AI4BHARAT

Speech Recognition

AI technologies for speech recognition hold promise to enable a variety of use-cases, including providing input tools for lower literacy users. AI4Bharat has a deep focus on building state-of-the-art speech recognition in many Indian languages and in ensuring that the models are deployable on mobile devices.

Our contributions

Dhwani Dataset

17,000 hours of raw speech data for 40 Indian languages from a wide variety of domains including education, news, technology, and finance

Know More →

Updated
IndicWav2Vec

State-of-the-art open-source ASR models for 9 languages (including Nepali and Sinhala) as measured on public benchmarks.

Know More →

Coming Soon
Pratilipi Dataset

6,000 hours of speech and text for 10 Indian languages mined and aligned from audio broadcasts and PDF transcripts. from All India Radio.

Know More →

Coming Soon
IndicSUPERB

A benchmark of speech recognition tasks including ASR, speaker verification and identification, and keyword detection for 10 Indian languages.

Know More →

Coming Soon
On-Device ASR

Much smaller ASR models which can be quantized and executed on Android devices to support privacy-preserving inference on personal devices.

Know More →

Coming Soon
Chitralekha

Chitralekha is an open-source tool for video transcription with IndicASR models with additional translation and transliteration support.

Know More →

Our Partners

DesiCrew

We are working with Desicrew to collect voice samples from across 500 districts in the country. We are beginning with TamilNadu in August 2022.

Karya

Karya is an application developed at Microsoft Research and maintained by Karya Inc. We are using Karya to collect voice samples from across the country.

NPTEL

We are working with NPTEL to deploy the Chitralekha tool for subtitling and translating higher education videos.

IndicASR Workshop

On 28th July, we are conducting a workshop to demonstrate our datasets, models, and applications.

Learn more