KAKYO YOSARI (RVC V2) (100 Epochs RMVPE) (KLM 4.1)

[coral trout]

hihi !!
30 minutes dataset, 32k w/ batch size 12, aivoice extracted w/ upcon
not recommended for singing, use for talking instead.
credit as karv4 if you use, or not :p

link:
https://huggingface.co/mnkz/aimods/resolve/main/KAKYO_YOSARI_AI.zip?download=true

japanese speech demo (no index)

mandarin speech demo (no index)

eng speech demo (no index)

japanese song demo (no index)

eng song demo (no index)

mandarin song demo (no index)

this model's probably very undertrained lmfao but i didnt have anymore runtimes so

[ancient rune]

Model Ready ✅

This model has been synced with Weights and is ready to use for free!