Models/IndicConformer ASR
IndicConformer ASR mark

IndicConformer ASR

BaseOpen-sourceMultilingualEnglishঅসমীয়াবাংলা+20 more

In plain words

IndicConformer ASR is a speech-to-text model that listens to spoken audio and writes out what was said as text. It is built for India and handles all 22 official Indian languages in a single multilingual model. It is open source and free to run yourself, and is not a chatbot or text generator.

How to use it

🚧
This model is coming soon!
A step-by-step guide for IndicConformer ASR will appear here once it goes live.

Languages & scripts supported

Works in these languages, in both native script and Roman typing.

English Englishঅসমীয়া Assameseবাংলা Bengaliबड़ो Bodoडोगरी Dogriગુજરાતી Gujaratiहिन्दी Hindiಕನ್ನಡ Kannadaکٲشُر Kashmiriकोंकणी Konkaniमैथिली Maithiliമലയാളം Malayalamমৈতৈলোন্ Manipuri (Meitei)मराठी Marathiनेपाली Nepaliଓଡ଼ିଆ Odiaਪੰਜਾਬੀ Punjabiसंस्कृतम् Sanskritᱥᱟᱱᱛᱟᱲᱤ Santaliسنڌي Sindhiதமிழ் Tamilతెలుగు Teluguاردو Urdu+ Roman & code-mixed

Strengths & limits

An honest look at what it does well and where it struggles.

Good at
Turning Indian-language speech into text
Covering all 22 official languages
One model for many languages
Self-hosting at no cost
Where it struggles
!Audio only, not text chat
!Cannot answer questions or generate text
!Accuracy varies by language and accent
!Needs clean audio for best results

About the maker

Who builds and maintains IndicConformer ASR.

AI4Bharat logo
AI4Bharat
4 models

AI4Bharat is an open-source research lab at IIT Madras dedicated to advancing AI for Indian languages. Its freely released datasets, benchmarks, and models — like Airavata and the IndicTrans translation series — are widely used across research and industry.

Compare

More like this

Comparable models you may also want to try.