A large-scale pre-trained RVC model specialized for Japanese pronunciation
Overview
Kuromame is a pre-trained model focused on breath (inhale/exhale) to achieve authentic Japanese pronunciation and realistic vocal delivery.
Why Only 32 kHz?
Higher sampling rates such as 48 kHz turned out to be extremely sensitive to handle, with almost no audible benefit.
While they might slightly reduce latency during real-time inference, the difference is negligible.
When fine-tuning for a target speaker, higher rates often caused issues such as reverberation noise and instability.
After considering multiple factors, the model outputs at 32 kHz by design.
If additional high-frequency range is desired, it’s better to expand it afterward using tools like an expander or similar processing.
Phase-wise Configuration and Fine-tuning
Each phase was carefully constructed by adjusting various configurations including the following augmentations, D/G learning rate, lambda_adv,lambda_fm,lambda_spectral, based on inference results.
Model Details
V1
- RefineGAN / SpinV2
- 119 Speakers(All japanese): 41 Hours
- SR: 32Khz
- Batch 64
- bf16
V2
- RefineGAN / SpinV2
- 361 Speakers(All japanese): 240 Hours (Separate speakers based on speaking style and vocal delivery.)
- SR: 32Khz
- Batch 32
- fp32