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.
17,000 hours of raw speech data for 40 Indian languages from a wide variety of domains including education, news, technology, and finance
State-of-the-art open-source ASR models for 9 languages (including Nepali and Sinhala) as measured on public benchmarks.
Over 6,400 hours of labelled audio across 12 Indian languages mined and aligned from audio broadcasts and PDF transcripts from All India Radio.
A benchmark of speech recognition tasks including ASR, speaker verification, speaker identification, language identification, query by example, and keyword detection for 12 Indian languages.
Much smaller ASR models which can be quantized and executed on Android devices to support privacy-preserving inference on personal devices.