{"adoption": {"forks": 140, "observed_at": "2026-08-28T04:07:18.359653+00:00", "stars": 2758}, "canonical_url": "https://ross.abutalabs.com/products/manga-ocr", "card": {"archived": false, "artifact_type": "library", "description": "Optical character recognition for Japanese text, with the main focus being Japanese manga", "domain": ["computer-vision", "image-processing", "machine-learning"], "enriched": true, "function": ["ocr", "image-processing", "machine-learning", "deep-learning", "nlp"], "health_score": 96, "homepage": null, "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "stable", "member_repos": ["kha-white/manga-ocr"], "name": "kha-white/manga-ocr", "platform": ["python", "cross-platform"], "pushed_at": "2026-07-19T08:43:43+00:00", "repo": "kha-white/manga-ocr", "stars": 2758, "tags": ["japanese", "manga", "transformers", "vision-encoder-decoder", "furigana", "pytorch", "natural-language-processing"], "topics": ["ocr", "japanese", "manga", "transformers", "computer-vision", "deep-learning", "comics"], "urls": [], "use_cases": ["extract japanese text from manga panels", "ocr japanese text from images", "recognize text in manga speech bubbles", "read vertical japanese text from scans", "build a japanese reading and mining workflow", "process furigana-laden text in comics", "use as a general purpose printed japanese ocr"], "what_it_is": "Manga OCR is a Python library providing optical character recognition for Japanese text, focused on Japanese manga. It uses a custom end-to-end Vision Encoder Decoder model built with Hugging Face Transformers, robust to vertical/horizontal text, furigana, overlaid text, varied fonts, and low-quality images.", "when_to_avoid": ["you need handwriting recognition rather than printed text", "you need OCR for languages other than Japanese", "you need scene text detection/localization rather than recognition of a given region", "you cannot run a PyTorch/Transformers model locally"], "when_to_choose": ["you need high-quality OCR for Japanese manga or printed Japanese text", "you need multi-line text recognition in a single pass", "your images are low quality, have furigana, or text overlaid on art", "you want a simple Python API or CLI to integrate into a reading workflow"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/manga-ocr", "repo": "kha-white/manga-ocr", "role": "main", "score": 90}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:07:18.359653+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T08:18:47.917358+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "05451f3162be9b197e24f2fc49af0f191f9a4884faf1b94175cab81efedaefef", "fetched_at": "2026-08-28T04:07:18.359653+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kha-white/manga-ocr"}, {"content_hash": "1ab30826634939a275385d58ba720dedd67847b5da1c909b04a886730e660407", "fetched_at": "2026-08-29T09:56:40.048038+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/manga-ocr/json"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:07:18.359653+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T08:18:47.917358+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "05451f3162be9b197e24f2fc49af0f191f9a4884faf1b94175cab81efedaefef", "fetched_at": "2026-08-28T04:07:18.359653+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kha-white/manga-ocr"}, {"content_hash": "1ab30826634939a275385d58ba720dedd67847b5da1c909b04a886730e660407", "fetched_at": "2026-08-29T09:56:40.048038+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/manga-ocr/json"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T08:18:47.917358+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "05451f3162be9b197e24f2fc49af0f191f9a4884faf1b94175cab81efedaefef", "fetched_at": "2026-08-28T04:07:18.359653+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kha-white/manga-ocr"}, {"content_hash": "1ab30826634939a275385d58ba720dedd67847b5da1c909b04a886730e660407", "fetched_at": "2026-08-29T09:56:40.048038+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/manga-ocr/json"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:07:18.359653+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:07:18.359653+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:07:18.359653+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T08:18:47.917358+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "05451f3162be9b197e24f2fc49af0f191f9a4884faf1b94175cab81efedaefef", "fetched_at": "2026-08-28T04:07:18.359653+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kha-white/manga-ocr"}, {"content_hash": "1ab30826634939a275385d58ba720dedd67847b5da1c909b04a886730e660407", "fetched_at": "2026-08-29T09:56:40.048038+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/manga-ocr/json"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:07:18.359653+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:07:18.359653+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T08:18:47.917358+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "05451f3162be9b197e24f2fc49af0f191f9a4884faf1b94175cab81efedaefef", "fetched_at": "2026-08-28T04:07:18.359653+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kha-white/manga-ocr"}, {"content_hash": "1ab30826634939a275385d58ba720dedd67847b5da1c909b04a886730e660407", "fetched_at": "2026-08-29T09:56:40.048038+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/manga-ocr/json"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:07:18.359653+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:07:18.359653+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:07:18.359653+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T08:18:47.917358+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "05451f3162be9b197e24f2fc49af0f191f9a4884faf1b94175cab81efedaefef", "fetched_at": "2026-08-28T04:07:18.359653+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kha-white/manga-ocr"}, {"content_hash": "1ab30826634939a275385d58ba720dedd67847b5da1c909b04a886730e660407", "fetched_at": "2026-08-29T09:56:40.048038+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/manga-ocr/json"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:07:18.359653+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:07:18.359653+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T08:18:47.917358+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "05451f3162be9b197e24f2fc49af0f191f9a4884faf1b94175cab81efedaefef", "fetched_at": "2026-08-28T04:07:18.359653+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kha-white/manga-ocr"}, {"content_hash": "1ab30826634939a275385d58ba720dedd67847b5da1c909b04a886730e660407", "fetched_at": "2026-08-29T09:56:40.048038+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/manga-ocr/json"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T08:18:47.917358+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "05451f3162be9b197e24f2fc49af0f191f9a4884faf1b94175cab81efedaefef", "fetched_at": "2026-08-28T04:07:18.359653+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kha-white/manga-ocr"}, {"content_hash": "1ab30826634939a275385d58ba720dedd67847b5da1c909b04a886730e660407", "fetched_at": "2026-08-29T09:56:40.048038+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/manga-ocr/json"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T08:18:47.917358+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "05451f3162be9b197e24f2fc49af0f191f9a4884faf1b94175cab81efedaefef", "fetched_at": "2026-08-28T04:07:18.359653+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kha-white/manga-ocr"}, {"content_hash": "1ab30826634939a275385d58ba720dedd67847b5da1c909b04a886730e660407", "fetched_at": "2026-08-29T09:56:40.048038+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/manga-ocr/json"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T08:18:47.917358+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "05451f3162be9b197e24f2fc49af0f191f9a4884faf1b94175cab81efedaefef", "fetched_at": "2026-08-28T04:07:18.359653+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kha-white/manga-ocr"}, {"content_hash": "1ab30826634939a275385d58ba720dedd67847b5da1c909b04a886730e660407", "fetched_at": "2026-08-29T09:56:40.048038+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/manga-ocr/json"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 93, "longevity": 100, "rhythm": 81}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 1691, "days_push": 45, "days_rel": 45, "gap_med": 82, "n_releases_24m": 4}, "score": 90, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}