| --- |
| license: mit |
| --- |
| # Introduction |
|
|
| This repository hosts the [EasyOCR](https://github.com/JaidedAI/EasyOCR) models — the |
| [CRAFT detector](https://github.com/clovaai/CRAFT-pytorch) and the [CRNN recognizer](https://www.jaided.ai/easyocr/modelhub/) — for the |
| [React Native ExecuTorch](https://www.npmjs.com/package/react-native-executorch) library, |
| exported to `.pte` for the **ExecuTorch** runtime (XNNPACK, CoreML and Vulkan backends). |
|
|
| If you'd like to run these models in your own ExecuTorch runtime, refer to the |
| [official documentation](https://pytorch.org/executorch/stable/index.html) for setup instructions. |
|
|
| Each language ships as **one fused `.pte`** (CRAFT *detect* + CRNN *recognize* in a single |
| file) per backend, using **static bucketed methods** — no dynamic-shape footguns. The `.pte` |
| is a pure tensor→tensor function; all pre/post-processing (resize, normalize, box extraction, |
| crop, CTC decode) is the client's job and is driven by `config.json`. |
|
|
| ## Languages |
|
|
| | code | charset size | code | charset size | |
| |---|---|---|---| |
| | english | 96 | korean | 1008 | |
| | latin | 351 | telugu | 165 | |
| | japanese | 2214 | kannada | 167 | |
| | zh_sim | 6718 | cyrillic | 207 | |
| |
| All languages share the same CRAFT detector and CRNN architecture — they differ **only** in |
| the recognizer charset. The detector half of each fused PTE is identical across languages. |
| |
| ## Backends |
| |
| | backend | target | precision | |
| |---|---|---| |
| | `xnnpack` | CPU (Android/iOS) | int8 (CRAFT + CRNN) | |
| | `coreml` | Apple ANE | weight-only int8 | |
| | `vulkan` | Android GPU | CRAFT int8 (GPU) + CRNN int8 (XNNPACK, mixed-delegate) | |
| |
| |
| ## Files |
| |
| ``` |
| config.json # shared base config (schema v1) |
| charsets/easyocr_<lang>.charset.txt # per-language CTC charset (JSON array) |
| <lang>/<backend>/easyocr_<lang>_<backend>_bucketed.pte |
| ``` |
| |
| - `config.json` is **shared** across all languages; it carries |
| `charsetUrlPattern: "easyocr_<lang>.charset.txt"` so the client resolves the charset by |
| language. Charset index `i` maps to logit `i + 1` (logit `0` is the CTC blank). |
|
|
| ## Buckets |
|
|
| Static per-size methods (`is_bucketed()` reports `[detect sides ; recognize widths]`): |
|
|
| - **detect** (square sides): `800, 1280` → `detect_800`, `detect_1280` (+ a `1280×320` portrait method) |
| - **recognize** (widths, height 64): `64, 128, 256, 512` → `recognize_64 … recognize_512` |
| `detect` runs once per image; `recognize` runs once per text line. |
|
|
| ## Compatibility |
|
|
| If you intend to use these models outside of React Native ExecuTorch, make sure your runtime is |
| compatible with the **ExecuTorch** version used to export the `.pte` files. For more details, see |
| the compatibility note in the |
| [ExecuTorch GitHub repository](https://github.com/pytorch/executorch/blob/main/runtime/COMPATIBILITY.md). |
| If you work with React Native ExecuTorch, the library constants guarantee compatibility with the |
| runtime used behind the scenes. |
|
|
|
|
