V1 version. In the current version, there is a lack of high-pitched vocal data for Karina, resulting in phase issues. (Refer to the sample below) It can be used for general music covers, but it is not suitable for songs in the ultra-high pitch range.

Information :

Model :
Model Name : Karina (카리나)
Job : Kpop Idol

Train info :
RVC 2
1050 Epochs
Batch size per GPU : 40

Dataset - source Info :
12 mins of speech
8 mins of Rebuilt Speech source
3 mins of Sing

Dataset - source correction :
Volume Normalizing (V1)
Basic de-noise (V1)

Model Link - https://huggingface.co/SeoulStreamingStation/IU-Voice-MultiLanguage-V1/resolve/main/Karina_V1.zip?download=true

Additional Details:

Tags: No tags available

Download Link: https://huggingface.co/SeoulStreamingStation/IU-Voice-MultiLanguage-V1/resolve/main/Karina_V1.zip?download=true