gpu-sankhya

Indian Number Shorthand
to Real Numbers

A small neural model, running locally in your browser

Try it out Type any amount phrase
Result
parsing… Wrong? Report it
Fraction word Number Unit Currency Range
Developer options
drop spans the lexicon can’t fully justify
0%
backend: CPU · WebGPU: checking…

        

Tap One, See the Number

Each of these runs in the box above

Use It in Your Code

You pass the phrase. You get back the span, the value, the unit, the currency and a calibrated confidence

$ npm install gpu-sankhya

import { parse } from "gpu-sankhya";

const spans = parse("sava lakh ka phone");

// spans[0] → { span: "sava lakh", start: 0, end: 9,
//              value: 125000, unit: "lakh", currency: null,
//              confidence: 0.97, verified: true,
//              tokens: [["PFX_SAVA","sava"],["UNIT_LAKH","lakh"]] }

// gate it:  parse(text, { strict: true, minConfidence: 0.9 })
// bulk it:  await parseBatch(texts, { backend: "webgpu" })

Inside the Model

A char-level CNN tags every character; a deterministic arithmetic core does the maths, so the value can never be hallucinated

Per-character tags
Decoded tokens
Arithmetic

Characters to classes to a number, in 40,475 parameters