2026-09-26: PP-DocLayoutV3_fp32_batchable.onnx, PP-DocLayoutV3_fp32_batchable_fp16.onnx, PP-OCRv6_medium_det.onnx, PP-OCRv6_small_det.onnx, PP-OCRv6_tiny_det.onnx, PP-OCRv6_tiny_rec_ctc.onnx, PP-OCRv6_tiny_rec_ctc_fp16.onnx, PP-OCRv6_medium_rec_ctc.onnx, PP-OCRv6_medium_rec_ctc_fp16.onnx, PP-OCRv6_small_rec_ctc.onnx, PP-OCRv6_small_rec_ctc_fp16.onnx, PP-FormulaNet_plus-M_encoder.onnx, PP-FormulaNet_plus-M_prep.onnx, PP-FormulaNet_plus-M_decoder_step.onnx, PP-FormulaNet_plus-M_tokenizer.json, PP-FormulaNet_plus-S_encoder.onnx, PP-FormulaNet_plus-S_prep.onnx, PP-FormulaNet_plus-S_decoder_step.onnx, PP-FormulaNet_plus-S_tokenizer.json, PP-LCNet_x1_0_table_cls.onnx, RapidTable_unet_uint8.onnx, SLANet_plus_encoder.onnx, SLANet_plus_decoder.bin
ddfe31e verified | license: apache-2.0 | |
| tags: | |
| - onnx | |
| - document-parsing | |
| - layout-analysis | |
| - ocr | |
| - table-structure-recognition | |
| - formula-recognition | |
| # docparser-models | |
| ONNX exports of PaddlePaddle document models, one flat file per model. | |
| `MANIFEST.txt` lists the sha256 of every file. All files are Apache-2.0. | |
| | File | Model | Source | | |
| | --- | --- | --- | | |
| | `PP-DocLayoutV3_fp32_batchable.onnx` | layout detection | [`PaddlePaddle/PP-DocLayoutV3_onnx`](https://huggingface.co/PaddlePaddle/PP-DocLayoutV3_onnx), output reshaped to `[B,300,7]` | | |
| | `PP-OCRv6_{tiny,small,medium}_det.onnx` | text detection | [`PaddlePaddle/PP-OCRv6_*_det_onnx`](https://huggingface.co/PaddlePaddle), unchanged | | |
| | `PP-OCRv6_{tiny,small,medium}_rec_ctc.onnx` | text recognition | [`PaddlePaddle/PP-OCRv6_*_rec_onnx`](https://huggingface.co/PaddlePaddle), plus `ctc_idx` / `ctc_prob` outputs (argmax and max over the class axis) | | |
| | `SLANet_plus_encoder.onnx`, `SLANet_plus_decoder.bin` | table structure | [`PaddlePaddle/SLANet_plus_onnx`](https://huggingface.co/PaddlePaddle/SLANet_plus_onnx): the encoder graph, and the GRU decoder's weights as raw float32 | | |
| | `PP-LCNet_x1_0_table_cls.onnx` | table classification (wired / wireless) | [`PaddlePaddle/PP-LCNet_x1_0_table_cls_onnx`](https://huggingface.co/PaddlePaddle/PP-LCNet_x1_0_table_cls_onnx), unchanged; labels `[wired_table, wireless_table]` | | |
| | `RapidTable_unet_uint8.onnx` | wired-table line segmentation | RapidAI [TableStructureRec](https://github.com/RapidAI/TableStructureRec)'s `unet.onnx` (Apache-2.0; byte-identical in [`opendatalab/PDF-Extract-Kit-1.0`](https://huggingface.co/opendatalab/PDF-Extract-Kit-1.0) `models/TabRec/UnetStructure/`), with a UINT8 RGB `[1,H,W,3]` input normalised in the graph and a UINT8 `[H,W]` class map output (`unet_io.py`) | | |
| | `PP-FormulaNet_plus-{M,S}_{encoder,prep,decoder_step}.onnx`, `_tokenizer.json` | formula recognition | [`PaddlePaddle/PP-FormulaNet_plus-M`](https://huggingface.co/PaddlePaddle/PP-FormulaNet_plus-M) / [`-S`](https://huggingface.co/PaddlePaddle/PP-FormulaNet_plus-S), split into encoder, cross-attention precompute and one greedy decoder step over a static KV cache | | |
| | `PP-DocLayoutV3_fp32_batchable_fp16.onnx`, `PP-OCRv6_{tiny,small,medium}_rec_ctc_fp16.onnx` | FP16 graphs for ONNX Runtime's TensorRT provider | derived from the FP32 file of this repository by `convert_fp16.py` (onnx 1.21.0, onnxconverter-common 1.16.0; I/O stay FP32) | | |
| Pre- and post-processing follow each source model's `inference.yml`. | |