Finetuning code?
#5
by Hanswalter - opened
I love the quality! Thanks for sharing this. Can you please also share the finetuning code? Pretty much useless without. Thanks again! If not, I could just use S2... :-(
Not planning on releasing the training code, but we've put more or less everything you'd need to know into the research paper: https://mistral.ai/static/research/voxtral-tts.pdf
So then why was the model given? If the fine tuning and voice cloning is all closed, then this model is useless. There are better open source models than this which can be used. 🙄
patrickvonplaten changed discussion status to closed