diamond-1.0
A sequence-to-sequence model for speech restoration via an autoregressive RQ-Transformer over neural audio codec tokens.
audio → audio · made by nineninesix
Sold by
Nobody in the catalogue publishes a price for this yet.
About
diamond-1.0 — an audio model from nineninesix.
It takes audio and returns audio. It was published in July 2026. The catalogue files it under speak. Its weights are published under APACHE-2.0, so you may run it on your own machine, or buy it from whoever serves it cheapest.
Every current figure
- Maker
- nineninesix
- Register
- model
- Takes
- audio
- Returns
- audio
- Published
- July 2026
- Licence
- apache-2.0
Known as 1 name
nineninesix/diamond-1.0