Yatharth Sharma's picture

9 2 24

Yatharth Sharma

YatharthS

·

AI & ML interests

TTS, speech generation, Agents, MCP

Recent Activity

replied to their post about 9 hours ago

I just released NovaSR, a tiny 52kb audio upsampler that can enhance 3600 seconds of muffled 16khz audio in to clearer 48khz audio in just 1 second! NovaSR can - Enhance TTS model quality. - Restore poor quality datasets. - Work on any device(just 52kb which is smaller than a 3 second audio file!) Model: https://huggingface.co/YatharthS/NovaSR Space to try it: https://huggingface.co/spaces/YatharthS/NovaSR Github repo: https://github.com/ysharma3501/NovaSR

updated a model about 9 hours ago

YatharthS/LuxVoice

liked a model about 12 hours ago

YatharthS/LuxVoice

View all activity

Organizations

YatharthS 's models 6

YatharthS/LuxVoice

Text-to-Speech • Updated about 9 hours ago • 1

YatharthS/NovaSR

Audio-to-Audio • Updated 4 days ago • 257 • 54

YatharthS/LinaCodec

Audio-to-Audio • Updated 15 days ago • 185 • 19

YatharthS/FlashSR

Audio-to-Audio • Updated 24 days ago • 52

YatharthS/MiraTTS

Text-to-Speech • 0.5B • Updated 26 days ago • 7.7k • 181

YatharthS/LayaCodec

Audio-to-Audio • Updated Dec 14, 2025 • 37 • 12