JoyCN/PaddleOCR-Pytorch

.
├── README.md / README_zh.md
├── LICENSE                                                 # Apache 2.0
├── config.json                                             # Repo metadata + model index
│
├── ptocr_v5_*.safetensors                                  # 15 PP-OCRv5 weights at root (stable URLs)
├── ptocr_v5_server_{det,rec}.pth                           # Legacy pth copies of V5 server (kept)
│
├── configs/
│   ├── det/PP-OCRv5/
│   │   ├── PP-OCRv5_mobile_det.yml
│   │   └── PP-OCRv5_server_det.yml
│   └── rec/PP-OCRv5/
│       ├── PP-OCRv5_mobile_rec.yml                         # zh / zh-Hant / en / ja
│       ├── PP-OCRv5_server_rec.yml
│       └── multi_language/                                 # 11 multilingual rec yamls
│           ├── en_PP-OCRv5_mobile_rec.yaml
│           ├── korean_PP-OCRv5_mobile_rec.yml
│           ├── latin_PP-OCRv5_mobile_rec.yml               # French / German / Spanish / ...  (40+ Latin-script)
│           ├── eslav_PP-OCRv5_mobile_rec.yml               # Russian / Belarusian / Ukrainian
│           ├── cyrillic_PP-OCRv5_mobile_rec.yaml           # 33 Cyrillic-script languages
│           ├── arabic_PP-OCRv5_mobile_rec.yaml             # Arabic / Persian / Uyghur / Urdu / ...
│           ├── devanagari_PP-OCRv5_mobile_rec.yaml         # Hindi / Marathi / Nepali / Sanskrit / ...
│           ├── th_PP-OCRv5_mobile_rec.yaml                 # Thai
│           ├── el_PP-OCRv5_mobile_rec.yaml                 # Greek
│           ├── ta_PP-OCRv5_mobile_rec.yaml                 # Tamil
│           └── te_PP-OCRv5_mobile_rec.yaml                 # Telugu
│
├── dicts/                                                  # Character set dictionaries (required for rec)
│   ├── ppocrv5_dict.txt                                    # base (zh / zh-Hant / en / ja)
│   └── ppocrv5_<lang>_dict.txt                             # 11 multilingual dicts
│
└── legacy/                                                 # Older PP-OCR v2/v3/v4 weights (kept for back-compat)
    ├── ch_ptocr_mobile_v2.0_cls_infer.pth
    ├── ch_ptocr_v4_det_infer.pth
    ├── ch_ptocr_v4_rec_infer.pth
    ├── en_ptocr_v3_det_infer.pth
    └── en_ptocr_v4_rec_infer.pth

from huggingface_hub import snapshot_download, hf_hub_download

# Option 1: download the whole repo (weights + configs + dicts + README)
repo_dir = snapshot_download(repo_id="JoyCN/PaddleOCR-Pytorch")
print("downloaded to:", repo_dir)

# Option 2: fetch a single weight file
weight_path = hf_hub_download(
    repo_id="JoyCN/PaddleOCR-Pytorch",
    filename="ptocr_v5_korean_mobile_rec.safetensors",
)

# 1. clone the inference code repo
git clone https://github.com/frotms/PaddleOCR2Pytorch
cd PaddleOCR2Pytorch
pip install torch safetensors pyyaml shapely pyclipper opencv-python pillow scikit-image

# 2. Assume you ran snapshot_download above into /path/to/hf_repo
python tools/infer/predict_rec.py \
  --image_dir doc/imgs_words/korean/1.jpg \
  --rec_algorithm SVTR_LCNet \
  --rec_model_path /path/to/hf_repo/ptocr_v5_korean_mobile_rec.safetensors \
  --rec_yaml_path  /path/to/hf_repo/configs/rec/PP-OCRv5/multi_language/korean_PP-OCRv5_mobile_rec.yml \
  --rec_image_shape "3,48,320" \
  --rec_char_dict_path /path/to/hf_repo/dicts/ppocrv5_korean_dict.txt \
  --use_gpu False

import sys, numpy as np, cv2, torch, yaml
from safetensors.torch import load_file

# Requires https://github.com/frotms/PaddleOCR2Pytorch on PYTHONPATH
sys.path.insert(0, "/path/to/PaddleOCR2Pytorch")
from pytorchocr.modeling.architectures.base_model import BaseModel
from pytorchocr.postprocess import build_post_process

HF_REPO = "/path/to/hf_repo"   # the path returned by snapshot_download
yml_path    = f"{HF_REPO}/configs/rec/PP-OCRv5/multi_language/korean_PP-OCRv5_mobile_rec.yml"
weight_path = f"{HF_REPO}/ptocr_v5_korean_mobile_rec.safetensors"

# 1. load config + dictionary
with open(yml_path, encoding="utf-8") as f:
    cfg = yaml.safe_load(f)
dict_path = cfg["Global"]["character_dict_path"]          # './dicts/ppocrv5_korean_dict.txt'
dict_abs  = f"{HF_REPO}/{dict_path.lstrip('./')}"
with open(dict_abs, encoding="utf-8") as f:
    chars = [l.strip("\n\r") for l in f]
n_char = len(chars) + 2                                   # +1 blank, +1 space (if use_space_char)

# 2. build network + load weights (safetensors = zero-code-exec, mmap-fast)
cfg["Architecture"]["Head"]["out_channels_list"] = {
    "CTCLabelDecode": n_char,
    "SARLabelDecode": n_char + 2,
    "NRTRLabelDecode": n_char + 3,
}
net = BaseModel(cfg["Architecture"], out_channels=n_char)
net.load_state_dict(load_file(weight_path, device="cpu"))
net.eval()

# 3. preprocess (resize to [3, 48, 320], normalize to [-1, 1])
img = cv2.imread("input_word.jpg")
h, w = img.shape[:2]
ratio = w / h
tw = min(int(48 * ratio), 320)
img = cv2.resize(img, (tw, 48))
canvas = np.zeros((48, 320, 3), dtype=np.uint8)
canvas[:, :tw] = img
x = canvas.astype(np.float32).transpose(2, 0, 1) / 255.0
x = (x - 0.5) / 0.5
x = torch.from_numpy(x).unsqueeze(0)

# 4. forward + CTC decode
with torch.no_grad():
    logits = net(x)
post_op = build_post_process({
    "name": "CTCLabelDecode",
    "character_dict_path": dict_abs,
    "use_space_char": True,
})
result = post_op(logits)
print("prediction:", result)          # e.g. [('바탕으로', 0.9998)]

torch        >= 1.13
safetensors  >= 0.4
numpy, pillow, opencv-python
pyyaml, shapely, pyclipper
scikit-image                # required by det post-processing

legacy/ch_ptocr_mobile_v2.0_cls_infer.pth
legacy/ch_ptocr_v4_det_infer.pth
legacy/ch_ptocr_v4_rec_infer.pth
legacy/en_ptocr_v3_det_infer.pth
legacy/en_ptocr_v4_rec_infer.pth

@misc{pp_ocrv5_pytorch_joycn_2025,
  title        = {PP-OCRv5 PyTorch Model Zoo},
  author       = {JoyCN},
  howpublished = {\url{https://huggingface.co/JoyCN/PaddleOCR-Pytorch}},
  year         = {2025}
}