Apply for community grant: Company project (gpu and storage)
#1
by
gaganyatri
- opened
Dhwani is a self-hosted GenAI platform designed to provide voice mode interaction for Kannada and other Indian languages.
Research Goals
- Measure and improve the Time to First Token Generation (TTFTG) for model architectures in ASR, Translation, and TTS systems.
- Develop and enhance a Kannada voice model that meets industry standards set by OpenAI, Google, ElevenLabs, xAI
- Create robust voice solutions for Indian languages, with a specific emphasis on Kannada.
ASR(Indic Conformer) on CPU + TTS (Parler-tts) on GPU + LLM(Qwen-2.5-3B) on GPU + Translate(IndicTrans) on CPU + VLM (moondream) for Indian languages, currently focussed on kannada.
Currently running on T4 instance. Would help to upgrade to 24GB/ 48GB instance to provide better results for Kannada/Indian language