FocsleFo’c’sle
PP

PaddleOCR-Edge-v5

7%
by PaddlePaddle

Latest PaddleOCR with edge-tuned recognition head. 80+ languages, single binary.

OCRApache-2.0INT8FP16ocrmultilingual
142K downloads 8.4K deploymentsUpdated Apr 4, 2028
Headline:18.4ms · Qualcomm QCS8550 · INT8
OverviewBenchmarks6Sim ResultsDeploy6FilesDiscussion23

About this model

Latest PaddleOCR with edge-tuned recognition head. 80+ languages, single binary.

Authored by paddlepaddle. Curated into the Fo’c’sle reference set on 2028-04-04. All cross-chip benchmarks below were collected in matched-pair runs in the HIL lab using the same input pipeline, same upstream preprocessing, and the same downstream consumer. See the methodology page for the full protocol.

Task
OCR
Parameters
9.4 M
Benchmarked on
6 chips
Deployments
8.4K

Architecture

Detection + recognition pipeline
Inferred from upstream weights · simplified
DocumentText detectCrop & rectifyRecognizerStrings

Headline benchmarks

QQualcomm QCS8550INT8
6.48ms p50
154 FPS98.6% acc12.7 W
Apple Neural Engine (M4)FP16
10.2ms p50
98 FPS99.4% acc7.2 W
HHailo-8INT8
12.0ms p50
83 FPS97.3% acc2.4 W

Training data

Pretrained on the upstream maintainer’s released checkpoint. Edge-distillation pass uses 2.4M frames from the Fo’c’sle distillation corpus (consented public data + opt-in publisher contributions). Quantization-aware fine-tune uses 320K calibration samples drawn from the target task’s eval domain.

  • Pretraining corpus: upstream maintainer release
  • Distillation corpus: 2,400,000 frames
  • Calibration set: 320,000 samples (per task)
  • Eval set: standard benchmark + matched-pair HIL runs