# Shruti Maithili

Canonical: https://udgamlabs.com/models/shruti/maithili · Updated: 2026-11-07

Models · Shruti · 29.7 MB · released 7 November 2026

Speech to text for Maithili and English, on your device, with no server.

Try it in your browser: [https://udgamlabs.com/models/shruti/maithili#try](https://udgamlabs.com/models/shruti/maithili#try)

Shruti Maithili · 29.7 MB · Maithili and English · 7 November 2026

## Maithili and English in one 29.7 MB file that runs on your device.

Shruti Maithili writes Maithili in Devanagari, and it keeps English words in English letters, as here: आब packet बना कऽ online बेचबाक विचार कऽ रहल छी. It is one small file, and we make no comparative claim for it: IndicConformer Maithili is ahead or level on every test we ran. It runs offline on a five-year-old phone, about 9× faster than real time in 64 MB of memory with the native engine, and it invented no words on 100 silent clips.

| Model | File | IndicVoices valid | DiarBench, English in English | DiarBench, native |
| --- | --- | --- | --- | --- |
| Shruti Maithili | 29.7 MB | 42.5 | 45.7 | 51.2 |
| IndicConformer Maithili | 137.7 MB | 39.3 | 46.9 | 40.2 |

Word error rate %, lower is better; DiarBench 54 turns, the same scorer for every model, measured 3 November 2026. IndicVoices valid is IndicVoices’ own held-out split: its speakers are kept out of training and its sentences blocked, but it is the same source as our training data, so it flatters us. DiarBench is real conversation from outside it: 54 turns from 15 conversations, 727 reference words, 109 of them English, in 30 turns. The English-in-English column scores against references that write English words in English (Latin script), and English words count only if written in English letters; the native column scores against references that write those English words in Devanagari. Other Maithili speech models exist that we have not measured; these results cover only the models listed here.

### Where it falls short

- IndicConformer Maithili is ahead or level on every test. IndicVoices valid 42.5 vs 39.3 (+1.01 to +5.73), DiarBench native 51.2 vs 40.2 (+6.67 to +14.77), DiarBench English in English 45.7 vs 46.9 (-6.29 to +3.88). Character errors on DiarBench 31.26% vs 15.02%.
- A small test. 54 turns from 15 conversations, 30 of them with English, 109 English words. It can’t say much either way, including whether the two are level.
- Unmeasured rivals. rockerritesh/whisper-tiny-maithili (151.1 MB, about 44 MB as q8\_0) and others exist. We have not measured them.
- English words in Devanagari: about 34 of DiarBench’s 109 by automatic alignment (shastri as शास्त्री). DiarBench also glosses some local names in Latin, so a correct native spelling can score as an error.
- In a browser it was tested on 5 lines played into this page on one phone’s Chrome, with the language set. All 5 came out in Devanagari, and 3 kept some English letters. Not yet tested with a live microphone. On the other Shruti languages where we measured it, plain English loses a little accuracy this way.
- No Maithili reader has reviewed this output yet.
- Loud noise: Shruti models sometimes repeat a phrase over and over in loud noise (measured on Shruti Hindi-family models, not on Maithili).
- Not tested on Maithili: noise, music, far-away or speaker-played audio, Linux, Windows and iOS. No punctuation; numbers come out as words.

[Try Shruti Maithili](#try) [Shruti Maithili on Hugging Face](https://huggingface.co/udgamlabs/shruti-maithili) the model file, the full results and how each model was run

## Use it in your app

Every Shruti model runs in Cactus’s open-source needle engine. Download the engine for your platform and the file for your language, and pass it a WAV file or 16 kHz audio.

```
# Command line (Mac, Linux, Windows)
# Engine: huggingface.co/Cactus-Compute/needle3, your platform
# Model:  shruti-maithili.cact, from Shruti Maithili's Hugging Face repo
./needle --model shruti-maithili.cact --audio clip.wav
# for speech that is only English: --audio-language en

# Python
pip install cactus-needle

import needle
shruti = needle.Whistle(weights="shruti-maithili.cact")
print(shruti.transcribe("clip.wav")["text"])
```

- Android, iOS and the web: call the engine’s C API. `needle_load` takes the model file, `needle_transcribe` a clip, and `needle_stream_transcribe_process` about a second of live audio at a time. The demo on this page makes the same calls, from WebAssembly in a Web Worker.
- Leave the language unset for Hindi and Hinglish: detection does as well as setting it on Hindi, Hinglish, accented Hindi and US English. Set English when the speech is only English with an Indian accent, which detection often takes for Hindi. On a subset of Svarah: 21.13% word errors with English set, 25.75% detected.
- Keywords, one per line, favour the names, places and product words your users say.
- Cactus’s Python package (cactus-needle) sends anonymous usage counts by default; set `NEEDLE_TELEMETRY=0` to turn that off. The command-line engine and the WebAssembly engine on this page make no network requests of their own.

## Credits

Every Shruti model is built on [Cactus Whistle](https://huggingface.co/Cactus-Compute/whistle) and runs in the [needle engine](https://github.com/cactus-compute/needle), both by Cactus Compute under Apache-2.0. The engine files on this page are Cactus’s WebAssembly build, unmodified, served with [its licence](https://udgamlabs.com/models/shruti/needle/LICENSE.txt) and [notice](https://udgamlabs.com/models/shruti/needle/NOTICE.txt). Shruti Maithili’s model card on Hugging Face lists its training datasets and their licences.

[Every Shruti language](https://udgamlabs.com/models/shruti#languages)

---

## 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