pix2struct-tiny-randomby fxmartyπ₯οΈ GPUFP16β¬ 4.8Kβ₯ 2image-to-textMultimodalmitlicense:mitView on Hugging Face
react-native-executorch-pp-ocrv6by software-mansionβ‘ CPU/GPUβ¬ 4.6Kβ₯ 0image-to-textMultimodalapache-2.0license:apache-2.0View on Hugging Face
thai-trocrby openthaigptπ₯οΈ GPUFP16β¬ 4.6Kβ₯ 28image-to-textMultimodalapache-2.0license:apache-2.0View on Hugging Face
Electricity-Meter-OCR-7Bby Word2Liπ₯οΈ GPUFP16~17 GB7B paramsβ¬ 4.5Kβ₯ 2image-to-textMultimodalmitlicense:mitView on Hugging Face
chexpert-mimic-cxr-impression-baselineby IAMJBπ₯οΈ GPUFP16β¬ 4.4Kβ₯ 0image-to-textMultimodalmitlicense:mitView on Hugging Face
mscoco_finetuned_CoCa-ViT-L-14-laion2B-s13B-b90kby laionπ₯οΈ GPUFP16~32 GB13B paramsβ¬ 4.4Kβ₯ 23image-to-textMultimodalmitlicense:mitView on Hugging Face
cyrillic_PP-OCRv5_mobile_recby PaddlePaddleβ‘ CPU/GPUβ¬ 4.4Kβ₯ 0image-to-textMultimodalapache-2.0license:apache-2.0View on Hugging Face
PP-OCRv4_mobile_detby PaddlePaddleβ‘ CPU/GPUβ¬ 4.2Kβ₯ 5image-to-textMultimodalapache-2.0license:apache-2.0View on Hugging Face
hayai-ocr-v2by JustANormalTinkererπ₯οΈ GPUFP16β¬ 4.2Kβ₯ 8image-to-textMultimodalapache-2.0dataset:hal-utokyo/manga109-slicense:apache-2.0View on Hugging Face
LightOnOCR-2-1B-ocr-soup-GGUFby noctrexπ» CPUGGUF~1 GB1B paramsβ¬ 4.1Kβ₯ 10image-to-textMultimodalconversationalView on Hugging Face
FuseCap_Image_Captioningby noamrotπ₯οΈ GPUFP16β¬ 4.1Kβ₯ 23image-to-textMultimodalmitlicense:mitView on Hugging Face
nougat-smallby facebookπ₯οΈ GPUFP16β¬ 4.1Kβ₯ 35image-to-textMultimodalcc-by-4.0license:cc-by-4.0View on Hugging Face
PP-DocBlockLayoutby PaddlePaddleβ‘ CPU/GPUβ¬ 4.1Kβ₯ 5image-to-textMultimodalapache-2.0license:apache-2.0View on Hugging Face
pix2text-mfr-1.5by breezedeusπ» CPUONNXβ¬ 4.1Kβ₯ 3image-to-textMultimodalmitlicense:mitView on Hugging Face
th_PP-OCRv5_mobile_recby PaddlePaddleβ‘ CPU/GPUβ¬ 4.0Kβ₯ 3image-to-textMultimodalapache-2.0license:apache-2.0View on Hugging Face
DeQA-Score-Mix3by zhiyuanyouπ₯οΈ GPUFP16β¬ 4.0Kβ₯ 7image-to-textMultimodalmitlicense:mitView on Hugging Face
blip-image-captioning-baseby zhao-liyingβ‘ CPU/GPUβ¬ 4.0Kβ₯ 0image-to-textMultimodalbsd-3-clauselicense:bsd-3-clauseView on Hugging Face
crnn-fa-license-plate-recognition-v2by hezaraiβ‘ CPU/GPUβ¬ 3.9Kβ₯ 4image-to-textMultimodaldataset:hezarai/persian-license-plate-v1View on Hugging Face
PP-LCNet_x1_0_table_clsby PaddlePaddleβ‘ CPU/GPUβ¬ 3.9Kβ₯ 2image-to-textMultimodalapache-2.0license:apache-2.0View on Hugging Face
blip-large-long-capby unographyπ₯οΈ GPUFP16β¬ 3.9Kβ₯ 5image-to-textMultimodalbsd-3-clauselicense:bsd-3-clauseView on Hugging Face
Uni-MuMER-Qwen3-VL-2Bby phxemberπ₯οΈ GPUFP16~5 GB2B paramsβ¬ 3.8Kβ₯ 0image-to-textMultimodalapache-2.0dataset:phxember/uni-mumer-datalicense:apache-2.0View on Hugging Face
PP-OCRv3_mobile_recby PaddlePaddleβ‘ CPU/GPUβ¬ 3.7Kβ₯ 1image-to-textMultimodalapache-2.0license:apache-2.0View on Hugging Face
Falcon-OCRby tiiuaeπ₯οΈ GPUFP16π§²βTorrent availableβ no seedersβΊβ¬ 3.6Kβ₯ 175image-to-textMultimodalapache-2.0license:apache-2.0View on Hugging Face