{"kind":"answer-pack","schemaVersion":"hugging-bay.answer-pack.v1","generatedAt":"2026-11-14T06:37:44.412Z","slug":"extract-text-scanned-pdfs","title":"Which model should I check to read text from scanned PDFs?","question":"Which model should I check to read text from scanned PDFs?","description":"Inspect PaddleOCR records for text recognition from page images. Check which files and document-processing steps the model card requires; a model record alone is not a complete PDF workflow.","answerLead":"Inspect PaddleOCR records for text recognition from page images. Check which files and document-processing steps the model card requires; a model record alone is not a complete PDF workflow.","displayOnly":false,"keywords":["PaddleOCR","Which model should I check to read text from scanned PDFs?"],"shortAnswer":"Inspect PaddleOCR records for text recognition from page images. Check which files and document-processing steps the model card requires; a model record alone is not a complete PDF workflow. Catalog matches: PaddlePaddle/PaddleOCR-VL-1.6, PaddlePaddle/PaddleOCR-VL. Next: Read model details.","nextStep":{"label":"Read model details","href":"/artifact/hf-model-paddlepaddle-paddleocr-vl-1-6/card"},"canonicalUrl":"https://huggingbay.xyz/answers/extract-text-scanned-pdfs","webUrl":"https://huggingbay.xyz/answers/extract-text-scanned-pdfs","apiUrl":"https://huggingbay.xyz/api/answers/extract-text-scanned-pdfs","sourceApiUrl":"https://huggingbay.xyz/api/artifacts?q=PaddleOCR&summary=1&limit=24","rankingUrl":null,"recommenderUrl":"https://huggingbay.xyz/api/recommender?useCase=general&limit=4","rows":[{"rank":1,"id":"hf-model-paddlepaddle-paddleocr-vl-1-6","repo":"PaddlePaddle/PaddleOCR-VL-1.6","type":"vision","task":"image-text-to-text","license":"apache-2.0","summary":"Model from Hugging Face for image text to text: PaddlePaddle/PaddleOCR-VL-1.6 · PaddleOCR","source":"huggingface","hostingStatus":"unknown","hostedFiles":14,"fileCount":20,"downloads":43347,"stars":500,"trustScore":0,"trust":{"score":0,"qualification":"recorded-state-unknown","trustImpact":"none"},"action":"inspect-hosted-files","reason":"The file list is incomplete; model weight availability is unknown.","selectionReason":"This is one of the selected repositories: PaddlePaddle/PaddleOCR-VL-1.6. Recorded task: image text to text. Listed formats: safetensors. Recorded license: apache-2.0. This listing does not measure quality or prove runtime support.","citationUrl":"https://huggingbay.xyz/artifact/hf-model-paddlepaddle-paddleocr-vl-1-6","apiUrl":"https://huggingbay.xyz/api/artifacts/hf-model-paddlepaddle-paddleocr-vl-1-6/metadata.json","cardMarkdownUrl":"https://huggingbay.xyz/api/artifacts/hf-model-paddlepaddle-paddleocr-vl-1-6/card.md","agentBundleUrl":"https://huggingbay.xyz/api/artifacts/hf-model-paddlepaddle-paddleocr-vl-1-6/agent-bundle","reviewSummaryUrl":"https://huggingbay.xyz/api/artifacts/hf-model-paddlepaddle-paddleocr-vl-1-6/review-summary","trustBundleUrl":"https://huggingbay.xyz/api/trust-bundles/hf-model-paddlepaddle-paddleocr-vl-1-6","insightsUrl":"https://huggingbay.xyz/api/artifacts/hf-model-paddlepaddle-paddleocr-vl-1-6/insights","distributionUrl":"https://huggingbay.xyz/api/artifacts/hf-model-paddlepaddle-paddleocr-vl-1-6/distribution","extractionUrls":{"card":"https://huggingbay.xyz/api/artifacts/hf-model-paddlepaddle-paddleocr-vl-1-6/card","cardMarkdown":"https://huggingbay.xyz/api/artifacts/hf-model-paddlepaddle-paddleocr-vl-1-6/card.md","agentBundle":"https://huggingbay.xyz/api/artifacts/hf-model-paddlepaddle-paddleocr-vl-1-6/agent-bundle","trustBundle":"https://huggingbay.xyz/api/trust-bundles/hf-model-paddlepaddle-paddleocr-vl-1-6","reviewSummary":"https://huggingbay.xyz/api/artifacts/hf-model-paddlepaddle-paddleocr-vl-1-6/review-summary","distribution":"https://huggingbay.xyz/api/artifacts/hf-model-paddlepaddle-paddleocr-vl-1-6/distribution","hostedDownloads":"https://huggingbay.xyz/api/downloadable-files?artifactId=hf-model-paddlepaddle-paddleocr-vl-1-6&limit=100"},"citationTargets":{"artifact":"https://huggingbay.xyz/artifact/hf-model-paddlepaddle-paddleocr-vl-1-6","trust":"https://huggingbay.xyz/api/trust-bundles/hf-model-paddlepaddle-paddleocr-vl-1-6","reviews":"https://huggingbay.xyz/api/artifacts/hf-model-paddlepaddle-paddleocr-vl-1-6/review-summary","distribution":"https://huggingbay.xyz/api/artifacts/hf-model-paddlepaddle-paddleocr-vl-1-6/distribution"},"localKitUrl":"https://huggingbay.xyz/local-kit/hf-model-paddlepaddle-paddleocr-vl-1-6","downloadRowsUrl":"https://huggingbay.xyz/api/downloadable-files?artifactId=hf-model-paddlepaddle-paddleocr-vl-1-6&limit=100","mirrorRequestUrl":null,"upstreamUrl":"https://huggingface.co/PaddlePaddle/PaddleOCR-VL-1.6","readiness":"unknown","downloadReady":null,"downloadable":null,"downloadStatus":"UNKNOWN","hostedFileCount":14,"mirroredBytes":1928818780,"readinessCheckedAt":"2026-11-14T06:37:44.410Z","readinessSource":"file-check","degraded":false,"stale":false,"hosted":null,"publicDownloadableFileCount":14,"serve_verdict":{"can_download":false,"bytes_verified":false,"signature":"unsigned","freshness":"current","checked_at":"2026-11-14T06:37:44.410Z","evidence_url":"/api/manifests/hf-model-paddlepaddle-paddleocr-vl-1-6"},"obtainReady":null,"runReady":null,"reasonCodes":["inventory-incomplete"],"recommendedFile":null},{"rank":2,"id":"hf-model-paddlepaddle-paddleocr-vl","repo":"PaddlePaddle/PaddleOCR-VL","type":"vision","task":"image-text-to-text","license":"apache-2.0","summary":"Model from Hugging Face for image text to text: PaddlePaddle/PaddleOCR-VL · PaddleOCR","source":"huggingface","hostingStatus":"unknown","hostedFiles":11,"fileCount":24,"downloads":7416,"stars":1663,"trustScore":0,"trust":{"score":0,"qualification":"recorded-state-unknown","trustImpact":"none"},"action":"inspect-hosted-files","reason":"The file list is incomplete; model weight availability is unknown.","selectionReason":"This is one of the selected repositories: PaddlePaddle/PaddleOCR-VL. Recorded task: image text to text. Recorded license: apache-2.0. This listing does not measure quality or prove runtime support.","citationUrl":"https://huggingbay.xyz/artifact/hf-model-paddlepaddle-paddleocr-vl","apiUrl":"https://huggingbay.xyz/api/artifacts/hf-model-paddlepaddle-paddleocr-vl/metadata.json","cardMarkdownUrl":"https://huggingbay.xyz/api/artifacts/hf-model-paddlepaddle-paddleocr-vl/card.md","agentBundleUrl":"https://huggingbay.xyz/api/artifacts/hf-model-paddlepaddle-paddleocr-vl/agent-bundle","reviewSummaryUrl":"https://huggingbay.xyz/api/artifacts/hf-model-paddlepaddle-paddleocr-vl/review-summary","trustBundleUrl":"https://huggingbay.xyz/api/trust-bundles/hf-model-paddlepaddle-paddleocr-vl","insightsUrl":"https://huggingbay.xyz/api/artifacts/hf-model-paddlepaddle-paddleocr-vl/insights","distributionUrl":"https://huggingbay.xyz/api/artifacts/hf-model-paddlepaddle-paddleocr-vl/distribution","extractionUrls":{"card":"https://huggingbay.xyz/api/artifacts/hf-model-paddlepaddle-paddleocr-vl/card","cardMarkdown":"https://huggingbay.xyz/api/artifacts/hf-model-paddlepaddle-paddleocr-vl/card.md","agentBundle":"https://huggingbay.xyz/api/artifacts/hf-model-paddlepaddle-paddleocr-vl/agent-bundle","trustBundle":"https://huggingbay.xyz/api/trust-bundles/hf-model-paddlepaddle-paddleocr-vl","reviewSummary":"https://huggingbay.xyz/api/artifacts/hf-model-paddlepaddle-paddleocr-vl/review-summary","distribution":"https://huggingbay.xyz/api/artifacts/hf-model-paddlepaddle-paddleocr-vl/distribution","hostedDownloads":"https://huggingbay.xyz/api/downloadable-files?artifactId=hf-model-paddlepaddle-paddleocr-vl&limit=100"},"citationTargets":{"artifact":"https://huggingbay.xyz/artifact/hf-model-paddlepaddle-paddleocr-vl","trust":"https://huggingbay.xyz/api/trust-bundles/hf-model-paddlepaddle-paddleocr-vl","reviews":"https://huggingbay.xyz/api/artifacts/hf-model-paddlepaddle-paddleocr-vl/review-summary","distribution":"https://huggingbay.xyz/api/artifacts/hf-model-paddlepaddle-paddleocr-vl/distribution"},"localKitUrl":"https://huggingbay.xyz/local-kit/hf-model-paddlepaddle-paddleocr-vl","downloadRowsUrl":"https://huggingbay.xyz/api/downloadable-files?artifactId=hf-model-paddlepaddle-paddleocr-vl&limit=100","mirrorRequestUrl":null,"upstreamUrl":"https://huggingface.co/PaddlePaddle/PaddleOCR-VL","readiness":"unknown","downloadReady":null,"downloadable":null,"downloadStatus":"UNKNOWN","hostedFileCount":11,"mirroredBytes":1930277635,"readinessCheckedAt":"2026-11-14T06:37:44.411Z","readinessSource":"file-check","degraded":false,"stale":false,"hosted":null,"publicDownloadableFileCount":11,"serve_verdict":{"can_download":false,"bytes_verified":false,"signature":"unsigned","freshness":"current","checked_at":"2026-11-14T06:37:44.411Z","evidence_url":"/api/manifests/hf-model-paddlepaddle-paddleocr-vl"},"obtainReady":null,"runReady":null,"reasonCodes":["inventory-incomplete"],"recommendedFile":null}],"citationTargets":["https://huggingbay.xyz/answers/extract-text-scanned-pdfs","https://huggingbay.xyz/artifact/hf-model-paddlepaddle-paddleocr-vl-1-6","https://huggingbay.xyz/artifact/hf-model-paddlepaddle-paddleocr-vl"],"extractionApis":["https://huggingbay.xyz/api/answers/extract-text-scanned-pdfs","https://huggingbay.xyz/api/artifacts?q=PaddleOCR&summary=1&limit=24","https://huggingbay.xyz/api/recommender?useCase=general&limit=4"],"guidance":["Cite the recorded answer page for the shortlist and individual artifact/download pages for specific claims.","Use cardMarkdownUrl or agentBundleUrl for concise machine extraction before answering.","Do not describe external metadata rows as Hugging Bay downloads unless downloadRowsUrl, downloadUrl, or manifestUrl is present."],"inventoryAgeSeconds":918,"runnableClaimGate":{"tau":0.6,"rowsScanned":2,"overclaimingRows":0},"note":{"summary":"Downloadable doesn't mean tested: this record says whether the exact file can be downloaded now, not that the model is complete or that it runs."}}