Downloads · 30 days
0
rvc-ringformer-v2-pretrain
its5Q/rvc-ringformer-v2-pretrain
rvc-ringformer-v2-pretrain is a audio-to-audio model from its5Q. Use it for the audio-to-audio task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
Pretrained RingFormer v2 from codename's RVC fork
Access
Public
Updated Nov 12, 2025
Repo size
520 MB
Likes
2
Public
Repo makeup
Click a slice to open those files.
.pth520 MB · 100%
At a glance
- Task
- Audio-to-Audio
- License
- mit
- Access
- Public
- Created
- Nov 4, 2025
- Updated
- Nov 12, 2025
- SHA
- 2bfb5572
Model card
From the Hugging Face model README
Summary
Pretrained RingFormer v2 from codename's RVC fork
Sample rate: 40000
Embedder: Spin v2
Mel Loss: Experimental L1 + MR-STFT loss
F0: RMVPE
Precision: FP16 / FP32 mixed (BF16 proved to be very imprecise in ablation tests, achieving way worse loss values, I don't recommend using it for training any RVC models)
Speakers: 225
Dataset length: 235:31:50, of which 37:26:53 is Russian, rest is English.
First checkpoints in the upcoming days, haven't finished training yet
- Task
- Audio-to-Audio
- License
- mit
- Languages
- ru, en
- Created
- Nov 4, 2025
- Updated
- Nov 12, 2025