Project Euromir

# Before Start : > - This version is an improvement on an earlier model I made on AI HUB (5 month ago), this model is pre-trained on OV2 Super (which is not the case with the old one). The new model has an batch size 4 :joe_cool: (old have 40 :nails: ). > - For me, this version is **2x better** ! :lfg: # Last Update : <t:1707174714:R> > - **Model URL :** > - https://huggingface.co/rayzox57/ProjectEuromir_RVC/resolve/main/ProjectEuromir_v2_Ov2_500e.zip > - **Version :** > - :firev2: RVC V2.0 - Ov2 Super > - **Pitch Extraction Algorithm :** > - RMVPE > - **Epochs - Steps :** > - 500 - 2.5k > - **Dataset :** > - ~ 00:00:47 [ Euromir - Liftoff! ] > - UVR + Manual Finishing > - **Recommended Usage :** > - Speech > - **Search Feature Ratio :** > - 0.75 > - **Pitch :** > - ( -10 / -4 = Man ) - Depend Base Voice > - Voice is very deep ! > - You can adjust if you find better version # Previews : > - **Preview_TTS_RU.wav :** > - *Provide* : ElevenLabs V1 - David RU > - *Contains External Effects* : Yes > - *Pitch* : -6 > - *Feature Ratio* : 0.75 > > - **Preview_TTS_EN.wav :** > - *Provide* : ElevenLabs V1 - David EN > - *Contains External Effects* : Yes > - *Pitch* : -6 > - *Feature Ratio* : 0.75 > > - **Preview_Cover.wav :** > - *Provide* : Mustard - Ballin [ My DIY Acapella ] > - *Contains External Effects* : Yes > - *Pitch* : -10 > - *Feature Ratio* : 0.75 > - *Info* : For Fun

Reference : https://www.youtube.com/watch?v=aqQEVxMqWds