Description
its been a long time since ive posted here here is my version with a clean dataset and a good pretrain :3 edit: btw this is from cbt1, i got access to the current audio files at the moment of editing this message, the model was made before i got the new audio files Info: Sample rate: 32k Batch size: 32 Pretrain: Original Precision: Fp32 Pitch extraction method: Rmvpe Dataset info: 2:45 minutes of audio, from youtube because we don't have the actual audio files yet>:(
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
More to explore
Tamer
32
Loading more