Unlimited-OCR 3B
Free.ai (self-hosted)
·
ocr
·
~300 Token page
Unlimited-OCR 3B bụ an OCR model e mepụtara site na Baidu. Ọrụ na Image / scan to structured Markdown, complex layouts, tables, multi-page documents.. Self-hosted na Free.ai GPUs - na-agba ọsọ n'efu megide ụbọchị gị token pool (300 tokens Ihu). E wepụtara ya n'okpuru MIT - iji ahịa ekwenyela na Free.ai.
Jiri site na API
OpenAI-na-akpaghị aka REST API. Kewapụta kii nakwa kpọọ móòdù a n'ime sekọnd.
curl -X POST https://api.free.ai/v1/ocr/ \
-H "Authorization: Bearer sk-free-..." \
-H "Content-Type: application/json" \
-d '{"model":"unlimited-ocr","prompt":"your prompt here"}'Ajụjụ ndị a jụrụkarị
Unlimited-OCR 3B na-ewepụ ngwe site n'ịmage na PDFs. Bipụta ihuakwụkwọ skenètị̀, skịnètị̀, mọọbụ foto nke dọkumenti ahụ na Unlimited-OCR 3B na-eziga ngwe ahụ - na-echekwa nkwụsị̀ nke ụkpụrụedemede na (n'ime ike engines) táàbụ̀, fómùlà, nakwa struct.
Unlimited-OCR 3B na-ejikwa ikiriputa - Latin, Cyrillic, CJK, Arabic, Devanagari, na ndị ọzọ. /ocr/ landing nwere ndesịta asụsụ zuru ezu maka engine.
Yabụ maka nsụgharị aka-akpụzi-ụdị; cursive na shorthand bụ ndị dị njọ. TrOCR na nsụgharị-n'okpuru engines dị ugbua dị mma karịa Tesseract nke ochie na nsụgharị aka.
Layout-aware engines (GOT-OCR, Marker, Florence-2) na-ebuli Markdown/HTML table na LaTeX maka fomulụ. Plain-text engines na-ebuli ngwe na-enweghị struct - chekwaa model a's output mode.
Unlimited-OCR 3B na-agba ọsọ na GPUs anyị site na ọha na eze gị; $ 5 → 200,000 akwụ ụgwọ tokens mgbe. ~ 300 tokens kwa peeji.
PNG, JPG, WebP, HEIC, BMP, nakwa otu na ọtụtụ ibe PDFs ruo 50 MB. A na-ewepụ ihenhọrọ ndị ahụ n'ụzọ ọbụla tupu ewepụtụ ha.
Nhazi akara bụ>98% na ihuakwụkwọ mbipụta dị ọcha, na-apụ na foto dị ala-reso, scans nke a na-atọ n'obi, mọọbụ ihumkpụrụedemede na-adịghị asị. Tụkwasị engines na /ocr/compare/ mgbe nhazi dị mkpa.
Ee - /batch/ na-anabata nsomebefaịlụ nke inyogo/PDFs. Nhazi ọbụla na-abanye na /account/?tab=history. Maka nchebe nsomebefaịlụ-tree jiri API.
Ee - POST faịlụ gị na /v1/ocr/ na model="Unlimited-OCR 3B". Na-eziga JSON na ngwe + (n'oge a na-akwado ya) nhazi + okwu-nhazi banye igbe. /api/ nwere nlekọta zuru ezu.
Self-hosted models na-echekwa faịlụ gị na GPUs anyị; premium na-aga site na DPA. Dọkumenti ahụ ehichapụ mgbe ọha-windo. Anyị anaghị arụ ọrụ na init gị.
Ee - Free.ai na-enye ọrụ n'obere n'ihe ngwe ahụ ebudatara. Ichọrọ ikikembanye n'ọnụọgụgụ dọkumenti ahụ.
1-5 sekọnd n'ihu ọfụụ. Layout-aware engines (tabs, mathematics) na-ewe ogologo oge. Multi-page PDFs na-egosipụta n'ụzọ linear.