Hugging Face's logo

Transformers documentation

PP-OCRv5_server_rec

You are viewing main version, which requires installation from source. If you'd like regular pip install, checkout the latest stable version (v5.3.0).
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 2025-05-20 and added to Hugging Face Transformers on 2026-03-18.

PP-OCRv5_server_rec

PyTorch

Overview

PP-OCRv5_server_rec is a dedicated lightweight model for text recognition, focusing specifically on efficient recognition and understanding of text elements in multi-language documents and natural scenes.

Model Architecture

PP-OCRv5_server_rec is one of the PP-OCRv5_rec series, the latest generation of text recognition models developed by the PaddleOCR team. It is designed to efficiently and accurately support the recognition of Simplified Chinese, Traditional Chinese, English, Japanese, as well as complex text scenarios such as handwriting, vertical text, pinyin, and rare characters with a single model. While maintaining recognition performance, it also balances inference speed and model robustness, providing efficient and accurate technical support for document understanding in various scenarios.

Usage

Single input inference

The example below demonstrates how to detect text with PP-OCRv5_server_rec using the AutoModel.

AutoModel 
import requests
from PIL import Image
from transformers import AutoImageProcessor, AutoModelForTextRecognition

model_path="PaddlePaddle/PP-OCRv5_server_rec_safetensors"
model = AutoModelForTextRecognition.from_pretrained(model_path, device_map="auto")
image_processor = AutoImageProcessor.from_pretrained(model_path)

image = Image.open(requests.get("https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_ocr_rec_001.png", stream=True).raw).convert("RGB")
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-OCRv5_server_rec using the AutoModel:

AutoModel 
import requests
from PIL import Image
from transformers import AutoImageProcessor, AutoModelForTextRecognition

model_path = "PaddlePaddle/PP-OCRv5_server_rec_safetensors"
model = AutoModelForTextRecognition.from_pretrained(model_path, device_map="auto")
image_processor = AutoImageProcessor.from_pretrained(model_path)

image = Image.open(requests.get("https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_ocr_rec_001.png", stream=True).raw).convert("RGB")
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)

PPOCRV5ServerRecForTextRecognition

class transformers.PPOCRV5ServerRecForTextRecognition

< >

( config: PPOCRV5ServerRecConfig )

Parameters

  • config (PPOCRV5ServerRecConfig) — 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.

PPOCRV5ServerRec 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

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 (PPOCRV5ServerRecConfig) and inputs.

The PPOCRV5ServerRecForTextRecognition 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.

PPOCRV5ServerRecConfig

class transformers.PPOCRV5ServerRecConfig

< >

( 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 tokenizer_class: str | None = 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 = 18385 conv_kernel_size: list | None = None qkv_bias: bool = True num_attention_heads: int = 8 attention_dropout: float = 0.0 layer_norm_eps: float = 1e-06 )

Parameters

  • output_hidden_states (bool, optional, defaults to False) — Whether or not the model should return all hidden-states.
  • return_dict (bool, optional, defaults to True) — Whether to return a ModelOutput (dataclass) instead of a plain tuple.
  • dtype (Union[str, torch.dtype], optional) — The chunk size of all feed forward layers in the residual attention blocks. A chunk size of 0 means that the feed forward layer is not chunked. A chunk size of n means that the feed forward layer processes n < sequence_length embeddings at a time. For more information on feed forward chunking, see How does Feed Forward Chunking work?.
  • chunk_size_feed_forward (int, optional, defaults to 0) — The dtype of the weights. This attribute can be used to initialize the model to a non-default dtype (which is normally float32) and thus allow for optimal storage allocation. For example, if the saved model is float16, ideally we want to load it back using the minimal amount of memory needed to load float16 weights.
  • is_encoder_decoder (bool, optional, defaults to False) — Whether the model is used as an encoder/decoder or not.
  • id2label (Union[dict[int, str], dict[str, str]], optional) — A map from index (for instance prediction index, or target index) to label.
  • label2id (Union[dict[str, int], dict[str, str]], optional) — A map from label to index for the model.
  • problem_type (Literal[regression, single_label_classification, multi_label_classification], optional) — Problem type for XxxForSequenceClassification models. Can be one of "regression", "single_label_classification" or "multi_label_classification".
  • tokenizer_class (str, optional) — The class name of model’s tokenizer.
  • 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 18385) — The number of output channels from the PPOCRV5ServerRecHead, 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 (float, 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 PPOCRV5ServerRecModel. It is used to instantiate a Pp Ocrv5 Server 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-OCRv5_server_rec_safetensors

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

PPOCRV5ServerRecModel

class transformers.PPOCRV5ServerRecModel

< >

( config: PPOCRV5ServerRecConfig )

Parameters

  • config (PPOCRV5ServerRecConfig) — 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.

PPOCRV5ServerRec 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

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 (PPOCRV5ServerRecConfig) and inputs.

The PPOCRV5ServerRecModel 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.

PPOCRV5ServerRecEncoderWithSVTR

class transformers.PPOCRV5ServerRecEncoderWithSVTR

< >

( 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

PPOCRV5MobileRecEncoderWithSVTR

class transformers.PPOCRV5MobileRecEncoderWithSVTR

< >

( 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

PPOCRV5ServerRecImageProcessorFast

class transformers.PPOCRV5ServerRecImageProcessorFast

< >

( **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 PPOCRV5ServerRecImageProcessorFast 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-OCRv5_server_det PPLCNet→