# Lekhani now types 12 languages, each under 1 MB, in your browser

Canonical: https://udgamlabs.com/blog/lekhani-12 · Updated: 2026-11-14

> Type Hindi, Bengali, Marathi, Tamil, Telugu, Urdu, Gujarati, Kannada, Malayalam, Punjabi, Odia or Assamese in English letters and Lekhani writes the script, on your own device. Ahead of IndicXlit's model in all 12.

Release · 2026-11-14 · By Jitesh K Prasad

Most people who write an Indian language on a phone or a laptop don't use its script keyboard. They type it in English
letters: "kemon acho", "kem cho", "eppadi irukkeenga". Turning those letters into the language's own script is called
transliteration, and the tools that do it well usually run on a server or carry word lists of hundreds of megabytes.

Lekhani started on 30 October with Hindi, from a 0.87 MB download that runs inside a web page. Telugu, Tamil and
Kannada followed. **Today it covers 12 languages: Hindi, Bengali, Marathi, Tamil, Telugu, Urdu, Gujarati, Kannada,
Malayalam, Punjabi, Odia and Assamese. Each one is under 1 MB, and all of it runs on your own device**, so nothing you
type is sent anywhere.

<Film src="https://udgamlabs.com/models/lekhani/lekhani-12.mp4" poster="/models/lekhani/lekhani-12.jpg" caption="What Lekhani does, in about a minute. Every word on screen in a language's own script is the page's own output, recorded on the page one language at a time, at real speed." />

## What you get

| You type | Lekhani writes | Language |
|---|---|---|
| kemon acho | কেমন আছো | Bengali |
| kasa ahes | कसा आहेस | Marathi |
| aap kaise hain | آپ کیسے ہیں | Urdu |
| kem cho | કેમ છો | Gujarati |
| mazha peyyunnu | മഴ പെയ്യുന്നു | Malayalam |
| sat sri akal | ਸਤ ਸ੍ਰੀ ਅਕਾਲ | Punjabi |
| kemiti achha | କେମିତି ଅଛ | Odia |
| kene asa | কেনে আছা | Assamese |
| eppadi irukkeenga | எப்படி இருக்கீங்க | Tamil |
| ela unnaru | ఎలా ఉన్నారు | Telugu |
| hegiddira | ಹೇಗಿದ್ದೀರಾ | Kannada |
| aap kaise ho | आप कैसे हो | Hindi |

All lowercase, typed the way people text. Each of these was typed on the page itself before this post went up.

## How it works

Each language has its own small model, 0.8M or 1.2M parameters stored at 4 bits, plus a list of that language's common
words. The model reads a word letter by letter and proposes its 8 best spellings; the list moves a common real word up
when the model is unsure. A word that isn't in the list, such as a new name, still works from the model alone.

One runner, 15.8 KB of JavaScript (6.6 KB compressed) with no dependencies, serves all 12. Everything a page loads for one language (the
model, its word list, two small settings files and the runner) is between 0.71 and 1.0 MB.

## Use it in your own page

Download `translit.js` and the folder for your language from [Hugging Face](https://huggingface.co/udgamlabs/Lekhani)
or [GitHub](https://github.com/udgamlabs/lekhani), serve them next to your page (any static host works), and:

```js
import { Transliterator } from "./translit.js";

const tr = await Transliterator.load({
  model: "tamil/model.q4.gz", json: "tamil/model.json.gz",
  words: "tamil/words.bin.gz", rerank: "tamil/rerank.json",
});

tr.text("eppadi irukkeenga");  // எப்படி இருக்கீங்க
```

`tr.text()` writes every run of English letters in the language's script and leaves everything else as it is.
`tr.word()` returns the 8 spellings the model considered, best first, if you want to show suggestions as a keyboard does.
The same runner works in Node 18 or newer; the README has both examples. Nothing is sent to a server.

## The result

> **Result.** Ahead of IndicXlit's model in all 12 languages, by 4.2 to 14.8 points, from under 1 MB each.

We scored every language on the Aksharantar test (AI4Bharat): every romanised word in the test, top-1 exact match
against any reference spelling, the same words and the same scorer for every system. Each language's settings were
chosen on the validation set and the test was scored once, between 28 October and 13 November 2026.

| Language | Test words | Lekhani | IndicXlit's model | Gap (paired 95% interval) |
|---|---:|---:|---:|---:|
| Hindi | 9,991 | **65.9%** | 58.9% | +7.0 (+6.1 to +8.0) |
| Tamil | 11,405 | **74.2%** | 64.2% | +10.0 (+9.3 to +10.7) |
| Marathi | 12,059 | **70.9%** | 63.2% | +7.8 (+7.0 to +8.6) |
| Bengali | 13,367 | **70.2%** | 55.4% | +14.8 (+14.0 to +15.6) |
| Urdu | 14,617 | **57.6%** | 44.4% | +13.2 (+12.4 to +14.0) |
| Kannada | 11,165 | **79.4%** | 72.7% | +6.7 (+6.0 to +7.4) |
| Telugu | 9,936 | **81.2%** | 72.6% | +8.5 (+7.7 to +9.3) |
| Malayalam | 12,343 | **67.1%** | 59.5% | +7.6 (+6.9 to +8.4) |
| Gujarati | 17,402 | **72.8%** | 61.2% | +11.6 (+10.9 to +12.3) |
| Punjabi | 10,949 | **55.7%** | 44.5% | +11.2 (+10.3 to +12.0) |
| Odia | 4,201 | **49.9%** | 45.6% | +4.2 (+3.0 to +5.5) |
| Assamese | 5,476 | **58.6%** | 53.1% | +5.5 (+4.4 to +6.7) |

IndicXlit's model on its own has 11.5M parameters, run with its default settings. It is the comparison we set for every
language before training, and every paired interval above is clear of zero.

## Where it falls short

- **IndicXlit's full Python package is level or ahead in ten of the twelve.** It adds a word list of millions of words
  per language (358 MB in memory for Hindi). Lekhani is ahead of it only in Bengali (+2.8) and Urdu (+9.4), level in
  Tamil, Telugu, Gujarati and Punjabi, and behind in Hindi (-2.8), Marathi (-1.8), Kannada (-1.4), Malayalam (-2.1),
  Odia (-2.1) and Assamese (-1.8). If you can hold those lists in memory, the package is the more accurate choice.
- **Names are weak, except in Hindi.** In the other eleven languages, the test's name rows get 25% to 60% right on the
  first guess.
- **Odia, Punjabi, Urdu and Assamese are weak in absolute terms:** 50%, 56%, 58% and 59% of test words right on the
  first guess.
- **Odia and Assamese have no real-typing test.** Their scores cover the test's dictionary-style romanisation, not
  words as people type them in chat.
- **One word at a time, no sentence context**, and no native speaker has reviewed the misses yet; some may be accepted
  spellings that the answer lists don't include.

## Try it

- In your browser: [udgamlabs.com/models/lekhani](https://udgamlabs.com/models/lekhani#try)
- Model and files: [huggingface.co/udgamlabs/Lekhani](https://huggingface.co/udgamlabs/Lekhani)
- Demo: [huggingface.co/spaces/udgamlabs/Lekhani](https://huggingface.co/spaces/udgamlabs/Lekhani)
- Code and examples: [github.com/udgamlabs/lekhani](https://github.com/udgamlabs/lekhani)

Code and weights are open under Apache-2.0. If you write one of these languages every day, tell us which words it gets
wrong; they are what we want to fix next.

Thank you to AI4Bharat for Aksharantar, IndicXlit and IndicCorp, which this work stands on.

---

## About Udgam Labs

Udgam Labs is an independent AI research lab. We work from first principles: before we build, we understand why things work, whether we are training a model, fine-tuning one or applying AI to a new problem. Today that means open models such as Gargi, a 384M-parameter language model that comes within 2 points of Qwen2.5-0.5B on three reasoning benchmarks with about 1,000× less training data. Next come products, custom models for businesses, and AI in the physical world. Udgam (उद्गम) is Sanskrit for origin.

Udgam Labs · AI research from first principles · https://udgamlabs.com