forward: int = 0 is_encoder_decoder: bool = False id2label: dict[int, str] | dict[str, str] | None = None label2id: dict[str, int] | dict[str, str] | None = None problem_type: typing.Optional[typing.Literal['regression', 'single_label_classification', 'multi_label_classification']] = None hidden_act: str = 'silu' backbone_config: dict | transformers.configuration_utils.PreTrainedConfig | None = None hidden_size: int = 120 mlp_ratio: float = 2.0 depth: int = 2 head_out_channels: int = 18714 conv_kernel_size: list | None = None qkv_bias: bool = True num_attention_heads: int = 8 attention_dropout: float | int = 0.0 layer_norm_eps: float = 1e-06 )

Parameters

  • hidden_act (str, optional, defaults to silu) — The non-linear activation function (function or string) in the decoder. For example, "gelu", "relu", "silu", etc.
  • backbone_config (Union[dict, ~configuration_utils.PreTrainedConfig], optional) — The configuration of the backbone model.
  • hidden_size (int, optional, defaults to 120) — Dimension of the hidden representations.
  • mlp_ratio (float, optional, defaults to 2.0) — Ratio of the MLP hidden dim to the embedding dim.
  • depth (int, optional, defaults to 2) — Number of Transformer layers in the vision encoder.
  • head_out_channels (int, optional, defaults to 18714) — The number of output channels from the PPOCRV6SmallRecHead, responsible for final classification.
  • conv_kernel_size (list, optional) — The size of the convolutional kernel.
  • qkv_bias (bool, optional, defaults to True) — Whether to add a bias to the queries, keys and values.
  • num_attention_heads (int, optional, defaults to 8) — Number of attention heads for each attention layer in the Transformer decoder.
  • attention_dropout (Union[float, int], optional, defaults to 0.0) — The dropout ratio for the attention probabilities.
  • layer_norm_eps (float, optional, defaults to 1e-06) — The epsilon used by the layer normalization layers.

This is the configuration class to store the configuration of a PPOCRV6SmallRecModel. It is used to instantiate a Pp Ocrv6 Small 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_small_rec_safetensors

Configuration objects inherit from PreTrainedConfig and can be used to control the model outputs. Read the documentation from PreTrainedConfig for more information.

PPOCRV6SmallRecModel

class transformers.PPOCRV6SmallRecModel

< >

( config: PPOCRV6SmallRecConfig )

Parameters

  • config (PPOCRV6SmallRecConfig) — 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.

PPOCRV6SmallRec 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

< >

( pixel_values: FloatTensor **kwargs: typing_extensions.Unpack[transformers.utils.generic.TransformersKwargs] ) → BaseModelOutputWithNoAttention or tuple(torch.FloatTensor)

Parameters

  • pixel_values (torch.FloatTensor of shape (batch_size, num_channels, image_size, image_size)) — The tensors corresponding to the input images. Pixel values can be obtained using PPOCRV6SmallRecImageProcessor. See PPOCRV6SmallRecImageProcessor.__call__() for details (processor_class uses 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 (PPOCRV6SmallRecConfig) and inputs.

The PPOCRV6SmallRecModel forward method, overrides the __call__ special method.

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance 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.FloatTensor of 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 when output_hidden_states=True is passed or when config.output_hidden_states=True) — Tuple of torch.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.

PPOCRV6SmallRecEncoderWithSVTR

class transformers.PPOCRV6SmallRecEncoderWithSVTR

< >

( config )

SVTR: Scene Text Recognition with a Single Visual Model https://www.paddleocr.ai/v2.10.0/en/algorithm/text_recognition/algorithm_rec_svtr.html

PPOCRV6SmallRecImageProcessor

class transformers.PPOCRV6SmallRecImageProcessor

< >

( **kwargs: typing_extensions.Unpack[transformers.processing_utils.ImagesKwargs] )

Parameters

  • **kwargs (ImagesKwargs, optional) — Additional image preprocessing options. Model-specific kwargs are listed above; see the TypedDict class for the complete list of supported arguments.

Constructs a PPOCRV6SmallRecImageProcessor image processor.

get_target_size

< >

( shape_list: list )

Calculate the width and height from the widest image in the batch.

post_process_text_recognition

< >

( predictions )

Parameters

  • predictions — Model outputs with logits attribute (probability maps of shape (batch_size, height, vocab_size)).

Post-processes raw model logits to decode the recognized text and its confidence score.

Update on GitHub

←PP-OCRv6_small_det PP-OCRv6_tiny_rec→