The Fifth Elephant Open Source AI Hackathon 2024

GenAI makers and creators contest and showcase

Tickets

Loading…

Suhas

Speech to text for Indian Healthcare

Submitted Nov 20, 2023

Speech to text for Indian Healthcare

If you had access to a speech-to-text model which is specifically trained on English audio taken from Indian speakers, it would be more accurate than the audio models trained on general audio data. And if we extend this to the medical domain, then the accuracy of such models would be significantly higher than the SOTA models like whisper which are not trained specifically on Indian context.

In this hackathon I would like to work on this project to:

  1. Explore current speech-to-text models in Indian context
  2. Explore pulbic data-sets with audio data of Indian speakers available in english and Healthcare field
  3. Fine-tune SOTA models like whisper and distil-whisper and compare results

Currently a lot of applications are being built for health-care professionals to help digitize patient healthrecords, clinical recordings etc. With models trained for such specific domain, it will be easier for others to build applications over them.

Comments

{{ gettext('Login to leave a comment') }}

{{ gettext('Post a comment…') }}
{{ gettext('New comment') }}
{{ formTitle }}

{{ errorMsg }}

{{ gettext('No comments posted yet') }}

Hybrid access (members only)

Hosted by

The Fifth Elephant hackathons

Supported by

Host

Jump starting better data engineering and AI futures

Venue host

Welcome to the events page for events hosted at The Terrace @ Hasura. more

Partner

Providing all founders, at any stage, with free resources to build a successful startup.