Mori-kamiyama/Orono-v1
AI model by Mori-kamiyama
Older snapshot: check the original source for current information.
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
日本語の縦書き・横書きOCR研究モデル3種の固定スナップショットです。 This repository contains Ogi (detection), Oikawa (recognition), and Buncho (reading order). It is a research checkpoint release, not a Transformers AutoModel package or a standalone OCR application. No external n-gram model, corpus, index, rescoring code, training images, evaluation text, full predictions, optimizer state, or credentials are included. The character vocabulary and glyph embeddings belong to the recognizer and are included. Oikawa has 4,337,313 parameters across both directions. Each line uses one direction's projection and FFNs; CNN, attention and glyph dictionary are shared. The vocabulary has 8,707 characters, plus CTC blank ID 0; character ID i+1 maps to chars.json[i]. Ogi takes a 1024×1024 RGB letterboxed image with ImageNet normalization. Its fused inference model has 8,078,513 parameters; the native checkpoint retains its original unfused state. Oikawa takes upright grayscale crops with a 64-pixel cross axis and variable long axis, stride 16, normalized as 1 - pixels / 255. Horizontal text is…
Read the full model card ↗ · Preview checked 2026-10-29T08:39:45.592Z
Inside the original model card — Document outline
- Orono v1 — Japanese vertical and horizontal OCR
- Contents
- Download
- Load the native recognizer
- ONNX inference
- Detector and reading-order dependencies
- Existing evaluation (not rerun for publication)
- Provenance and licensing
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Documentation belongs to its respective authors. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
Mori-kamiyama/Orono-v1 is a task-unspecified model repository published by Mori-kamiyama on Hugging Face. A library was not reported.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- Not reported
- Library
- Not reported
- Recent downloads (30 days)
- 0
- Cumulative likes
- 0
- Hugging Face trending score
- 0
- Reported safetensors parameters
- Not reported
- Architecture
- Not reported
- License
- Not reported — check the model card
- Access
- Not gated by Hugging Face
- Created
- 2026-10-29T06:25:34.000Z
- Last modified
- 2026-10-29T06:25:53.000Z
Compatibility and lineage
Reported languages: ja
Base-model lineage was not included.
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-10-29T06:48:44.800Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.