base speaker TTS training codes needed for fair comparison

[xvdp]

the distance between the base speaker and extracted tonecolor makes the result not too good. The alternative, using openais Base Speaker is not satisfactory for an "open" project.

Are you intending to release training codes and if so when? Thank you

[Zengyi-Qin]

After https://github.com/myshell-ai/OpenVoice/issues/13#issuecomment-1873596951 you can have the training code for a better base speaker model.

[dilerbatu]

When will you publish this update ?