Mias Amazing RVC Model Pack
https://huggingface.co/redoverflow/two_tpot/resolve/main/two_tpot.zip?download=true
Audition Across 18 Pitch References
Click any semitone cell below to hear how this voice performs on female and male reference vocals and lock your preferred pitch.
Our worker is generating the 18-pitch reference samples for this model. You can already use this model immediately in EasyAIVoice or download the raw weights from Hugging Face.
Run Model in EasyAIVoice Now →Sonic Profile at Selected Pitch
Acoustic traits measured directly from the generated output sample. Switch pitches in the Sample Deck to see how timbre shifts.
Architecture: RVC v2 · Source Host: Hugging Face
Voices That Sound Like Mias Amazing RVC Model Pack
Close but not quite the right fit? Audition nearby candidates matched by vocal embedding and timbre.
About Mias Amazing RVC Model Pack
haiiiii i decided to collect all my new and old models into a pack here note: new models have a password on them which you can find in the repo note 2: model examples are included within the archive # English models ## New models - **Laura Les (100 gecs) [503 epochs]** - trained on 6:22 minutes of cleaned up official acapellas from the **1000 gecs** and **1000 gecs and The Tree of Clues** albums. Louder vocals produce more autotuned/processed results, quieter ones produce calmer and unprocessed results. <https://huggingface.co/redoverflow/myrvcmodels/blob/main/100gecsv2.7z> ## Old models - **Two (The Power of Two) [500 epochs]** - trained on 8:56 minutes of cleaned up voice from most TPOT episodes (i dont remember which). <https://huggingface.co/redoverflow/two_tpot/blob/main/two_tpot.zip> - **Wilbur Soot (Singing) [370 epochs]** - trained on almost 2 hours of (poorly) cleaned up acapellas. Of course, this model really sucks, I will remake it somewhere in the future. <https://huggingface.co/redoverflow/wilbursoot/blob/main/wilbursoot.zip> - **jschlatt funny mic mode [450 epochs]** - trained on 3:33 minutes of pure funny mic yelling. Higher pitches produce the yelling effect, lower ones actually have a more calmer voice. <https://huggingface.co/redoverflow/schloggie_funnymic/blob/main/schloggie_funnymic.zip> # Russian models ## New models - **Pomni (The Amazing Digital Circus) (RU) [515 epochs]** - trained on 1:30 minutes of cleaned up voice from the pilot episode. <https://huggingface.co/redoverflow/myrvcmodels/blob/main/rus_pomni.7z> ## Old models - **Lida (Russian Artist) [300 epochs]** - this models dataset was prepared poorly (the model is pretty old afaik), theres a lot of autotune and it sounds really dirty. <https://huggingface.co/redoverflow/lidav2/blob/main/lida.zip> - **SO2 Bomb Voice [300 epochs]** - joke model. Works surprisingly well. <https://huggingface.co/redoverflow/so2bombvoice/blob/main/so2bombvoice.zip> - **the satoruu (vocalist of ) [400 epochs]** - trained on 40 minutes of (poorly) cleaned up dataset. Model barely sounds good. <https://huggingface.co/redoverflow/theendofsunnydays/blob/main/theendofsunnydays.zip>