NEWVectors or files. Pick a path.Start →
    Models/Image To Text/microsoft/trocr-base-printed
    Image To Texttransformers

    trocr-base-printed

    by microsoft

    384Kdl/month
    209likes
    Identifier
    Model ID
    microsoft/trocr-base-printed

    Tags

    transformerspytorchsafetensorsvision-encoder-decoderimage-text-to-texttrocrimage-to-textarxiv:2109.10282endpoints_compatibleregion:us

    Use trocr-base-printed on Mixpeek

    Build multimodal processing pipelines with this model and others. Extract features, run inference, and set up retrieval in Mixpeek Studio.

    Open Studio

    How It Runs on Mixpeek

    On Mixpeek, trocr-base-printed runs as a managed extractor inside a processing pipeline. Point a bucket of image to text data at it, and Mixpeek handles GPU provisioning, batching, retries, and writing the outputs into a vector store you can query.

    Extractor outputs land in the Mixpeek Vector Store (MVS), where you can combine them with retrieval, reranking, and filter stages to build end-to-end search and agent-perception pipelines, no model-serving infrastructure to maintain.