This model consists solely of pure speech data without any vocal data. It is created and distributed to test whether the KLM 4.4 X1 pre-trained model functions as intended for its purpose.
Info -
DataSet :
Conversational - 24 Mins
Recitative tone - 21 Mins
Dramatic tone - 11 Mins
Train :
Loops : 365
BSP GPU : 16
Model Link -
https://huggingface.co/SeoulStreamingStation/RVC_Voice_Models/resolve/main/Voice_Sion.zip?download=true