KrylovDESwitch language: Deutsch

Runs entirely in your browser. Nothing is uploaded.

Vision

Language & text

Audio

            The models behind these

            These tools are other people’s research. Every model below is downloaded into your browser and run there, here is who built it, what it does, and the licence it carries.

            • Tesseract (LSTM)

              Reads printed text out of images and scans, line by line, using a recurrent network rather than character templates.

              Tesseract contributors, originally Hewlett-Packard and GoogleApache-2.0

            • ResNet-50

              Names what a photo shows, from a thousand ImageNet categories: a vision model small enough for a phone.

              Kaiming He and colleagues, via MicrosoftApache-2.0

            • YOLOS-tiny

              Finds individual objects in an image and returns a box for each, rather than labelling the picture as a whole.

              Yuxin Fang and colleagues, Huazhong University of Science and TechnologyApache-2.0

            • MoveNet Lightning

              Estimates 17 body points of a single person (shoulders, elbows, knees) and so their posture.

              The TensorFlow.js team, GoogleApache-2.0

            • Whisper tiny

              Transcribes spoken audio, detecting the language for itself as it goes.

              OpenAIApache-2.0

            • OPUS-MT (en↔de)

              Translates between German and English; a separate small model for each direction.

              The Language Technology Research Group, University of HelsinkiCC-BY-4.0

            • mBERT NER (10 languages)

              Finds names, places and organisations in text: the basis of the redaction tool.

              David Adelani, on Google’s multilingual BERTAFL-3.0

            • DistilBERT SST-2

              Judges whether an English sentence reads as positive or negative.

              Victor Sanh and colleagues, Hugging FaceApache-2.0

            • DistilBERT SQuAD

              Answers a question by marking the span of the supplied text where the answer sits.

              Victor Sanh and colleagues, Hugging FaceApache-2.0

            • T5-small

              Condenses longer text into a few sentences.

              Colin Raffel and colleagues, Google ResearchApache-2.0

            • DeBERTa-v3-xsmall NLI

              Sorts text into categories you type yourself, having never been trained on them.

              The sentence-transformers cross-encoder projectApache-2.0

            Run withtransformers.js (Joshua Lochner and the Hugging Face team, Apache-2.0)tesseract.js (Jerome Wu and contributors, Apache-2.0)TensorFlow.js (The TensorFlow.js team, Google, Apache-2.0)