nicholas-cc

We're working on a HuggingFace release that will help with finetuning. We'd like to do a paper, after a larger release - we're a team of 4.

Moshi is a good model to build chat applications on, this is designed to be more of a proper base model with all the quirkiness, naturalness, and researcher-friendliness of base modeling.

Yes

Hertz-dev is a base model, meaning it's just trained to predict the next token of audio. If your prompt is an old male voice with a British accent, the model will most likely continue speaking in an old male voice with a British accent. Being a base model, hertz-dev is easily finetunable for specific tasks - it would be a simple change to add manual configurations for the gender/age/accent.

I'm one of the devs. Our model is fully voice-to-voice, no text was involved in the making of hertz-dev for exactly this reason.

It seems like if you choose to record transactions to the blockchain you end up posting every transaction to the blockchain which is quite expensive; why not only store the hash of the HTTP request and use a Merkle Tree to store multiple requests in a single Bitcoin transaction? The only reason I see why not is that then the actual request data could be lost or not revealed, but since this protocol saves all requests to an internal database as well, I don't see why that would be a problem.