Back to News
YatharthS•April 1, 2023
LavaSR
Open Source
Audio
### TL;DR
LavaSR is a lightweight and high-quality speech enhancement model designed to improve low-quality audio inputs. It utilizes a 50MB bandwidth extension model combined with the UL-UNAS denoiser to restore and enhance speech effectively.
Key Insights & Metrics
Pricing
Free
Cost structure
Version
1.0
Current release version
Hardware
CPU: Any modern processor; GPU: Any CUDA-compatible GPU for accelerated inference
Compute requirements
Category
Open Source
Licensing model
Region
Unknown
Primary region
Key Features
- 50MB model size for efficient deployment
- Supports input rates from 8-48kHz, outputting at 48kHz
- Inference speeds ranging from 10-50x real-time on CPU and 400-4000x real-time on GPU
- Enhances low-quality audio datasets, TTS, ASR models, and voice calls
Discussion
0
Upvotes
0
Downvotes
0 reviews
Sign in to leave a review
Reviews
No reviews yet. Be the first to review!