Image-to-Text
MLX
Safetensors
PaddleOCR
English
Chinese
pp_ocrv6_small_det
OCR
PaddlePaddle
textline_detection
pp_ocrv6_tiny_det
Instructions to use mikoy92/PP-OCRv6-tiny-det-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mikoy92/PP-OCRv6-tiny-det-mlx with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir PP-OCRv6-tiny-det-mlx mikoy92/PP-OCRv6-tiny-det-mlx
- PaddleOCR
How to use mikoy92/PP-OCRv6-tiny-det-mlx with PaddleOCR:
# 1. See https://www.paddlepaddle.org.cn/en/install to install paddlepaddle # 2. pip install paddleocr from paddleocr import TextDetection model = TextDetection(model_name="PP-OCRv6-tiny-det-mlx") output = model.predict(input="path/to/image.png", batch_size=1) for res in output: res.print() res.save_to_img(save_path="./output/") res.save_to_json(save_path="./output/res.json") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
PP-OCRv6 tiny text detection MLX
This is an MLX-format conversion of PaddlePaddle/PP-OCRv6_tiny_det_safetensors for use with mlx-vlm.
import mlx.core as mx
from PIL import Image
from mlx_vlm import load
model, processor = load("mikoy92/PP-OCRv6-tiny-det-mlx")
image = Image.open("document.png")
inputs = processor(image)
outputs = model(**inputs)
mx.eval(outputs.logits)
result = processor.post_process_object_detection(
outputs,
target_sizes=inputs["target_sizes"],
)[0]
print(result["boxes"])
- Downloads last month
- 65
Model size
438k params
Tensor type
F32
·
Hardware compatibility
Log In to add your hardware
Quantized
Model tree for mikoy92/PP-OCRv6-tiny-det-mlx
Base model
PaddlePaddle/PP-OCRv6_tiny_det_safetensors