Hugging Face trending model Diamond-1.0 targets audio-to-audio speech enhancement

nineninesix · hf · 2026-07-21

`nineninesix/diamond-1.0` is trending on Hugging Face as an audio-to-audio model. Its listed use cases include speech restoration and speech enhancement, and the model card tags it with autoregressive audio modeling and neural audio codecs.

Original post →

More from Multimodal

Multimodal channel →