Pitch previews
Listen across generated pitch samples, then Run. Hold Ctrl or Cmd to select multiple pitches.
When i was trying to remove the sound effects from the dataset with MVSEP ( Bandit Model )
The voice was always in music or effects
I had to retrain it 3 times with different datasets until it could be accurate enough
So the voice is hoarse as hell <:skullsob:1159372531992645662>
Use these settings ( Best i can get ):
P: 6 (For male), 0 (For female)
Index: 0.8
FR (Filter Radius): 7
RMS: 0.25
Protect Rate: 0.5
Model:
https://huggingface.co/cheir/b-block/resolve/main/b_block_v3.zip?download=true
Tags: No tags available
Download Link: https://huggingface.co/cheir/b-block/resolve/main/b_block_v3.zip?download=true Hosted on Hugging Face
Convert this model in EasyAIVoice
Listen across generated pitch samples, then Run. Hold Ctrl or Cmd to select multiple pitches.