Name: sanah | AI RVC Model
Brand: Weights
Rating: 4.8 (13 reviews)

WebKit

 Discover the innovative Sanah (Polish Singer) AI Voice Model from Weights, specially designed using Retrieval-Based Voice Conversion (RVC) Technology. Based on the advanced RVC V2 Model and trained with Crepe V2, this model delivers highly accurate and natural vocal reproductions. With its ability to generate authentic Polish singing tones, users can now create stunning AI covers, personalized text-to-speech messages, and even explore AI music generation like never before. Explore your creativity without limits - try out our FREE AI Tools today and experience extraordinary voice conversion results with just a few clicks. Join us at Weights as we revolutionize the way you interact with artificial intelligence!

Retrained from the RVC V1 one! Made by me Same Dataset Trained with crepe V2 20th RVC V2 Model. USE FEATURE RATIO TO 1.0 ALWAYS. Credit to me on Youtube & TikTok. UPDATED: Retrained with Mangio-Crepe Extraction.

sanah

sanah (Polish Singer)

CrimsonZockt

All of my RVC V1 models have been retrain to RVC V2 models! You can use covers for a good quality!
Huggingface link Up!

https://huggingface.co/CrimsonZockt/RVC-Model/resolve/main/sanahV2.zip

Join the server if you are interested in Polish AI Models.
https://discord.gg/9vkWFbpeT2

sanah (Polish Singer) (RVC V2) 300 Epochs

Trained on Applio Locally OG Pretrain, Sample Rate 48k, contentvec Embedder, HifiGAN Vocoder, Batch Size 4, FP16 Precision, And 18 Minutes Dataset (Album) Index Ratio 1.0 Recommended Credit to me On Youtube (@FuturisticLabelAI) & Tiktok (@futuristiclabelai)

Julia Posnik (Egoistka Era)

Julia Posnik (Egoistka Era) (RVC V2) (RMVPE) (350 Epochs)

Trained on Applio Locally I decided to on the version v3! This old one must be promise OG Pretrain, Sample Rate 48k, contentvec Embedder, HifiGAN Vocoder, Batch Size 4, FP16 Precision, And 9 Minutes Dataset (All Singles and so on) Index Ratio 1.0 Recommended Credit to me On Youtube (@FuturisticLabelAI) & Tiktok (@futuristiclabelai)

Blanka Stajkow (All-Round)

Blanka Stajkow (All-Round) (RVC V2) (RMVPE) (300 Epochs)

Trained on Applio Locally One Song "SMUTNO MI" had cutoff 16hz so, I used AudioSR. I don't use AudioSR because sucks! OG Pretrain, Sample Rate 48k, contentvec Embedder, HifiGAN Vocoder, Batch Size 4, FP16 Precision, And 20 Minutes Dataset (Only Songs) Index Ratio 1.0 Recommended Credit to me On Youtube (@FuturisticLabelAI) & Tiktok (@futuristiclabelai)

Julita Maria Kosy (Marie) (Babygirl Era)

Julita Maria Kosy (Marie) (Babygirl Era) (RVC V2) (RMVPE) (350 Epochs)

Trained on Applio Locally TITAN Pretrain, Sample Rate 40k, contentvec Embedder, Batch Size 4, FP16 Precision, And 24 Minutes Dataset (Mniejszeodtrzech Album) Index Ratio 1.0 Recommended Credit to me On Youtube (@FuturisticLabelAI) & Tiktok (@futuristiclabelai)

Magda Bereda (Mniejszeodtrzech Era)

Magda Bereda (Mniejszeodtrzech Era) (RVC V2) (RMVPE) (550 Epochs)

REPOSTED Trained on Applio Locally TITAN Pretrain, Sample Rate 40k, contentvec Embedder, Batch Size 4, FP16 Precision, And 11 Minutes Dataset (nitki Album) Index Ratio 1.0 Recommended Credit to me On Youtube (@FuturisticLabelAI) & Tiktok (@futuristiclabelai)

sanah

Description

Samples

Sanah

Susanahoria