|
Download README.md from ternlabs/tre-ocr: direct link, hf CLI and curl.
- Browser
- Download file 2.53 kB
-
https://huggingface.co/ternlabs/tre-ocr/resolve/main/README.md
- Command line
-
hf download hf://ternlabs/tre-ocr/README.md
-
curl -L -o README.md https://huggingface.co/ternlabs/tre-ocr/resolve/main/README.md
2.53 kB
| license: apache-2.0 | |
| language: | |
| - vi | |
| library_name: paddleocr | |
| pipeline_tag: image-to-text | |
| tags: | |
| - ocr | |
| - vietnamese | |
| - paddleocr | |
| - document-ai | |
| base_model: PaddlePaddle/PP-OCRv6_medium_rec | |
| # tre-ocr: round 1 recogniser | |
| A PaddleOCR PP-OCRv6 medium text recogniser, fine-tuned for Vietnamese, from | |
| [ternlabs/tre-ocr](https://github.com/ternlabs/tre-ocr): OCR for Vietnamese documents, with | |
| the accuracy measured, not assumed. | |
| ## What it is for | |
| Reading **scanned Vietnamese stock-exchange disclosures** (resolutions, notices, | |
| explanations filed by HOSE and HNX companies). It is meant to run inside the tre-ocr tool, | |
| which pairs it with PaddleOCR's stock recogniser on the same text boxes: where their digits | |
| differ the stock line is used, and a number is reported only when both agree with | |
| confidence of at least 0.95. Otherwise the number is left empty (`[?]`), never guessed. | |
| Used alone, outside that pairing, it has **not** been measured. | |
| ## Results (set F, measured once, pass marks fixed in advance) | |
| 40 scanned pages, none seen in training, at most 2 per company. | |
| | Mark | Needed | Result | 95% interval | | |
| |---|---|---|---| | |
| | Number recall | ≥ 98% | **98.7%** (607 of 615) | 97.5 to 99.3 | | |
| | Wrong when sure | ≤ 1% | **0.19%** (1 of 535) | 0.0 to 1.1 | | |
| | Coverage | ≥ 85% | **87.4%** | | | |
| | Company field | ≥ 90% | **91.7%** (22 of 24) | 74.2 to 97.7 | | |
| The candidate passed each mark, but the intervals reach past them: close to the marks, not | |
| clear of them. Tone marks were scored against a reading no person checked, so they are | |
| reported in METHOD.md and never used as a pass. Full method, sets and limits: | |
| [METHOD.md](https://github.com/ternlabs/tre-ocr/blob/main/METHOD.md). | |
| ## Limits | |
| - **Financial statements have not passed**; the tool refuses them. | |
| - Handwriting, other document kinds and other scan conditions are not measured. | |
| ## Training | |
| Fine-tuned only on typed public filings rendered to look scanned. Every test-set file, and | |
| every page naming a test-set company, was left out. | |
| ## Use | |
| ``` | |
| git clone https://github.com/ternlabs/tre-ocr && cd tre-ocr | |
| pip install -r requirements-reader.txt # needs poppler-utils | |
| bash tools/get_weights.sh # fetches and hash-checks these weights | |
| python -I tools/read_pdf.py some.pdf --out cache/drafts | |
| ``` | |
| Files here: `round1-rec.tar.gz`, SHA-256 | |
| `010c5757be568a258d6657402a3acbbf6450f46dd978840e4f5a298e1e22fd5e`, the same archive | |
| `get_weights.sh` checks. | |
| ## Licence | |
| Apache License 2.0. Published by [Tern Labs](https://ternlabs.io). | |