Description
Model Info - Architecture: RVC - Vocoder: NSF-HiFiGAN - Sample Rate: 32kHz - F0 Extraction: RMVPE - Embedder: ContentVec - Pretrain: Legacy Core - Precision: BFloat16 Training Details - Epochs: 413 - Dataset Length: 13m 21s - Batch Size: 8 NOTE: i recommend setting the feature ratio to 0.5 Download
Comments
No comments yet. Start the conversation!
Add a comment
Samples
New
Classic
1. Singing
Male
English
2. Singing
Female
English
3. Singing (Dry)
Female
English
4. Singing (High)
Female
English
5. Singing 2
Male
English
6. Singing (Dry)
Male
English
7. Singing (Dry, High)
Male
English
Pitch
![RM of BTS [KLM KPU II 32K]](https://imgproxy.weights.com/insecure/size:288:0/resizing_type:fill/plain/https://assets.weights.com/model_images/cmewmygpc00031x427s139nri/0373e4ccfb96336bdab30dba72815284.jpg)
More to explore
SOOBIN of TXT
9.1k
🐻TXT BEOMGYU
1.9k
TXT Beomgyu
20k
Choi Yeonjun
1.6k
yeonjung
86
yeonjun
50
Soobin txt
366
TXT Kai
23
Loading more
