Skip to content
ModelListedExternal
Download

PP OCRv6 Medium Det Mlx

This is an MLX-format conversion of PaddlePaddle/PP-OCRv6mediumdetsafetensors for use with mlx-vlm.

Sourcehuggingface.co/mikoy92/PP-OCRv6-medium-det-mlx/tree/364560d8396a9acfe691a4aa54d090bc4a3663f3
KindOtherBase modelPaddlePaddle/PP-OCRv6_medium_det_safetensorsVersionRevision 364560dBgrade

Model source

Kind
Other
File size
83.9 MB
Base model
PaddlePaddle/PP-OCRv6_medium_det_safetensors
Version
vRevision 364560d
Updated
Oct 23, 2026
Downloads
31
Source
Hugging Face

Source description

PP-OCRv6 medium text detection MLX

This is an MLX-format conversion of PaddlePaddle/PP-OCRv6_medium_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-medium-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"])

Sources

1 source
Hugging FacePrimaryVersion 364560d8396a9acfe691a4aa54d090bc4a3663f3
huggingface.co/mikoy92/PP-OCRv6-medium-det-mlx/tree/364560d8396a9acfe691a4aa54d090bc4a3663f3

Verified Oct 23

Model artifacts

1 artifact

model.safetensors

safetensors · 83.9 MB · SHA-256 4529347f25cf…6349 · Hugging Face

Download file

Source excerpts

3 excerpts
ReadmeAug 6huggingface.co/mikoy92/PP-OCRv6-medium-det-mlx

--- license: apache-2.0 library_name: mlx language: - en - zh pipeline_tag: image-to-text tags: - OCR - PaddlePaddle - PaddleOCR - textline_detection - mlx base_model: PaddlePaddle/PP-OCRv6_medium_det_safetensors --- # PP-OCRv6 medium text detection MLX This is an MLX-format conversion of `PaddlePaddle/PP-OCRv6_medium_det_safetensors` for use with `mlx-vlm`. ```python import mlx.core as mx from PIL import Image from mlx_vlm import load model, processor = load("mikoy92/PP-OCRv6-medium-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"]) ```

NoteOct 23huggingface.co/mikoy92/PP-OCRv6-medium-det-mlx

Source context: 31 downloads · 0 likes · Pipeline image-to-text · Library mlx · Repo mikoy92/PP-OCRv6-medium-det-mlx

NoteAug 6huggingface.co/mikoy92/PP-OCRv6-medium-det-mlx

Source context: 102 downloads · 0 likes · Pipeline image-to-text · Library mlx · Repo mikoy92/PP-OCRv6-medium-det-mlx