Logo
Sign in
Sign up

Aespa - Karina (에스파 카리나) RVC2 - 1050 Epochs

Created: January 5, 2024
Aespa - Karina (에스파 카리나) RVC2 - 1050 Epochs

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%3Fdownload%3Dtrue?download=true Hosted on Hugging Face

Convert this model in EasyAIVoice

Original Link: https://huggingface.co/SeoulStreamingStation/IU-Voice-MultiLanguage-V1/resolve/main/Karina_V1.zip?download=true (404 not found)

Auto-resolved Link: https://huggingface.co/SeoulStreamingStation/IU-Voice-MultiLanguage-V1/resolve/main/Karina_V1.zip%3Fdownload%3Dtrue?download=true

Sample deck

Pitch previews

Listen across generated pitch samples, then Run. Hold Ctrl or Cmd to select multiple pitches.

samples ready
female base · pitch 0 Generated female reference sample
Run
male
female
female-base generated sample male-base generated sample Enrichment pending: no scores or voice accords yet Ctrl/Cmd-click = select multiple pitches