PP-OCRv6 small text recognition MLX

This is an MLX-format conversion of PaddlePaddle/PP-OCRv6_small_rec_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-small-rec-mlx")
image = Image.open("word.png")

inputs = processor(image)
outputs = model(**inputs)
mx.eval(outputs.logits)

print(processor.post_process_text_recognition(outputs)[0])