Dataset Length: 29 Seconds
Model Architecture: v2
Target Sample Rate: 32k
Speaker_id: 0
Pitch Extraction Algorithm: Rmvpe
Pretrain Type: Original
Batch Size: 4
Epochs: 300
Step Number: 1500
Tags: huggingface, ai-model
Download Link: https://huggingface.co/MusicHunter/PSY_GangnamStyle_Intro_FilterLead/resolve/main/FilterLead_e300_s1500.zip?download=true Hosted on Hugging Face