software-mansion/react-native-executorch-easy-ocr

Introduction

This repository hosts the EasyOCR models — the CRAFT detector and the CRNN recognizer — for the 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 for setup instructions.

Each language ships as one fused .pte (CRAFT detect + CRNN recognize in a single file) per backend, with a single dynamic detect method and one fixed-width recognize method (no per-size method buckets). 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. EasyOCR is the fallback pipeline — PP-OCRv6 is primary.

Repository layout

<language>/<backend>/config.json                 # per-backend spec
<language>/<backend>/easy_ocr_<language>_<backend>_<precision>.pte
<language>/charset.txt                           # charset[i] -> logit i+1, blank = 0

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. Charset index i maps to logit i + 1 (logit 0 is the CTC blank).

Methods & I/O contract

method	input	output
detect (CRAFT)	[1,3,H,W] f32 RGB, ImageNet-normalized by the client: (x/255 − mean)/std, mean=[0.485,0.456,0.406], std=[0.229,0.224,0.225]	score [1,H/2,W/2,2] (region + affinity, NHWC)
recognize (CRNN)	[1,3,64,512] f32 RGB, client-normalized (x/255 − 0.5)/0.5 (RGB→gray conv is baked)	[1,127,V] probs (softmax baked)

Nothing is baked for input normalization — the client normalizes before calling, with different norms per method (ImageNet for detect, 0.5/0.5 for recognize). detect exports the detection heatmap only; CRAFT's RefineNet feature map is dropped, as nothing on-device consumes it.

Shape discovery (get_model_schema)

Every .pte exports one no-arg constant method, get_model_schema, returning a JSON ModelSpec string: per method, the input and output parameter specs (dtype plus a domain per dimension — constant, range with {min, max, step}, or enum with explicit choices) and the runtime constraints the method declares over its dimensions. The older get_dynamic_dims_<m> / get_enum_shapes_<m> companion methods are gone — everything they carried now lives in this one document.

backend	detect H	detect W
xnnpack	range [320, 1280] step 32	range [320, 1280] step 32
vulkan	range [800, 1280] step 32	range [320, 1280] step 32
coreml	enum 320, 800, 1280	enum 320, 800, 1280

recognize is fixed at [1,3,64,512] on every backend and declares a linear runtime constraint tying its input width to its CTC timestep count: width = 4 × timesteps + 4. The CRNN crops a trailing timestep, so 512 → 127 is not a plain width/timestep ratio — read the constraint rather than dividing. detect runs once per image; recognize runs once per text line, with every crop snapped to width 512 (the BiLSTM only delegates at a fixed time dimension).

Backends

backend	target	detect	recognize	warm latency (detect @800² / recognize)
xnnpack	CPU	int8, dynamic (see note)	int8 @512	~810 ms / ~24 ms (Galaxy S24)
coreml	Apple ANE	weight-only int8, enumerated	weight-only int8 @512	~83 ms / ~27 ms (Apple M-series ANE)
vulkan	Android GPU	fp16, dynamic (resize)	int8 @512 on XNNPACK (mixed-delegate)	~750 ms / ~24 ms (Galaxy S24, Xclipse 940)

XNNPACK detect accuracy note: the int8 detector is calibrated for sizes ≤ 800 px (its accurate operating band). Larger inputs up to 1280 are accepted but best-effort — static-activation int8 is not stable at ≥ 960 px (this was equally true, though unmeasured, of the previous per-bucket builds). Prefer resizing pages to ≤ 800 on CPU; the Vulkan and CoreML detectors are accurate over their full advertised ranges.

CoreML notes (iOS)

• The CoreML .pte is a multifunction Core ML model (detect + recognize share one precompiled .mlmodelc). Requires iOS 18+ and an ExecuTorch runtime ≥ 1.3.
• First-ever load on a device triggers a one-time per-shape ANE specialization (OS-cached afterwards) — warm each model once after install.

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. If you work with React Native ExecuTorch, the library constants guarantee compatibility with the runtime used behind the scenes.

These models were exported with ExecuTorch 1.3.1 and no forward compatibility is guaranteed; older runtimes may not load them.