Image-to-Text
MLX
Safetensors
mlx-weights
paddlepaddle-ocr
ppocrv5
ppocrv6
ppdoclayoutv3
pp-structure
apple-silicon
Instructions to use plaincompute/ppocr-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use plaincompute/ppocr-mlx with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir ppocr-mlx plaincompute/ppocr-mlx
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
| { | |
| "model_type": "pp_ocrv5_mobile_rec", | |
| "backbone_config": { | |
| "model_type": "pp_lcnet_v3", | |
| "scale": 0.95, | |
| "out_features": ["stage2", "stage3", "stage4", "stage5"], | |
| "out_indices": [2, 3, 4, 5], | |
| "divisor": 16, | |
| "block_configs": [ | |
| [[3, 16, 32, 1, false]], | |
| [[3, 32, 64, 1, false], [3, 64, 64, 1, false]], | |
| [[3, 64, 128, [2, 1], false], [3, 128, 128, 1, false]], | |
| [ | |
| [3, 128, 256, [1, 2], false], | |
| [5, 256, 256, 1, false], | |
| [5, 256, 256, 1, false], | |
| [5, 256, 256, 1, false], | |
| [5, 256, 256, 1, false] | |
| ], | |
| [ | |
| [5, 256, 512, [2, 1], true], | |
| [5, 512, 512, 1, true], | |
| [5, 512, 512, [2, 1], false], | |
| [5, 512, 512, 1, false] | |
| ] | |
| ] | |
| }, | |
| "hidden_act": "silu", | |
| "hidden_size": 120, | |
| "mlp_ratio": 2.0, | |
| "depth": 2, | |
| "head_out_channels": 18385, | |
| "conv_kernel_size": [1, 3], | |
| "qkv_bias": true, | |
| "num_attention_heads": 8, | |
| "attention_dropout": 0.0 | |
| } |