Hugging Face's logo

Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up
Back to feed
YatharthS 
posted an update 5 days ago
Post
3804
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: YatharthS/NovaSR
Space to try it: YatharthS/NovaSR
Github repo: https://github.com/ysharma3501/NovaSR
MihaiPopa-1

Did you try my TinySR?
Model: https://huggingface.co/MihaiPopa-1/TinySR
Space (I used GPT-5 mini for this): https://huggingface.co/spaces/MihaiPopa-1/TinySR-Demo
It works at like 6x runtime on the CPU and it's only 57.6 KB!

·
YatharthS

Yeah seems very cool, great work!
JymNils
•
edited about 24 hours ago

i guess this will be by default included on MIRATTS, can you deploy a ONNX version of it, so bouth have the same format?

·
YatharthS

Hey, I am working on a new TTS model called LuxVoice which will include this instead and I’ll try my best to convert this to onnx as well.

In this post