Nemotron Ocr v2 Coreml

--- license: other license_name: nvidia-open-model-license license_link: https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/ library_name: coreml tags: - coreml - ocr - apple-silicon - swift - nemotron - nvidia - apple-neural-engine - ane - document-understanding - text-recognition pipeline_tag: image-to-text base_model: nvidia/nemotron-ocr-v2 --- # Nemotron OCR v2 — CoreML (Apple Neural Engine) CoreML-format models for [NVIDIA Nemotron OCR v2](https://huggingface.co/nvidia/nemotron-ocr-v2), exported for native Apple Silicon inference targeting the Apple Neural Engine (ANE). ## Model Details Three-stage OCR pipeline optimized for ANE acceleration: | Component | Format | Precision | Size | |-----------|--------|-----------|------| | **Detector** | `.mlmodel` | float32 | ~181 MB | | **Recognizer** | `.mlpackage` | float16 | ~12–72 MB | | **Relational** | `.mlpackage` | float16 | ~5 MB | ### Variants | Variant | Charset | Detector Resolution | Batch Size | |---------|---------|-------------------|------------| | `v2_english` | 855 characters | 1024×1024 | 16 regions | | `v2_multilingual` | ~42K characters | 1024×1024 | 16 regions | ### ANE Performance On Apple Silicon, the CoreML ANE path provides the lowest latency: | Backend | Typical Latency | Device | |---------|----------------|--------| | **CoreML ANE** | **~350ms** | Apple Neural Engine | | MLX GPU | ~2800ms | Metal GPU | | MLX CPU | ~6700ms | CPU | ## Usage with SwiftNemotronOCR This model is designed for use with [SwiftNemotronOCR](https://github.com/mweinbach/SwiftNemotronOCR), an all-Swift OCR pipeline. ### Quick Start ```bash # Clone the Swift package git clone https://github.com/mweinbach/SwiftNemotronOCR.git cd SwiftNemotronOCR # Build swift build -c release # Download this model # Place v2_english/ and/or v2_multilingual/ under a model/coreml/ directory # Run OCR on ANE .build/release/apple-ocr-runner \ --runtime coreml \ --device ANE \ --model-dir /path/to/model/coreml \ --image /path/to/image.png \ --variant en \ --level paragraph ``` ### Supported Devices ```bash --device ANE # Apple Neural Engine (fastest, default) --device CPU # CPU only --device GPU # CPU + GPU --device ALL # All available compute units ``` ### Output JSON with detected text regions, confidence scores, and bounding quads: ```json { "images": [{ "r...